Information processing device, information processing method, and information processing program

Abstract

To properly provide information on an object in which a user may be interested.SOLUTION: An information processing device comprises a first identification unit, a second identification unit, and a provision unit. The first identification unit identifies a first object which has become to be included in an interest range of a user in an interest space in which each of a plurality of objects is indicated by a vector according to relevance to interests of a plurality of users and the vector is updated per prescribed period. The second identification unit identifies a second object which was similar in the past to the first object identified by the first identification unit. The provision unit provides the user with information on the second object identified by the second identification unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, various techniques for providing information to users have been proposed. For example, Patent Document 1 proposes a technique for delivering advertisements according to a quadrant to which a category in which a user has an interest belongs, out of a plurality of quadrants into which categories in which the user has an interest are classified based on factors related to commercial transactions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-099631 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is room for improvement in the above-mentioned conventional technology, which provides information depending on the quadrant, and there is room for improvement in terms of providing information flexibly, and it is desired to provide information on subjects that may be of interest to the user appropriately.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can appropriately provide information on subjects that may be of interest to a user. [Means for solving the problem]

[0006] The information processing device according to the present application includes a first identification unit, a second identification unit, and a providing unit. The first identification unit identifies a first object that has become included in a user's range of interests in an interest space in which each of multiple objects is represented by a vector according to relevance to the interests of multiple users and the vector is updated every predetermined period. The second identification unit identifies a second object that was similar to the first object identified by the first identification unit in the past. The providing unit provides the user with information about the second object identified by the second identification unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide appropriate information on subjects that may be of interest to a user. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system including the information processing device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a content table stored in the content storage unit of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of interest space information stored in the interest space information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a first target identified by a first identification unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a second target identified by a second identification unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a second target identified by the second identification unit of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a flowchart showing a processing procedure by the processing unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, 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 device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. The information processing according to the embodiment is processing executed by an information processing device 1, and includes search processing, model generation processing, and information provision processing.

[0011] First, the search process and the model generation process will be described. n For example, the information processing device 1 has a search target database, which is a database in which search targets are indexed and stored, and executes a search process using information from the search target database, etc. For example, the information from the search target database is stored in a storage unit 11 (see FIG. 2).

[0012] As shown in FIG. 1, users U1 to U n Terminal devices 21-2 n By operating the terminal devices 21-2 nThe terminal devices 21-2 perform a process of transmitting a search query to the information processing device 1. n (Steps S11 to S1 n ) where n is an integer greater than or equal to 2.

[0013] For example, in step S11, the user U1 operates the terminal device 21 to cause the terminal device 21 to execute a process of transmitting a search query from the terminal device 21 to the information processing device 1. n In this case, user U n Terminal device 2 n By operating the terminal device 2 n The terminal device 2 performs a process of transmitting a search query to the information processing device 1. n In the following, users U1 to U n When referring to each of the terminal devices 21 to 22 without distinguishing them individually, they are referred to as a user U, and n When referring to each of these without distinguishing them individually, they may be referred to as terminal devices 2.

[0014] The search query includes one or more search terms (search keywords) input by the user U into the terminal device 2. For example, if the user U inputs "sneakers" into the terminal device 2 as one or more search terms, the search query includes "sneakers." Also, if the user U inputs "women's sneakers" into the terminal device 2 as one or more search terms, the search query includes "women's sneakers." "Women's sneakers" includes the two search terms "sneakers" and "women's," separated by a space.

[0015] The information processing device 1 includes terminal devices 21-2 n The search queries sent from the respective n For example, the information processing device 1 receives a search query from the terminal device 21 in step S21, and n And terminal device 2 n Accepts search queries from.

[0016] Next, the information processing device 1 performs steps S21 to S2n The search process is performed based on the received search query (steps S31 to S3 n For example, in step S31, the information processing device 1 executes a search process to search the search target database for an object corresponding to one or more search terms included in the search query transmitted from the terminal device 21 and accepted in step S21. n In the terminal device 2 n Step S2 n The search process is performed to search the search target database for targets corresponding to one or more search terms included in the received search query.

[0017] Next, the information processing device 1 performs steps S31 to S3 n The terminal devices 21-2 display search results that are the results of the search processing. n (Steps S41 to S4 n For example, in step S41, the information processing device 1 transmits the search results, which are the results of the search process in step S31, to the terminal device 21. n In step S3 n The search results, which are the results of the search process, are displayed on the terminal device 2. n Send to.

[0018] Next, the information processing device 1 performs steps S21 to S2 n An interest model is generated based on the search query received (step S5). The interest model generated in step S5 is a model that receives information indicating each of a plurality of targets as input and outputs an M-dimensional vector. M is, for example, an integer in the range of 500 to 2000, but is not limited to this example. The M-dimensional vector may be represented by, for example, a distributed representation, or may be represented by a representation other than the distributed representation. Hereinafter, the M-dimensional vector will be simply referred to as a vector.

[0019] In step S5, the information processing device 1 generates an interest model, which is a trained model, by learning the characteristics of each of the multiple search terms, regarding two or more search terms that satisfy a predetermined condition as having similar characteristics. The two or more search terms that satisfy the predetermined condition are multiple search terms included in the same search query, or search terms included in multiple search queries sent from the terminal device 2 by the same user U within a predetermined time period.

[0020] The information processing device 1 performs learning using two or more search terms that satisfy predetermined conditions as learning data so that the vectors of the two or more search terms are similar to each other. The information processing device 1 can also treat search terms included in search queries sent from the terminal device 2 by the same user U as two or more search terms that satisfy the predetermined conditions, regardless of when the search queries were sent.

[0021] A search term is composed of one search keyword, but may be composed of two or more search keywords. For example, if the search query includes the character string "sneakers for women," the information processing device 1 treats "sneakers" and "women's" as different search terms, but can also treat the set of "sneakers" and "women's" as a single search term.

[0022] The information processing device 1 generates an interest model that outputs a vector (e.g., a distributed representation) from information indicating a target such as a search term using, for example, a technology of a deep structured semantic model (DSSM) that uses a long short-term memory (LSTM), which is a type of recurrent neural network (RNN), also known as a recursive neural network, for vector generation (e.g., distributed representation generation). Note that the method of generating an interest model that outputs a vector from information indicating a target is not limited to the above-mentioned example.

[0023] The information processing device 1 generates an interest model for each predetermined period TA. For example, if the predetermined period TA is one month, the information processing device 1 generates an interest model for each month of January, February, March, and so on in 2022.

[0024] Next, the information provision process will be described. The information processing device 1 identifies the interest range of each user U in the interest space (step S6). In the interest space, each of a plurality of objects is represented by a vector according to the relevance to the interests of a plurality of users U. In the interest space, the objects represented by the vectors are not limited to the objects represented by the search terms, and may be objects other than the objects represented by the search terms.

[0025] The information processing device 1 inputs information indicating the target into the interest model generated in step S5, and performs a process for each target to obtain the target vector output from the interest model, thereby generating an interest space including the vector of each target. The information processing device 1 generates an interest space for each period TA, for example, using the interest model for each period TA.

[0026] Then, the information processing device 1 inputs the search terms contained in multiple search queries sent from the terminal device 2 by the same user U into the interest model generated in step S5, and performs a process for each search term to obtain the vector of the search terms output from the interest model.

[0027] The information processing device 1 calculates an average vector by averaging vectors of search terms included in multiple search queries sent from the terminal device 2 by the same user U, and determines the calculated average vector as the user interest vector. Then, the information processing device 1 identifies a range similar to the user interest vector as the interest range of each user U. Note that the information processing device 1 can also calculate the average vector by, for example, weighting the vector of a search term more heavily for a search term in a search query that is received more recently.

[0028] The information processing device 1 identifies the range of interests of each user U for each period TA using an interest model for each period TA. For example, the information processing device 1 identifies the range of interests for each user U for the period TA based on multiple search queries sent by the same user U from the terminal device 2 within the period TA.

[0029] Next, the information processing device 1 identifies a first object that has become included in the range of interests of the user U in the interest space (step S7). Then, the information processing device 1 identifies a second object that was similar to the first object identified in step S7 in the interest space in the past (step S8). Then, the information processing device 1 provides the user U with information on the second object identified in step S8 (step S9). The processes of steps S6 to S9 are performed for each user U.

[0030] For example, assume that the generation cycle of an interest model is one month, and the interest model for February 2022 is the most recent interest model. Also assume that the interest space for January 2022 is generated using the interest model for January 2022, and the interest space for February 2022 is generated using the interest model for February 2022.

[0031] Furthermore, in the interest space in January 2022, the target "tapioca" and the target "maritozzo" are similar to each other, but the target "tapioca" and the target "maritozzo" are not included in the range of user U1's interests. Furthermore, in the interest space in February 2022, the target "maritozzo" continues to be not included in the range of user U1's interests, but the target "tapioca" is included in the range of user U1's interests.

[0032] In this case, the information processing device 1 identifies the target "tapioca" as the first target and the target "maritozzo" as the second target. Then, the information processing device 1 provides information on the target "maritozzo" identified as the second target to the user U1.

[0033] In this way, the information processing device 1 provides the user U with information on a second object that was similar in the past to a first object that has come to be included in the range of interests of the user U in the interest space. This allows the information processing device 1 to appropriately provide information on objects that may interest the user U.

[0034] [2. Information Processing System Configuration] 2 is a diagram showing an example of the configuration of an information processing system including an information processing device 1 according to an embodiment. As shown in FIG. 2, the information processing system 100 includes an information processing device 1 and a plurality of terminal devices 21 to 22. n The information processing device 1 and the plurality of terminal devices 21-2 n are communicably connected via a network N by wire or wirelessly.

[0035] The information processing device 1 is an information processing device capable of communicating with various devices via a predetermined network N such as the Internet, and is realized by, for example, a server device or a cloud system. For example, the information processing device 1 is connected to various other devices via the network N so as to be able to communicate with them.

[0036] The information processing device 1 also provides online services such as web services to the terminal device 2 of each user U. For example, the information processing device 1 provides online services such as SNS (Social Networking Service), electronic commerce (EC) sites, posting sites, electronic payments, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route searches, route guidance, line information, operation information, and weather forecasts, in addition to the search service and information provision service described above. The information processing device 1 can also act as an intermediary for online services by cooperating with various servers that provide the online services described above.

[0037] The terminal device 2 is an information processing device used by a user U to access content such as web pages displayed in a browser or content for applications. For example, the terminal device 2 is a desktop personal computer (PC), a notebook PC, a tablet terminal, a mobile phone, a personal digital assistant (PDA), etc. Note that the terminal device 2 is not limited to the above-mentioned examples and may be, for example, a smart watch or a wearable device.

[0038] 3. Configuration of Information Processing Device 1 The following describes an example of the functional configuration of the information processing device 1. As shown in FIG.

[0039] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 may be connected to terminal devices 21 to 22. n and transmits and receives information between them via network N.

[0040] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element 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 11 also has a search information storage unit 20, a user information storage unit 21, a content storage unit 22, and an interest space information storage unit 23.

[0041] 3.2.1. Search Information Storage Unit 20 The search information storage unit 20 stores information on a plurality of search targets provided by the information processing device 1 in the search service. For example, the search information storage unit 20 stores a search target database, which is a database in which each of a plurality of search targets is indexed and stored.

[0042] The information to be searched is, for example, information on various contents such as web pages collected by a crawler, etc. The information to be searched stored in the search information storage unit 20 is, but is not limited to, the URL (Uniform Resource Locator) and summary of the content.

[0043] 3.2.2. User Information Storage Unit 21 The user information storage unit 21 stores information about users U1 to U n 3 is a diagram showing an example of a user information table stored in the user information storage unit 21 of the information processing device 1 according to the embodiment.

[0044] As shown in FIG. 3, the user information table stored in the user information storage unit 21 includes information such as a "user ID (identifier)," "user name," "attributes," and "search history" for each user U. The "user ID" is identification information unique to each user U. The "user name" is information indicating the name of the user U.

[0045] "Attributes" is information indicating the attributes of user U. The attributes of user U include demographic attributes or psychographic attributes of user U. Demographic attributes are demographic attributes of user U. Psychographic attributes are attributes that indicate user U's values, lifestyle, personality, interests, etc.

[0046] In the example shown in FIG. 3, the demographic attributes of user U include information such as "gender" and "age." "Gender" is information indicating the gender of user U, and "age" is information indicating the age of user U. Note that the demographic attributes of user U further include, for example, user U's job title, job responsibilities, annual income, address, commuting route, training history, family composition, etc. User U's preferences include, for example, user U's level of interest in each of items such as clothes, travel, cars, motorcycles, computers, and lunch.

[0047] The "search history" is information about the search history of an online service provided by the information processing device 1 or an online service mediated by the information processing device 1 by the user U. For each search query, the "search history" includes, for example, information indicating the date and time when the search query was received by the information processing device 1, and information about one or more search terms (search keywords) included in the search query.

[0048] 3.2.3. Content storage unit 22 The content storage unit 22 stores content provided by the information processing device 1 through online services other than search services. Fig. 4 is a diagram showing an example of a content table stored in the content storage unit 22 of the information processing device 1 according to the embodiment. In the example shown in Fig. 4, the content storage unit 22 includes a "content ID," "content," and the like for each piece of content.

[0049] "Content ID" is identification information unique to each piece of content. "Content" is information related to the content associated with the "Content ID." Specifically, the content may indicate information related to the content. For example, the content is content provided by an online service. For example, the content is content related to a portal site, a news site, an auction site, a weather forecast site, a shopping site, or a finance (stock price) site. The content may also be content related to a route search site, a map provider site, a travel site, a restaurant introduction site, a blog site, a posting site, a music distribution site, a video distribution site, or a social networking site.

[0050] For example, in Fig. 4, the content with content ID "C1" is "CO1." Note that in the example shown in Fig. 4, the content is expressed by an abstract code such as "CO1," but the content may be in a file format containing specific numerical values, specific character strings, and various information. Note that the content storage unit 22 is not limited to the above example, and may store various information depending on the purpose.

[0051] 3.2.4. Interest Space Information Storage Unit 23 The interest space information storage unit 23 stores interest space information for each predetermined period TA. The interest space information includes information such as vectors of multiple objects placed in the interest space. The interest space is an M-dimensional space. The period TA is, for example, one month, but is not limited to this example and may be, for example, one week, two weeks, or three months. The period TA may also be a period during which the number of new search queries or new search terms received by the information processing device 1 exceeds a preset threshold.

[0052] 5 is a diagram showing an example of interest space information stored in the interest space information storage unit 23 of the information processing device 1 according to the embodiment. In the example shown in FIG. 5, the interest space information stored in the interest space information storage unit 23 includes, for each object, a "object ID," a "object," and a "vector."

[0053] The "object ID" is identification information unique to each object. An "object" is an object that may be of interest to a user U and is placed in the interest space, and may belong to various categories such as shopping, travel, news, sports, entertainment, finance, games, movies, or music.

[0054] For example, in FIG. 5, the object of object ID "Q1" is "O1" and the vector is "V1." Note that in the example shown in FIG. 5, the object is expressed by an abstract code such as "O1," but the object may be represented by a specific character string or may be represented by an image, etc. Also, in the example shown in FIG. 5, the vector is expressed by an abstract code such as "V1," but the vector is an M-dimensional vector and is represented, for example, by the values ​​of the vector components of each dimension.

[0055] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) using RAM as a work area to execute various programs (one example of an information processing program) stored in a storage device inside the information processing device 1. The processing unit 12 is also a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0056] 2, the processing unit 12 has a receiving unit 30, a searching unit 31, a learning unit 32, an identifying unit 33, a calculating unit 34, and a providing unit 35, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 2, and may have any other configuration as long as it performs the information processing described below.

[0057] 3.3.1. Reception unit 30 The reception unit 30 receives various requests. The reception unit 30 receives various requests from external information processing devices. For example, the reception unit 30 receives requests from each terminal device 2.

[0058] The reception unit 30 receives a search query including one or more search terms (search keywords) input by the user U from the terminal device 2 via the network N and the communication unit 10. The reception unit 30 also receives a content transmission request from the user U from the terminal device 2 via the network N and the communication unit 10. The content transmission request is a request that specifies content.

[0059] [3.3.2. Search Unit 31] The search unit 31 searches for information to be searched for that corresponds to one or more search terms included in the search query received by the reception unit 30 from among the plurality of pieces of information to be searched for that are stored in the search information storage unit 20. The search unit 31 transmits the searched information to the terminal device 2 that sent the search query as a search result via the network N and the communication unit 10.

[0060] The search unit 31 can also search for information to be searched for according to one or more search terms included in the search query received by the reception unit 30 from among a plurality of contents stored in the content storage unit 22. The search unit 31 transmits the searched contents as search results via the network N and the communication unit 10 to the terminal device 2 that sent the search query.

[0061] [3.3.3. Learning Section 32] The learning unit 32 generates an interest model for each period TA, which is a trained model that has learned the characteristics of each of a plurality of search terms, assuming that two or more search terms that satisfy predetermined conditions have similar characteristics.

[0062] The two or more search terms that satisfy the predetermined condition are multiple search terms included in the same search query, or search terms included in multiple search queries sent from the terminal device 2 by the same user U within a predetermined time period. Note that the learning unit 32 can also treat search terms included in search queries sent from the terminal device 2 by the same user U as two or more search terms that satisfy the predetermined condition, regardless of the time when the search queries were sent.

[0063] The learning unit 32 generates training data using search terms included in search queries with search dates and times within the time period TA. For example, the learning unit 32 acquires two or more search terms that satisfy predetermined conditions for each time period TA from the user information storage unit 21, and generates an interest model using the acquired two or more search terms as training data. For example, the learning unit 32 performs training using the two or more search terms that satisfy the predetermined conditions as training data, so that the vectors of the two or more search terms are similar to each other.

[0064] The learning unit 32 generates an interest model that outputs vectors from information indicating targets such as search terms, using, for example, DSSM technology, which uses LSTM, a type of RNN also known as a recursive neural network, for vector generation. Note that the method of generating an interest model that outputs vectors from information indicating targets such as search terms is not limited to the above-mentioned example, and various known techniques can be used as long as learning can be performed so that vectors indicating multiple similar targets are similar to each other.

[0065] The learning unit 32 acquires vectors for each of the multiple targets using the generated interest model for each period TA, and stores information including the acquired vectors of the multiple targets as interest space information in the interest space information memory unit 23 in the memory unit 11 for each period TA.

[0066] [3.3.4. Specification part 33] The identification unit 33 identifies a first object that has become included in the range of interests of a user U in an interest space in which each of a plurality of objects is represented by a vector according to the relevance to the interests of a plurality of users U and the vector is updated for each period TA, and identifies a second object that was similar to the first object in the past. The identification unit 33 includes a first identification unit 40 and a second identification unit 41.

[0067] [3.3.4.1. First specific part 40] The first identification unit 40 identifies a first object that has become included in the range of interests of a user U in an interest space in which each of multiple objects is represented by a vector according to its relevance to the interests of multiple users U and the vector is updated every period TA.

[0068] The first identification unit 40, for example, identifies the range of interests of each user U for each period TA using an interest model for each period TA. For example, the first identification unit 40 acquires, for each user U, search terms included in all search queries sent from the terminal device 2 by the same user U within each period TA from the user information storage unit 21. Then, the first identification unit 40 performs a process for each period TA in which the first identification unit 40 averages the vectors of the acquired search terms to calculate an average vector, and determines the calculated average vector as the user interest vector for each user U. Note that the first identification unit 40 can also calculate the average vector by, for example, weighting the vector of the search term more heavily the more recent the date and time it is received.

[0069] The first identification unit 40 identifies, for each user U, a range similar to the user interest vector of the user U as the user U's interest range. The similarity range to the user interest vector is, for example, a range of cosine similarity determined in advance, but is not limited to this example. Note that the first identification unit 40 can also identify the user U's interest range each time the number of new search queries or new search terms for the same user U exceeds a predetermined threshold.

[0070] The first identification unit 40 identifies a first object that has become included in the user U's range of interests in the latest interest space among the multiple objects. For example, if there are interest spaces for each month from October 2021 to February 2022, the latest interest space is the interest space for February 2022. The interest spaces for each month from October 2021 to February 2022 are obtained using the interest models for each month from October 2021 to February 2022.

[0071] For example, the interest space for October 2021 is obtained by inputting information indicating each of multiple targets into the interest model for October 2021, and the interest space for February 2022 is obtained by inputting information indicating each of multiple targets into the interest model for February 2022. In addition, the interest space is updated sequentially to the state of the interest space for October 2021, the state of the interest space for November 2021, the state of the interest space for December 2021, the state of the interest space for January 2022, and the state of the interest space for February 2022.

[0072] FIG. 6 is a diagram showing an example of a first object identified by the first identification unit 40 of the information processing device 1 according to the embodiment. FIG. 6 shows a part of the space of interest that is visualized by reducing the dimension of the M-dimensional space of interest. In the example shown in FIG. 6, the position P1(t -2 ) and the position P1(t -1 ) and the position P1(t0) of O1 in the latest interest space are shown.

[0073] As shown in Figure 6, the target O1 is not within the range of interests of user U1 in the interest space two periods ago and the interest space one period ago, but is within the range of interests of user U1 in the latest interest space. In this case, the first identification unit 40 identifies the target O1 as the first target. Note that if the latest interest space is the interest space of February 2022, the interest space of one period ago is, for example, the interest space of January 2022, and the interest space of two periods ago is, for example, the interest space of December 2021.

[0074] In addition, the first identification unit 40 can identify as the first object, for example, an object that was not within the range of interests of the user U in the interest space up until a predetermined period in the past, but has now become included in the range of interests of the user U in the latest interest space.

[0075] In the above example, whether or not the target is within the range of interests of the user U is determined using the interest space obtained using the interest model for the same period TA and the range of interests of the user U, but this is not limited to such an example. For example, the first identification unit 40 can also determine whether or not the target is within the range of interests of the user U by using the vector of each period TA of the target in the interest space of each period TA obtained using the interest model for each period TA and the range of interests of the user U obtained using the latest interest model.

[0076] [3.3.4.2.Second Specification Section 41] The second identification unit 41 identifies a second object that was similar in the past to the first object identified by the first identification unit 40. Specifically, the second identification unit 41 identifies as the second object an object that was similar to the first object identified by the first identification unit 40 in the space of interests one period or more ago. The similarity range of the first object is, for example, a predetermined range of cosine similarity with the first object, but is not limited to such an example.

[0077] Fig. 7 is a diagram showing an example of a second object identified by the second identification unit 41 of the information processing device 1 according to the embodiment. Similar to Fig. 6, Fig. 7 shows a part of an interest space visualized by reducing the dimension of the M-dimensional interest space.

[0078] In the example shown in FIG. 7, as in the example shown in FIG. 6, the position P1(t -2 ) and the position P1(t -1 ) and the position P1(t0) of the object O1 in the latest interest space. In the example shown in FIG. 7, the position P2(t -2 ) and the position P2(t -1 ) and the position P2(t0) of the object O2 in the latest interest space are shown.

[0079] In the interest space two periods ago and the interest space one period ago, the similarity range of the object O1 includes the object O2, and the second identification unit 41 identifies the object O2 as the second object.

[0080] The second identification unit 41 can also determine whether the second object was not included in the range of interests of the user U during a predetermined period in the past. Fig. 8 is a diagram showing an example of a second object identified by the second identification unit 41 of the information processing device 1 according to the embodiment. Like Figs. 6 and 7, Fig. 8 shows a part of an interest space visualized by reducing the dimension of the M-dimensional interest space.

[0081] In the example shown in FIG. 8, compared to the state shown in FIG. 7, the position P2(t -3 ) is shown. In the interest space three periods ago, the target O2 is included in the range of interests of the user U. In this case, the second identification unit 41 determines that the target O2 identified as the second target was included in the range of interests of the user U during a predetermined period in the past.

[0082] The predetermined period is, for example, the period TC = TA × K up to K periods ago. K is an integer of 10 or more, for example, but is not limited to such an example. Here, it is assumed that the second target is included in the user U's area of interest in the area of interest space before K + 1 periods ago, and the second target is not included in the user U's area of interest from the area of interest space K periods ago to 1 period ago or from the area of interest space K periods ago to the latest area of interest space. In this case, the second specifying unit 41 determines that the second target was not included in the user U's area of interest during a predetermined past period.

[0083] [3.3.5. Calculation unit 34] The calculation unit 34 calculates a score Sc for each second target based on at least one of the past similar periods and similarity degrees between the second target and the first target.

[0084] The past similar period is, for example, the total period during which the second target was similar to the first target from the period TA K periods ago to the period TA 1 period ago. For example, when K = 10 and TA = 1 month, in the period from 10 months ago to 1 month ago, the similar period of the second target that was not in the similar range of the first target in the period TA 7 months ago and the period TA 4 months ago is 8 months. In this case, the calculation unit 34 sets the score Sc to 80 (= 10 × 8), for example.

[0085] Also, the calculation unit 34 can calculate the score Sc by weighting and adding the periods during which the second target was similar to the first target with greater weights for more recent similar periods. For example, when K = 10 and the weights from the period TA K periods ago to the period TA 1 period ago are sequentially w K , w K-1 , ···, w2, w1, and w K < w K-1 < ··· < w2 < w1, the calculation unit 34 can calculate the score Sc using, for example, the following formula (1). Sc = w1 × a1 + w2 × a2 + ····· + w K-1 × a K-1 + w K × a K ···(1)

[0086] In the above formula (1), a1 is assigned a "1" if the two periods before the period TA were similar, and otherwise assigned a "0." a2 is assigned a "1" if the two periods before the period TA were similar, and otherwise assigned a "0." K-1 is assigned a "1" if it is similar in the K-1 previous period TA, otherwise it is assigned a "0", and a K is assigned a value of "1" if it is similar in the period TA K periods ago, and assigned a value of "0" if it is not. K , w K-1 , ···, w2, and w1 may be referred to as weight w when not distinguishing between them individually.

[0087] Furthermore, the calculation unit 34 can calculate the score of the second object based on the past similarity of the second object to the first object. For example, the calculation unit 34 can calculate the score Sc using the above formula (1) by increasing the weight w as the period during which the similarity of the second object to the first object is higher.

[0088] Furthermore, the calculation unit 34 can calculate the score of the second object based on the change in the past similarity of the second object with the first object. For example, the calculation unit 34 can increase the score Sc as the rate of increase in the past similarity of the second object with the first object increases.

[0089] For example, from a period TA K periods ago to a period TA one period ago, the oldest period TA in which the second object was similar to the first object is defined as the period TA K1 periods ago, and the similarity in period Ts1 is defined as similarity Ds1. Furthermore, from a period K periods ago to a period one period ago, the newest period TA in which the second object was similar to the first object is defined as the period TA K2 periods ago, and the similarity in period Ts2 is defined as similarity Ds2. In this case, the calculation unit 34 can calculate the score Sc using the following formula (2). In formula (2), k1 is a coefficient, and Sc1 is a fixed value. Sc=Sc1+k1(Ds2-Ds1) / (K2-K1)...(2)

[0090] Furthermore, the calculation unit 34 can also calculate, for example, the score Sc calculated by the above formula (1) and the score Sc calculated by the above formula (2) as the score Sc of the second target.

[0091] Furthermore, the calculation unit 34 can increase the score Sc the faster the rate of decline in the past similarity of the second object to the first object. For example, from the period TA K periods ago to the period TA one period ago, the oldest period TA in which the second object was similar to the first object is defined as the period TA K1 periods ago, and the similarity in period Ts1 is defined as similarity Ds1. Furthermore, from the period TA K periods ago to the period TA one period ago, the most recent period in which the second object was similar to the first object is defined as the period TA K2 periods ago, and the similarity in period Ts2 is defined as similarity Ds2. In this case, the calculation unit 34 can calculate the score Sc using the following formula (3). In the following formula (3), k2 is a coefficient, and Sc2 is a fixed value. Sc=Sc2+k2(Ds1-Ds2) / (K2-K1)...(3)

[0092] The calculation unit 34 can also calculate, for example, the score Sc of the second object by adding the score Sc calculated by the above formula (1) and the score Sc calculated by the above formula (3). The calculation unit 34 can also increase the score Sc of the second object, for example, the higher the similarity between the change in the past similarity of the second object with the first object and the specific change mode. The calculation unit 34 can also calculate, as the score Sc of the second object, a value obtained by adding the score Sc calculated by the above formula (1) and a score that increases as the similarity between the change in the past similarity of the second object with the first object and the specific change mode increases.

[0093] In this way, the calculation unit 34 can calculate the score Sc of the second object for each second object based on at least one of the past similarity period and the similarity between the second object and the first object.

[0094] [3.3.6.Providing Department 35] The providing unit 35 provides the user U with information on the second target identified by the identifying unit 33. The information on the second target is provided to the user U by transmitting it from the providing unit 35 to the terminal device 2 via the communication unit 10 and the network N. This allows the providing unit 35 to appropriately provide information on targets that may interest the user U.

[0095] For example, if the second object is "maritozzo," the information on the second object is information on maritozzo, and if the second object is "tapioca," the information on tapioca. The providing unit 35 acquires the information on the second object from the content stored in the content storage unit 22 of the storage unit 11, for example, and transmits the acquired information on the second object to the terminal device 2 via the communication unit 10 and the network N.

[0096] Furthermore, when the identification unit 33 determines that the second target was not included in the range of interests of the user U during a predetermined period, the provision unit 35 provides information about the second target to the user U. This allows the provision unit 35 to appropriately provide information about a target that is likely to be unknown to the user U but may be of interest to the user U.

[0097] Furthermore, the providing unit 35 can provide the user with information about the second object when the similarity between the second object and the range of interests of the user U in the interest space in the latest period TA is not outside a predetermined range. This also allows the providing unit 35 to appropriately provide information about an object that is likely to be unknown to the user U but may be of interest to the user U.

[0098] The providing unit 35 can also provide the user U with information on second targets, among the plurality of second targets, whose scores Sc calculated by the calculation unit 34 satisfy a predetermined condition. For example, the providing unit 35 provides the user U with information on second targets, among the plurality of second targets, whose scores Sc calculated by the calculation unit 34 are equal to or greater than a threshold. The providing unit 35 also provides the user U with information on second targets, among the plurality of second targets, whose scores Sc calculated by the calculation unit 34 are the highest.

[0099] In this way, the providing unit 35 provides information about the second target to the user U based on the score Sc calculated by the calculation unit 34, and therefore, when there are multiple second targets, it is possible to provide more appropriate information about the second target to the user U.

[0100] The providing unit 35 can provide the second target information to the user U in a push manner or in a pull manner. For example, the providing unit 35 can display the second target information as a pop-up on the terminal device 2 using an application installed on the terminal device 2, or can send the second target information to the email address of the user U by email. Furthermore, when the user U accesses the information processing device 1 using the terminal device 2, the providing unit 35 can also provide the second target information to the user U by sending the second target information to the terminal device 2. Note that the method of providing the second target information to the user U is not limited to these methods.

[0101] [4. Processing Procedure] Next, a processing procedure by the information processing device 1 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing a processing procedure by the processing unit 12 of the information processing device 1 according to the embodiment.

[0102] 9, the processing unit 12 of the information processing device 1 determines whether or not it is time to start learning the interest model (step S10). The timing for learning the interest model is, for example, a timing that occurs every period TA, but is not limited to this example.

[0103] When the processing unit 12 determines that it is time to start the learning process of the interest model (step S10: Yes), it generates the interest model (step S11). Then, the processing unit 12 generates interest space information using the interest model generated in step S11, and stores the generated interest space information in the storage unit 11 (step S12).

[0104] When the processing of step S12 is completed or when it is determined that the timing for the learning process of the interest model has not come (step S10: No), the processing unit 12 determines whether the timing for determining user interests has come (step S13). The timing for determining user interests is, for example, a timing that occurs every period TA, but is not limited to this example.

[0105] When the processing unit 12 determines that it is time to determine the user's interest (step S13: Yes), the processing unit 12 identifies the user's position of interest based on the user's search query (step S14).

[0106] When the processing of step S14 is completed or when it is determined that the timing for determining user interests has not come (step S13: No), the processing unit 12 determines whether the timing for determining information provision target has come (step S15). The timing for determining information provision target is the timing after the position of interest of the user U is identified in step S14. For example, the timing for determining information provision target is the timing immediately after the position of interest of the user U is identified in step S14 or the timing when the user U accesses the information processing device 1 using the terminal device 2.

[0107] When the processing unit 12 determines that it is time to determine an information provision target (step S15: Yes), it identifies a first object that has become included in the interest range of the user U in the interest space indicated by the interest space information generated in step S12 (step S16). Then, the processing unit 12 identifies a second object that was similar to the first object identified in step S16 in the past (step S17), and provides information on the second object identified in step S17 to the user U (step S18).

[0108] When the processing of step S18 is completed or when it is determined that the timing for determining whether or not the information subject has arrived (step S15: No), the processing unit 12 determines whether or not the timing for ending the operation has arrived (step S19). The processing unit 12 determines that the timing for ending the operation has arrived when, for example, the power supply of the information processing device 1 is turned off.

[0109] If the processing unit 12 determines that the operation end time has not yet arrived (step S19: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S19: Yes), it terminates the processing shown in Figure 9.

[0110] [5. Modifications] The above-described information processing device 1 may be implemented in various different forms other than the above-described embodiment, so other embodiments of the information processing device 1 will be described below.

[0111] The processing unit 12 of the information processing device 1 can generate multiple types of interest models. For example, the processing unit 12 can generate an interest model for each region and form an interest space for each region based on the interest model for each region. For example, the processing unit 12 can generate an interest model for each region by learning the characteristics of each of multiple search terms, assuming that two or more search terms that satisfy predetermined conditions among multiple search terms used by multiple users U in the target region have similar characteristics.

[0112] Furthermore, the processing unit 12 can form an interest space for each attribute of the user U based on an interest model for each attribute of the user U. For example, the processing unit 12 can generate an interest model for each specific attribute by learning the characteristics of each of a plurality of search terms, regarding two or more search terms that satisfy a predetermined condition among a plurality of search terms used by a plurality of users U having a specific attribute as having similar characteristics.

[0113] Furthermore, the processing unit 12 generates an interest model for a period TA based on a plurality of search queries sent by a plurality of users U from a plurality of terminal devices 2 within the period TA, but is not limited to this example. For example, the processing unit 12 can also generate an interest model for the latest period TA based on a plurality of search queries sent by a plurality of users U from a plurality of terminal devices 2 within the period TA in a period including the period TA P periods before and the latest period TA. P is an integer of 1 or greater.

[0114] The processing unit 12 can also identify the range of interests of each user U for each period TB based on multiple search queries sent by the same user U from the terminal device 2 during the period TB. The period TB is, for example, longer or shorter than the period TA. Note that the period TB may be a period during which the number of search queries or new search terms newly received by the information processing device 1 from the same user U exceeds a preset threshold.

[0115] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 10. Fig. 10 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0116] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0117] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0118] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0119] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

[0120] The CPU 81 of the computer 80 executes the programs loaded onto the RAM 82 to implement the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, these programs may be acquired from another device via the network N.

[0121] [7. Other] Furthermore, among the processes described in the above-mentioned embodiments and variations, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above-mentioned documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0122] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0123] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0124] [8. Effects] As described above, the information processing device 1 according to the embodiment includes a first identification unit 40, a second identification unit 41, and a providing unit 35. The first identification unit 40 identifies a first object that has become included in the range of interests of a user U in an interest space in which each of a plurality of objects is represented by a vector according to relevance to the interests of a plurality of users U and the vector is updated at predetermined intervals. The second identification unit 41 identifies a second object that was similar to the first object identified by the first identification unit 40 in the past. The providing unit 35 provides the user U with information on the second object identified by the second identification unit 41. This allows the information processing device 1 to appropriately provide information on objects that may interest the user U.

[0125] Furthermore, the second identification unit 41 determines whether the second target was not included in the range of interests of the user U during a predetermined period in the past. When the second identification unit 41 determines that the second target was not included in the range of interests of the user U during the predetermined period, the provision unit 35 provides information about the second target to the user U. This allows the information processing device 1 to appropriately provide information about a target that is likely to be unknown to the user U but may be of interest to the user U.

[0126] The information processing device 1 also includes a calculation unit 34 that calculates a score Sc of each second object based on at least one of a past similarity period and a similarity between the second object and the first object. The provision unit 35 provides the user U with information on a second object, among the plurality of second objects, whose score Sc calculated by the calculation unit 34 satisfies a predetermined condition. This allows the information processing device 1 to more appropriately provide the user U with information on objects that may be of interest to the user U.

[0127] Furthermore, the calculation unit 34 calculates the score Sc of the second object based on at least one of the length and recency of the past similarity period of the second object with the first object, which allows the information processing device 1 to more appropriately provide information on objects that may interest the user U.

[0128] Furthermore, the calculation unit 34 calculates the score Sc of the second object based on the past change in the similarity of the second object with the first object, which allows the information processing device 1 to more appropriately provide information on objects that may interest the user U.

[0129] Furthermore, the calculation unit 34 calculates the score Sc of the second object based on the rate of increase or decrease of the past similarity of the second object with the first object, which allows the information processing device 1 to more appropriately provide information on objects that may interest the user U.

[0130] Furthermore, when the similarity between the second object and the user U's range of interests is not outside a predetermined range, the providing unit 35 provides the user U with information about the second object. This allows the information processing device 1 to more appropriately provide information about objects that are likely to be unknown to the user U but may be of interest to the user U.

[0131] The interest space also includes multiple vectors obtained by inputting information on multiple targets into a trained model that has learned the characteristics of each of multiple search terms, with two or more search terms that satisfy predetermined conditions among multiple search terms used by multiple users U being considered to have similar characteristics. The first identification unit 40 identifies the range of interests of user U based on the vectors of search terms obtained by inputting the search terms used by user U into the trained model. This allows the information processing device 1 to more appropriately provide information on targets that may interest user U.

[0132] The information processing device 1 also includes a learning unit 32 that generates a trained model using multiple search terms used by multiple users U. This allows the information processing device 1 to more appropriately provide information on subjects that may interest the users U.

[0133] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0134] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0135] 1. Information processing equipment 2,21~2 n terminal device 10. Communications Department 11 Storage section 12 Processing section 20 Search information storage unit 21 User information storage unit 22 Content storage unit 23 Interest spatial information storage unit 30 Reception 31 Search Section 32 Learning Department 33 Specific part 34 Calculation section 35 Provision Department 40 First Specific Part 41 Second Specific Part 100 Information Processing Systems N Network

Claims

1. A first identification unit that identifies a first object that has become included in a user's interest range in an interest space in which each of a plurality of objects is represented by a vector and the vector is updated at predetermined intervals; a second identification unit that identifies a second object that was similar to the first object identified by the first identification unit in the past; a providing unit that provides the user with information about the second target identified by the second identifying unit, The interest space is The database includes vectors of the plurality of objects obtained by inputting information of the plurality of objects into a trained model that has learned the characteristics of each of the plurality of search terms, which are two or more search terms that satisfy predetermined conditions among the plurality of search terms used by a plurality of users, as having similar characteristics.

1. An information processing device comprising:

2. The second specifying unit is determining whether the second object was not included in the user's range of interests during a predetermined period of time in the past; The providing unit When the second identification unit determines that the second target was not included in the range of interests of the user during the predetermined period, information about the second target is provided to the user.

2. The information processing apparatus according to claim 1, wherein:

3. a calculation unit that calculates a score of the second object for each of the second objects based on at least one of a past similarity period and a similarity between the second object and the first object; The providing unit and providing the user with information on a second object whose score calculated by the calculation unit satisfies a predetermined condition among the plurality of second objects.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The calculation unit calculating a score for the second object based on at least one of the length and recency of the similarity period; 4. The information processing apparatus according to claim 3,

5. The calculation unit Calculating a score for the second object based on the change in the degree of similarity 5. The information processing apparatus according to claim 3, wherein the information processing apparatus is a computer.

6. The calculation unit Calculating a score for the second object based on the rate of increase or decrease of the similarity.

6. The information processing apparatus according to claim 5,

7. The providing unit When the similarity between the second object and the user's range of interests is not outside a predetermined range, information about the second object is provided to the user.

7. The information processing device according to claim 1, wherein:

8. The first identification unit Identifying the user's range of interests based on a vector of the search term obtained by inputting the search term used by the user into the trained model 8. The information processing device according to claim 1, wherein:

9. a learning unit that generates the trained model using the plurality of search terms used by the plurality of users; 9. The information processing device according to claim 1, wherein the information processing device is a computer.

10. A computer-implemented information processing method, comprising: a first identification step of identifying a first object that has become included in a user's range of interest in an interest space in which each of a plurality of objects is represented by a vector and the vector is updated every predetermined period; a second identification step of identifying a second object that was similar to the first object identified by the first identification step in the past; a providing step of providing the user with information on the second target identified by the second identifying step, The interest space is The database includes vectors of the plurality of objects obtained by inputting information of the plurality of objects into a trained model that has learned the characteristics of each of the plurality of search terms, which are two or more search terms that satisfy predetermined conditions among the plurality of search terms used by a plurality of users, as having similar characteristics. An information processing method comprising:

11. A first identification step for identifying a first object that has become included in a user's range of interest in an interest space in which each of a plurality of objects is represented by a vector and the vector is updated at predetermined intervals; a second identification procedure for identifying a second object that was previously similar to the first object identified by the first identification procedure; a providing step of providing the user with information on the second target identified by the second identifying step; The interest space is The database includes vectors of the plurality of objects obtained by inputting information of the plurality of objects into a trained model that has learned the characteristics of each of the plurality of search terms, which are two or more search terms that satisfy predetermined conditions among the plurality of search terms used by a plurality of users, as having similar characteristics. An information processing program characterized by:

Images