JP2023028742A - Information processing device, information processing method and information processing program - Google Patents

Abstract

To make it possible to provide useful information about a user to be a target.SOLUTION: An information processing device 10 acquires information on a user, acquires location information of the user, generates an interest vector indicating a category of interest of the user at a visited place by using the information on the user and the location information of the user, generates a user vector indicating a category of interest of a new user at the visited place, and estimates the category of interest of the new user based on the interest vector and the user vector.SELECTED DRAWING: Figure 1

Description

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

2. Description of the Related Art Conventionally, various techniques have been proposed for analyzing a huge amount of data exchanged via the Internet from various aspects for the purpose of utilizing it in business scenes and the like. For example, there is known a technique of analyzing customers (or “users” as appropriate) in consideration of seasonal trends using purchase history data or the like.

JP 2016-143080 A

However, conventional techniques have room for improvement in providing useful information about target users.

In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes a first acquisition unit that acquires user information, a second acquisition unit that acquires position information of the user, and and a first generation unit that generates an interest vector indicating the category of interest of the user in the visited place using the information of the user and the location information.

Further, an information processing method according to the present invention is an information processing method executed by an information processing apparatus, comprising: a first obtaining step of obtaining user information; and a second obtaining step of obtaining location information of the user. and a first generating step of using the information of the user and the location information to generate an interest vector indicating categories of interest of the user at the visited location.

Further, an information processing program according to the present invention includes a first obtaining step of obtaining user information, a second obtaining step of obtaining positional information of the user, and a visiting site using the user information and the positional information. and a first generating step of generating an interest vector indicating the category of interest of the user at the location.

The present invention can provide useful information about target users.

FIG. 1 is a diagram illustrating an example of processing of an information processing system according to an embodiment. FIG. 2 is a block diagram illustrating a configuration example of the information processing apparatus according to the embodiment; FIG. 3 is a diagram illustrating an example of first generation processing according to the embodiment. FIG. 4 is a diagram illustrating an example of second generation processing according to the embodiment. FIG. 5 is a flowchart illustrating an example of the flow of overall processing according to the embodiment. FIG. 6 is a diagram illustrating an example of a hardware configuration;

Hereinafter, modes for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as embodiments) will be described in detail 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 this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[Embodiment]
Hereinafter, the processing of the information processing system 100 according to the embodiment, the configuration of the information processing apparatus 10, a specific example of processing, and the flow of processing will be described in order, and finally the effects of the present embodiment will be described.

[1. Processing of information processing system 100]
The processing of the information processing system (or the system as appropriate) 100 according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of processing of an information processing system according to an embodiment. In the following, a configuration example of the system 100, processing of the system 100, and effects of the system 100 will be described in this order.

(1-1. Configuration example of system 100)
The system 100 shown in FIG. 1 has an information processing device 10 , a user information database (DB) 20 , a location information DB 30 and a user terminal (appropriately new user) 40 . Here, the information processing device 10, the user information DB 20, the position information DB 30, and the user terminal 40 are connected to each other via a predetermined communication network (not shown) so as to be communicable by wire or wirelessly. The system 100 may include multiple information processing apparatuses 10 , multiple user information DBs 20 , multiple location information DBs 30 , and multiple user terminals 40 .

(1-1-1. Information processing device 10)
The information processing device 10 is a device that transmits and receives data to and from the user information DB 20, the position information DB 30, and the user terminal 40, and is realized by, for example, a server device, a cloud system, or the like. The example of FIG. 1 shows a case where the information processing device 10 is realized by a server device.

(1-1-2. User terminal 40)
The user terminal 40 is a device (computer) used by a user who browses web pages and performs Internet shopping on the web. The user terminal 40 accepts user operations. The user terminal 40 is realized by, for example, a smart phone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The example of FIG. 1 shows a case where the user terminal 40 is realized by a smart phone.

(1-2. Processing of system 100)
(1-2-1. Processing of step S1)
In this system 100, first, the information processing device 10 refers to the user information DB 20 and acquires user information (step S1). Here, the user information is information about the user, and in addition to the user's action history such as search history, browsing history, and purchase history on the user's website, the user's gender, age, occupation, place of residence, This information includes user attributes such as whether the user is married or unmarried and whether the user has children. Furthermore, the user information may be user screen information, biometric information, or the like collected via the user's terminal (not shown), and is not particularly limited. In addition, in the example of FIG. 1, the information processing apparatus 10 acquires user information from the user information DB 20, but may acquire the user information from a user's terminal (not shown) or another terminal.

As described in step S1 above, the information processing device 10 is a device that acquires user information.

(1-2-2. Processing of step S2)
In the system 100, secondly, the information processing device 10 refers to the position information DB 30 and acquires the user's position information (step S2). Here, the position information is information about the place visited by the user, and includes the address of the visited place, the name of the facility, the type and use of the facility, the user's staying time and the number of visits. Furthermore, the position information may be information associated with a user's action history, such as search history, browsing history, and purchase history, which are user information. In addition, in the example of FIG. 1, the information processing apparatus 10 acquires the position information from the position information DB 30, but it may be collected from a user's terminal (not shown) or other terminals. Furthermore, the information processing device 10 may acquire the position information from movement information such as a travel log of the automobile.

As described in step S2 above, the information processing device 10 is a device that acquires user position information. For example, the information processing device 10 is a device that acquires user position information from the user's movement history.

(1-2-3. Processing of step S3)
In the present system 100, thirdly, the information processing device 10 generates an interest vector indicating the category of the user's interest in the visited place from the acquired user information and position information (step S3). Here, an interest vector is information obtained by vectorizing information indicating a category in which the user has an interest, and is a trend of search words (search queries) input by the user, an action history in various services, and an action history based on the action history. This is information obtained by vectorizing estimated user attributes and the like. At this time, the information processing apparatus 10 may generate a vector by aggregating a plurality of pieces of user information for each specific visited place, or may generate a vector for each day of the week or time period as an interest vector for the visited place. Alternatively, Laplacian smoothing may be used to generate the vectors.

As described in step S3 above, the information processing device 10 is a device that uses user information and user location information to generate an interest vector that indicates a category of user interest in a visited place. For example, the information processing device 10 is a device that aggregates interest vectors of a plurality of users and generates an interest vector in a visited place. Further, the information processing device 10 is a device that aggregates interest vectors for each predetermined day of the week or time period and generates an interest vector for a visited place.

(1-2-4. Processing of step S4)
Fourthly, in the system 100, the information processing device 10 acquires user information of the new user from the user terminal 40 (step S4). Here, the new user is a user whose interest category (user's preference) is estimated. For example, a new user is a user visiting a specific location for the first time, but may be a user who has visited the location in the past. In addition, in the example of FIG. 1, the information processing apparatus 10 acquires the user information of the new user from the user terminal 40, but the information processing apparatus 10 may acquire the user information from the user information DB 20 or another terminal (not shown).

As described in step S4 above, the information processing device 10 is a device that acquires information on new users.

(1-2-5. Processing of step S5)
Fifthly, in the system 100, the information processing device 10 acquires the position information of the new user from the user terminal 40 (step S5). In addition, in the example of FIG. 1, the information processing apparatus 10 acquires the new user's location information from the user terminal 40, but it may acquire it from the location information DB 30 or another terminal (not shown). Furthermore, the information processing apparatus 10 may acquire the position information from movement information such as a driving log of the new user's car.

As described in step S5 above, the information processing device 10 is a device that acquires the position information of the new user. For example, the information processing device 10 is a device that acquires the new user's location information from the new user's movement history.

(1-2-6. Processing of step S6)
Sixthly, in the system 100, the information processing device 10 generates an interest vector (user vector) indicating a category in which the new user has an interest in the visited place from the acquired user information and location information of the new user ( step S6). Here, the information processing apparatus 10 may generate a vector for each home or a specific visited place as the user vector, which is the interest vector of the new user, or may generate a vector obtained by integrating (merging) vectors of a plurality of visited places. may be generated, or a vector for each day of the week or time period may be generated.

The information processing apparatus 10 may also calculate an orientation score indicating a common attribute obtained by combining the new user's demographic attribute (demographic attribute) and location information from the user vector of the new user at the visited location. . For example, the information processing apparatus 10 calculates an orientation score of [male, 40s, <address/latitude/longitude>]=0.64 as the “outdoor orientation score”. At this time, the information processing apparatus 10 may calculate an average score for each day of the week or time period as the orientation score for the visited place.

As described in step S6 above, the information processing device 10 is a device that generates a user vector that indicates the category of interest of the new user at the visited location. For example, the information processing device 10 is a device that generates a user vector at a visited location where a new user has stayed for a predetermined time or longer, and is a device that generates a user vector at a predetermined visited location among the visited locations. Further, the information processing device 10 is a device that generates a user vector for a predetermined day of the week or time period. Furthermore, the information processing device 10 is a device that aggregates user vectors at a plurality of visited locations.

(1-2-7. Processing of step S7)
In the present system 100, seventhly, the information processing apparatus 10 estimates the category of interest of the new user based on the generated interest vector and the user vector of the new user (step S7). At this time, the information processing apparatus 10 estimates the category of interest of the new user based on the similarity between the interest vector of the visited place and the user vector of the new user. Further, the information processing apparatus 10 estimates categories in which the new user is interested based on the orientation score.

Here, when judging similarity, the information processing apparatus 10 calculates a similarity indicating similarity on a rule basis, and assumes that a category in which the calculated similarity exceeds a predetermined threshold is of interest. good. Also, the information processing apparatus 10 may use a model. For example, the information processing apparatus 10 learns a model such as a DNN (Deep Neural Network) so that when a search word or the like is input at a specific visited place, information regarding categories in which the new user is interested is output. . Then, the information processing apparatus 10 may input information indicating the behavior of the new user to be determined to the learned model, and estimate the category of interest of the new user based on the output of the model.

As described in step S7 above, the information processing device 10 is a device that estimates the new user's interesting category based on the interest vector and the user vector.

(1-3. Effect of system 100)
In this system 100, the information processing device 10 refers to the user information DB 20 to acquire user information, refers to the location information DB 30 to acquire user location information, and uses the acquired user information and location information to determine Generate an interest vector that indicates the user's interests. In addition, the information processing apparatus 10 acquires the user information and location information of the new user from the user terminal 40, and from the acquired user information and location information of the new user, the information processing device 10 generates a user vector indicating the interest of the new user in the visited place. Generate. Further, the information processing apparatus 10 estimates the category of interest of the new user based on the generated interest vector and the user vector of the new user. Therefore, the system 100 can provide useful information about the target user.

That is, the system 100 can collect not only the interests collected at the user's home, etc., but also the interests and intentions whose characteristics are clarified at places where the user stops by, such as shopping malls and hospitals. In addition, the present system 100 can collect preferences reflecting information on user's life events such as marriage and childbirth by taking into account places to drop by, days of the week, and time slots.

Furthermore, the present system 100 can easily reveal the preferences of a plurality of users in a specific place by vectorizing user information and location information. For example, the system 100 can reveal a user's health preferences at a spot in a hospital. In addition to the user's purpose, the system 100 can also reveal the influence of places, such as attracting customers. For example, the present system 100 uses information that is difficult to analyze from the user's SNS (Social Networking Service) evaluation, etc., such as a restaurant near a station or a convenience store located halfway between the city center and a tourist spot. can be collected as information that can be used for marketing.

[2. Configuration of information processing device 10]
The configuration of the information processing apparatus 10 according to the embodiment will be described with reference to FIG. FIG. 2 is a block diagram showing a configuration example of the information processing device 10 according to the embodiment. As shown in FIG. 2 , the information processing device 10 has a communication section 11 , a storage section 12 and a control section 13 . The information processing apparatus 10 includes an input unit (for example, a keyboard, a mouse, etc.) for receiving various operations from an administrator of the information processing apparatus 10, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. may have.

(2-1. Communication unit 11)
The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 11 is connected to a predetermined communication network (network) by wire or wirelessly, and transmits and receives information to and from the user information DB 20 , the location information DB 30 and the user terminal 40 .

(2-2. Storage unit 12)
The storage unit 12 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 12 according to the embodiment has, as shown in FIG. 2, a user information storage unit 12a, a position information storage unit 12b, an interest vector storage unit 12c, and a user vector storage unit 12d. The storage unit 12 stores various information referred to when the control unit 13 operates and various information acquired when the control unit 13 operates.

(2-2-1. User information storage unit 12a)
The user information storage unit 12a stores various types of information about users acquired from past users and new users 40 . For example, the user information storage unit 12a stores, in addition to the user's action history such as search history, browsing history, and purchase history on the website, the user's sex, age, occupation, place of residence, marital status, number of children, etc. Information including user attributes such as presence/absence, user terminal screen information, biometric information, and the like is stored.

(2-2-2. Position information storage unit 12b)
The position information storage unit 12b stores user position information acquired from past users and new users 40 . For example, the position information storage unit 12b stores the address of the visited place, the name of the facility, the type and use of the facility, the length of stay, the number of visits, etc., as the information about the place visited by the user.

(2-2-3. Interest vector storage unit 12c)
The interest vector storage unit 12c stores an interest vector that indicates the category of the user's interest in the visited place. For example, the interest vector storage unit 12c stores an interest vector for each visited place generated by the first generation unit 13c. Further, the interest vector storage unit 12c may store an interest vector in which a plurality of pieces of user information are aggregated for each specific visited place, or an interest vector classified by day of the week or time zone. Furthermore, the interest vector storage unit 12c may store the number of aggregated interest vectors together with the aggregated interest vectors.

(2-2-4. User vector storage unit 12d)
The user vector storage unit 12d stores user vectors indicating categories in which new users are interested. For example, the user vector storage unit 12d stores the user vector and orientation score for each visited place generated by the second generation unit 13d. The user vector storage unit 12d also stores user vectors generated for each home or specific visited place, user vectors obtained by integrating vectors of a plurality of visited places, and user vectors classified by day of the week and time period. You may

(2-3. Control unit 13)
The control unit 13 executes various programs (equivalent to an example of an information processing program) stored in a storage device inside the information processing apparatus 10 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. It is realized by being executed as a work area. Also, the control unit 13 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 13 includes a first acquisition unit 13a, a second acquisition unit 13b, a first generation unit 13c, a second generation unit 13d, and an estimation unit 13e. Realize or perform a function or action. Note that the internal configuration of the control unit 13 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it performs information processing to be described later. Moreover, the connection relationship between the processing units of the control unit 13 is not limited to the connection relationship shown in FIG. 2, and may be another connection relationship.

(2-3-1. First acquisition unit 13a)
The first acquisition unit 13a acquires user information. To explain the information collection source, for example, the first acquisition unit 13a acquires user information from the user information DB 20 . Also, the first acquisition unit 13 a acquires user information from the new user 40 .

On the other hand, to explain the contents of the information, for example, the first acquisition unit 13a acquires the user's search history, browsing history, purchase history, user attributes, etc. as user information. Furthermore, as user information, user screen information, biometric information, and the like may be obtained via the user's terminal.

Note that the first acquisition unit 13a may acquire vectorized user information. Further, the first acquisition unit 13a stores the acquired user information in the user information storage unit 12a.

(2-3-2. Second acquisition unit 13b)
The second acquisition unit 13b acquires user position information. To explain the source of information collection, for example, the second acquisition unit 13b acquires user information from the position information DB 30 . Also, the second acquisition unit 13 b acquires user information from the new user 40 .

On the other hand, to explain the content of the information, for example, the second acquisition unit 13b acquires position information from the movement history of the user. That is, the second acquisition unit 13b acquires the address of the place visited by the user, the name of the facility, the length of stay of the user, the number of visits, and the like from the travel information such as the travel log of the automobile.

Note that the second acquisition unit 13b may acquire vectorized position information of the user. The second acquisition unit 13b also stores the acquired location information of the user in the location information storage unit 12b.

(2-3-3. First generator 13c)
The first generation unit 13c generates an interest vector indicating the category of interest of the user in the visited place using the user's information and the location information. To explain the interest vector, for example, the first generation unit 13c converts the acquired user information and user position information into a user information vector and a position information vector in a cosine similarity space, an inner product space, a Euclidean distance space, or the like. Transform and generate an interest vector from the above vectors.

To explain the method of collecting interest vectors, for example, the first generating unit 13c collects interest vectors of a plurality of users and generates interest vectors in visited places. That is, the first generating unit 13c generates an interest vector by summing up user interest vectors for each location visited by a plurality of users, such as “hospital a” and “shopping mall b”. At this time, the first generation unit 13c may total interest vectors of a plurality of users or average the interest vectors.

The first generation unit 13c also aggregates interest vectors for each predetermined day of the week or time period to generate an interest vector for a visited place. That is, the first generating unit 13c generates, for example, an interest vector for "Hospital a" on "Sunday" and an interest vector for "Shopping mall b" on "Morning". Furthermore, the first generation unit 13c may generate an interest vector for each calendar such as "months" from January to December and "seasons" from spring, summer, autumn and winter.

Furthermore, the first generation unit 13c may aggregate interest vectors using Laplace smoothing. That is, the first generation unit 13c aggregates interest vectors for each visited place, day of the week, and time zone, and can aggregate interest vectors without reducing the total number of data and reducing estimation accuracy.

Note that the first generation unit 13c stores the generated interest vector in the interest vector storage unit 12c.

(2-3-4. Second generator 13d)
The second generation unit 13d generates a user vector indicating the category of interest of the new user at the visited location. To explain the visited place for generating the user vector, for example, the second generating unit 13d generates the user vector at the visited place where the new user has stayed for a predetermined time or longer. The second generation unit 13d also generates a user vector at a predetermined visited place among the visited places. That is, the second generation unit 13d may generate, for example, a vector at the home of the new user as the user vector, or may generate a vector at a restaurant other than the home that the new user frequently visits as the user vector.

To explain the method of collecting interest vectors, the second generation unit 13d generates user vectors for a predetermined day of the week or time slot. That is, the first generating unit 13c generates, for example, a user vector at home on "Sunday" and a user vector at "restaurant c" on "morning". Furthermore, the first generating unit 13c may generate a user vector for each calendar such as "months" of January to December, "seasons" of spring, summer, autumn and winter.

In addition, the second generation unit 13d aggregates user vectors at a plurality of visited locations to generate a user vector. That is, the first generation unit 13c, for example, aggregates the user vectors of "hospital a", "shopping mall b", and "restaurant c", and generates an integrated user vector. At this time, the first generation unit 13c may total the user vectors of the plurality of visited locations, or average the user vectors.

Furthermore, the second generation unit 13d may calculate an orientation score from the user vector. For example, the second generating unit 13d sets the new user's "outdoor orientation score" to 0 from a user vector of [male, 40s, <address/latitude/longitude>] as the new user's information and the new user's location information. .64. At this time, the second generation unit 13d may aggregate a plurality of orientation scores to calculate an average score, or may calculate an orientation score for each day of the week or time zone, as the orientation score for the visited place.

The second generation unit 13d stores the generated user vector in the user vector storage unit 12d.

(2-3-5. Estimation unit 13e)
Based on the interest vector and the user vector, the estimation unit 13e estimates the new user's interesting category. To explain the estimation method, for example, the estimation unit 13e estimates the category of interest of the new user based on the similarity between the interest vector in the visited place and the user vector of the new user. That is, the estimation unit 13e calculates, for example, the distance (eg, cosine similarity, inner product distance, Euclidean distance) between the interest vector and the user vector, and estimates the new user's interesting category based on the calculation result.

Describing the categories to be estimated, the estimation unit 13e estimates, for example, the interests of the new user, such as "outdoors" and "health". In addition, the estimation unit 13e estimates, for example, a new user's interest category in a specific location, such as "dining" in "shopping mall b".

[3. Specific example of processing]
A specific example of the processing according to the embodiment will be described with reference to FIGS. 3 and 4. FIG. FIG. 3 is a diagram illustrating an example of first generation processing according to the embodiment. FIG. 4 is a diagram illustrating an example of second generation processing according to the embodiment. A specific example of the first generation process according to the embodiment and a specific example of the second generation process will be described below in this order.

(3-1. Specific example of first generation processing)
A specific example of the first generation process according to the embodiment will be described with reference to FIG. Below, the aggregation method 1 and the aggregation method 2 will be described in order.

(3-1-1. Tabulation method 1)
Information processing apparatus 10 generates an interest vector of 'user A' in (A-1) which is the home of 'user A', and generates an interest vector of 'user B' in (B-1) which is the home of 'user B'. Generate an interest vector. That is, in aggregation method 1, the information processing apparatus 10 can generate an interest vector only at a specific location such as each user's home, and collect user preferences.

(3-1-2. Tabulation method 2)
The information processing apparatus 10 detects not only the interest vector of "user A" at home of "user A" (A-1), but also the stopping points of "user A" (A-2), (A-3 ) and (A-4) also generate the interest vector of “user A”. Similarly, the information processing apparatus 10 obtains not only the interest vector of "user B" at home (B-1) of "user B" but also the interest vector at "user B"'s stop-over point (B-2). also generates an interest vector for 'user B'.

Here, assuming that (A-2) and (B-2) are the same drop-off point, for example, "Hospital a", the information processing apparatus 10 determines that "User A" and "User By aggregating the interest vectors of "B", it becomes possible to reveal the preferences of a plurality of users in "Hospital a". That is, in aggregation method 2, the information processing apparatus 10 can generate interest vectors not only for specific bases but also for visited places, and can collect user preferences that differ from place to place.

Furthermore, the information processing apparatus 10 can also generate an interest vector in consideration of the "strength" of the interest vector, using the number of interest vectors to be aggregated when the interest vector is aggregated as described above. That is, in counting method 2, the information processing apparatus 10 can collect not only the user's orientation (direction of interest) but also the strength of the orientation (concentration of interest).

(3-2. Specific example of second generation processing)
A specific example of the second generation process according to the embodiment will be described with reference to FIG. Reference method 1, reference method 2, and reference method 3 will be described below in this order.

(3-2-1. Reference method 1)
The information processing apparatus 10 generates a user vector of "user C" in the home (C-1) of "user C" who is a new user, and determines the orientation of "user C" based on the generated user vector. refer. That is, in reference method 1, the information processing apparatus 10 can estimate the new user's orientation based only on the user vector at a specific site such as the new user's home.

(3-2-2. Reference method 2)
The information processing apparatus 10 detects not only the interest vector of "user C" at home of "user C" (C-1), but also the stopping points of "user C" (C-2) and (C-3). ) also generates a user vector of “user C” and refers to the orientation of “user C” based on the generated user vector.

Here, assuming that (C-2) is the same "hospital a" as (A-2) and (B-2) described above, the information processing apparatus 10 It becomes possible to refer to the intention. That is, in the reference method 2, the information processing apparatus 10 can estimate the preferences of the new user that differ from place to place based on the user vector not only at the specific site but also at the visited place.

(3-2-3. Reference method 3)
The information processing apparatus 10 integrates (merges) the user vectors generated at the home and stop-off points (C-1), (C-2), and (C-3) of "user C", and generates a user vector Based on this, the intention of "user C" is referred to. That is, in reference method 3, the information processing apparatus 10 can estimate the new user's overall orientation based on a plurality of user vectors at the new user's specific base and visited place.

[4. Process flow]
The overall flow of information processing will be described with reference to FIG. FIG. 5 is a flow chart showing the overall flow of processing according to the embodiment. Below, after explaining the flow of the whole process, the outline of each process will be explained.

(4-1. Overall processing flow)
First, the first acquisition unit 13a of the information processing device 10 executes a first acquisition process (step S101). Second, the second acquisition unit 13b of the information processing device 10 executes a second acquisition process (step S102). Third, the first generation unit 13c of the information processing device 10 executes a first generation process (step S103). Fourth, the second generation unit 13d of the information processing device 10 executes a second generation process (step S104). Fifth, the estimation unit 13e of the information processing device 10 executes estimation processing (step S105), and ends the processing. Note that the above steps S101 to S105 can also be performed in a different order. Also, some of the above steps S101 to S105 may be omitted.

(4-2. Flow of each process)
(4-2-1. Flow of first acquisition process)
First, the first acquisition process by the first acquisition unit 13a will be described. In the first acquisition process, the first acquisition unit 13 a acquires user information (user's action history, user attributes, etc.) from the user information DB 20 or the new user 40 .

(4-2-2. Flow of second acquisition process)
Secondly, the second acquisition process by the second acquisition unit 13b will be described. In the second acquisition process, the second acquisition unit 13b acquires the user's location information (address, facility name/type/use, etc.) from the location information DB 30 or the new user 40. FIG.

(4-2-3. Flow of first generation processing)
Thirdly, the first generation processing by the first generation unit 13c will be described. In the first generation process, the first generation unit 13c generates an interest vector indicating the category of the user's interest in the visited place from the acquired user information and position information. Here, the first generation unit 13c can generate an interest vector obtained by aggregating a plurality of pieces of user information for each specific visited place, and an interest vector for each day of the week and time period.

(4-2-4. Flow of second generation processing)
Fourthly, the second generation processing by the second generation unit 13d will be described. In the second generation process, the second generation unit 13d generates a user vector indicating the category of interest of the new user in the visited location from the acquired user information and location information of the new user. Here, the second generation unit 13d can generate a user vector for each home or specific visited place, a user vector obtained by integrating vectors of a plurality of visited places, and a user vector for each day of the week or time period. The second generation unit 13d can also calculate the new user's orientation score from the user vector.

(4-2-5. Flow of estimation processing)
Fifth, the estimation processing by the estimation unit 13d will be described. In the estimating process, the estimating unit 13d estimates categories in which the new user is interested based on the generated interest vector and the new user's user vector.

[5. Effect of Embodiment]
First, in the process according to the present embodiment described above, user information is acquired, user location information is acquired, and using the user information and the user location information, categories of interest of the user in the visited place are determined. Generate an interest vector that indicates . Therefore, in this process, useful information regarding the target user can be provided.

Second, in the process according to the present embodiment described above, a user vector indicating the new user's interest category in the visited place is generated, and based on the interest vector and the user vector, the new user's interest category is estimated. do. Therefore, in this process, it is possible to provide useful information about the target user by estimating the categories of interest of the new user at the visited location.

Third, in the processing according to the present embodiment described above, position information is acquired from the movement history of the user. Therefore, in this process, movement information can be effectively collected, and useful information regarding the target user can be provided.

Fourthly, in the processing according to the present embodiment described above, interest vectors of a plurality of users are aggregated to generate an interest vector in a visited place. Therefore, in this process, it is possible to collect information on visited places from a plurality of users, and to provide useful information regarding target users.

Fifthly, in the process according to the present embodiment described above, the interest vector is aggregated for each predetermined day of the week or time slot to generate the interest vector for the visited place. Therefore, in this process, it is possible to effectively collect information on the visited place, and to provide useful information regarding the target user.

Sixthly, in the processing according to the present embodiment described above, a user vector is generated for a visited place where a new user has stayed for a predetermined time or longer. Therefore, in this process, it is possible to refer to information on more important visited places, and to provide useful information regarding the target user.

Seventh, in the processing according to the present embodiment described above, a user vector is generated at a predetermined visited place among the visited places. Therefore, in this process, it is possible to flexibly refer to the information on the visited place, and to provide useful information regarding the target user.

Eighth, in the processing according to the present embodiment described above, a user vector for a predetermined day of the week or time period is generated. Therefore, in this process, it is possible to effectively refer to the information on the visited place, and to provide useful information regarding the target user.

Ninthly, in the processing according to the present embodiment described above, user vectors at a plurality of visited locations are aggregated to generate user vectors. Therefore, in this process, it is possible to efficiently refer to the information on the visited place, and to provide useful information regarding the target user.

[Modification of Embodiment]
Processing of the information processing system according to the modification of the embodiment and effects of the modification will be described below. Note that the configuration of the information processing apparatus 10 according to this modified example, a specific example of processing, and the flow of processing are common to those of the above-described embodiment, so description thereof will be omitted.

[1. Processing of information processing system]
Below, after explaining the difference from the information processing system 100 according to the above-described embodiment, the processing of the information processing system according to this modified example will be explained.

(1-1. Difference from System 100)
In the information processing system 100 according to the above-described embodiment, for example, the user's preferences can be analyzed using the purchase history data and the like along with the user's location information, and useful information regarding new users who are marketing targets can be provided. That is, the information processing system 100 described above is used by a product or service provider to distribute advertisements to the target users to induce purchase intentions, or to send direct mails of new products. used for

On the other hand, in the information processing system according to this modified example, based on the past user's intentions at a specific visited place that has been analyzed, it is possible to provide a new user with useful information about the visited place in response to a new user's request. can be done. That is, in the information processing system according to the present modification, for example, a new user inputs user information and location information into an API (application programming interface) that presents an orientation (hereinafter referred to as an “orientation API”), and the orientation API visits the user. By outputting the information of the categories of interest of the new user in the place, the new user can use it directly.

(1-2. System processing)
Processing of the information processing system according to this modification will be described below in the order of information input processing, orientation estimation processing, and information output processing.

(1-2-1. Information input processing)
In the information processing system according to this modified example, the new user inputs user information and user location information to the intention API based on the operation of the user terminal 40 (information input processing) as follows. That is, the new user inputs user attributes (demographic attributes), such as the user's gender, age, occupation, and place of residence, to the preference API. Also, the new user inputs the new user's location information acquired from the driving log of the car, for example, to the intention API. Note that the new user may input the user information stored in a predetermined DB or the user's location information to the intention API by operating the user terminal 40 .

(1-2-2. Intention estimation process)
In the information processing system according to the present modification, the information processing apparatus 10 estimates categories in which the new user has an interest based on the interest vectors of the places visited by the user in the past (intention estimation processing), as described below. ). That is, for example, the information processing apparatus 10 refers to the user information DB 20 to acquire user information, refers to the location information DB 30 to acquire user location information, and uses the acquired user information and location information to determine the location of the user at the visited location. Generate an interest vector that indicates the interests of . Further, the information processing apparatus 10 acquires the new user's user information and the user's location information input to the intention API, and indicates the new user's interest in the visited place from the acquired new user's user information and location information. Generate a user vector. Further, the information processing apparatus 10 estimates the category of interest of the new user based on the generated interest vector and the user vector of the new user.

Note that the orientation estimation processing of the information processing system described above is the same as [1. Processing of information processing system 100] (1-2. Processing of system 100), so detailed description thereof will be omitted.

(1-2-3. Information output processing)
In the information processing system according to this modified example, the orientation API provides various types of information to the new user based on the user's orientation estimated by the information processing apparatus 10 (information output processing). That is, for example, if the new user's visited place is "shopping mall b" and the new user's estimated category of interest is "meals", the oriented API is "shopping mall b". Information on eating and drinking establishments opened in the area is provided to a new user via a user terminal 40.例文帳に追加

[2. Effect of Modification of Embodiment]
In the process according to the present modification described above, the information processing apparatus 10 estimates the user's preference for the place visited by the user based on the user information actively input by the new user and the user's position information. It is possible to provide information that matches the intention. Therefore, the information processing apparatus 10 can provide useful information about the user after reflecting the range of information desired by the user and the timing of providing the information.

[Hardware configuration]
Also, the information processing apparatus 10 according to the above-described embodiments is implemented by, for example, a computer 1000 configured as shown in FIG. The information processing apparatus 10 will be described below as an example. FIG. 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus 10. As shown in FIG. Computer 1000 has CPU 1100 , RAM 1200 , ROM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

HDD 1400 stores programs executed by CPU 1100 and data used by these programs. Communication interface 1500 receives data from another device via a predetermined communication network, sends the data to CPU 1100, and transmits data generated by CPU 1100 to another device via a predetermined communication network.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing apparatus 10 according to the first embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 13 by executing programs loaded on the RAM 1200 . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via a predetermined communication network.

〔others〕
Although the embodiments of the present application have been described above, the present invention is not limited by the contents of these embodiments. In addition, the components described above include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those within the so-called equivalent range. Furthermore, the components described above can be combined as appropriate. Furthermore, various omissions, replacements, or modifications of components can be made without departing from the gist of the above-described embodiments.

Further, among the processes described in the above embodiments, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being performed manually can be performed manually. All or part of this can also be done automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the illustrated one, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

For example, the information processing apparatus 10 described above may be implemented by a plurality of server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform or the like using an API, network computing, or the like. .

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing content.

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

10 information processing device 11 communication unit 12 storage unit 12a user information storage unit 12b position information storage unit 12c interest vector storage unit 12d user vector storage unit 13 control unit 13a first acquisition unit 13b second acquisition unit 13c first generation unit 13d 2 generating unit 13e estimating unit 20 user information DB
30 Location information DB
40 user terminal (new user)
100 information processing system

Claims (11)

a first acquisition unit that acquires user information;
a second acquisition unit that acquires location information of the user;
a first generation unit that generates an interest vector indicating a category of interest of the user in a visited place using the information of the user and the location information;
An information processing device comprising: a second generation unit that generates a user vector indicating categories of interest of the new user at the visited location;
an estimation unit that estimates a category of interest of the new user based on the interest vector and the user vector;
The information processing apparatus according to claim 1, further comprising: The second acquisition unit acquires the location information from the movement history of the user.
The information processing apparatus according to claim 1, characterized by: The first generation unit aggregates the interest vectors of the plurality of users and generates the interest vector in the visited place.
The information processing apparatus according to claim 1, characterized by: The first generation unit aggregates the interest vector for each predetermined day of the week or time period to generate the interest vector for the visited place.
The information processing apparatus according to claim 1, characterized by: The second generation unit generates the user vector at the visited location where the new user has stayed for a predetermined time or longer.
3. The information processing apparatus according to claim 2, characterized by: The second generation unit generates the user vector at a predetermined visited place among the visited places,
3. The information processing apparatus according to claim 2, characterized by: The second generation unit generates the user vector for a predetermined day of the week or time period.
8. The information processing apparatus according to claim 2 or 7, characterized by: The second generation unit aggregates the user vectors at a plurality of the visited locations and generates the user vector.
3. The information processing apparatus according to claim 2, characterized by: An information processing method executed by an information processing device,
a first obtaining step of obtaining user information;
a second obtaining step of obtaining location information of the user;
a first generating step of generating an interest vector indicating a category of interest of the user at a visited location using the information of the user and the location information;
An information processing method comprising: a first obtaining step of obtaining user information;
a second obtaining step of obtaining location information of the user;
a first generation step of generating an interest vector indicating categories of interest of the user at a visited location using the information of the user and the location information;
An information processing program characterized by causing a computer to execute

Images