Information processing apparatus, 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 second object which was similar in the past to 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 including the first object 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 third object similar to a standard when the second object at the past point of time similar to the first object is set as the standard. The provision unit provides the user with information on the third object.SELECTED DRAWING: Figure 1

Description

Technical Field

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

Background Art

[0002] Conventionally, various techniques for providing information to users have been provided. For example, in Patent Document 1, among a plurality of quadrants in which categories that a user is interested in are classified based on elements related to commercial transactions, based on the quadrant to which the category that the user is interested in belongs, a technique for delivering an advertisement corresponding to the quadrant has been proposed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, there is room for improvement in the above-described conventional technology. In the above-described conventional technology, information provision depending on quadrants is performed, and there is room for improvement in terms of performing information provision flexibly, and it is desired to appropriately provide information on a target that a user may be interested in.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program that can appropriately provide information on a target that a user may be interested in.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a first specifying unit, a second specifying unit, and a providing unit. The first specifying unit specifies a first object and a second object that was similar in the past, such that each of a plurality of objects including the first object is represented by a vector in an interest space where vectors are updated every predetermined period according to the relevance to the interests of a plurality of users and is included in the user's interest range. The second specifying unit specifies a third object that is similar to a reference based on the second object at a past time point that was similar to the first object. The providing unit provides information on the third object to the user.

Effect of the Invention

[0007] According to one aspect of the embodiment, there is an effect that information on an object that a user may be interested in can be appropriately provided.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing the information processing apparatus, information processing method, and 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 by this embodiment. Also, the respective embodiments can be appropriately combined as long as the processing contents do not conflict. In addition, the same reference numerals are given to the same parts in the following embodiments, and redundant explanations are 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 the information processing apparatus 1 and includes a search process, a model generation process, and an information providing process.

[0011] First, the search process and the model generation process will be described. The information processing apparatus 1 shown in FIG. 1 is for users U1 to Un provides a search service. For example, the information processing apparatus 1 has a search target database in which search targets are indexed and stored, and executes a search process on information such as such a search target database. For example, the information of the search target database is stored in the storage unit 11 (see FIG. 2).

[0012] As shown in FIG. 1, users U1 to U n operate the terminal devices 21 to 2 n to cause the terminal devices 21 to 2 n to execute a process of transmitting a search query from the terminal devices 21 to 2 n to the information processing apparatus 1 (steps S11 to S1 n ). n is an integer of 2 or more.

[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 apparatus 1. Also, in step S1 n , the user U n operates the terminal device 2 n to cause the terminal device 2 n to execute a process of transmitting a search query from the terminal device 2 n to the information processing apparatus 1. Hereinafter, when each of the users U1 to U n is not individually distinguished, it may be described as the user U, and when each of the terminal devices 21 to 2 n is not individually distinguished, it may be described as the terminal device 2.

[0014] The search query includes one or more search terms (search keywords) input into the terminal device 2 by the user U. For example, when the user U inputs "sneaker" as one or more search terms into the terminal device 2, the search query includes "sneaker". Also, when the user U inputs "sneaker ladies" as one or more search terms into the terminal device 2, the search query includes "sneaker ladies". "Sneaker ladies" includes two search terms, "sneaker" and "ladies", separated by a space.

[0015] The information processing device 1 receives search queries transmitted from each of the terminal devices 21 to 2 n (steps S21 to S2 n ). For example, in step S21, the information processing device 1 receives a search query from the terminal device 21, and in step S2 n , it receives a search query from the terminal device 2 n .

[0016] Next, the information processing device 1 executes a search process based on the search queries received in steps S21 to S2 n (steps S31 to S3 n ). For example, in step S31, the information processing device 1 executes a search process to search for objects corresponding to one or more search terms included in the search query transmitted from the terminal device 21 and received in step S21 from the search target database. Also, in step S3 n , the information processing device 1 executes a search process to search for objects corresponding to one or more search terms included in the search query transmitted from the terminal device 2 n and received in step S2 n from the search target database.

[0017] Next, the information processing device 1 transmits the search results, which are the results of the search process in steps S31 to S3 n , to the terminal devices 21 to 2 n (steps S41 to S4 n)。For example, in step S41, the information processing apparatus 1 transmits the search result, which is the result of the search process in step S31, to the terminal device 21. Also, in step S4 n the information processing apparatus 1 transmits the search result, which is the result of the search process in step S3 n , to the terminal device 2 n .

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

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

[0020] The information processing apparatus 1 uses two or more search terms that satisfy a predetermined condition as learning data and performs learning so that the vectors of the two or more search terms are similar to each other. The information processing apparatus 1 can also treat the search terms included in the search query transmitted from the terminal device 2 by the same user U as two or more search terms that satisfy a predetermined condition regardless of the transmission timing of the search query.

[0021] Note that the search term is composed of one search keyword, but may also be composed of two or more search keywords. For example, when the search query includes the character string "sneaker ladies", the information processing apparatus 1 treats "sneaker" and "ladies" as different search terms, but can also treat the combination of "sneaker" and "ladies" as one search term.

[0022] The information processing apparatus 1 uses, for example, a technique of DSSM (Deep Structured Semantic Model) that uses LSTM (Long Short-Term Memory), which is a type of RNN (Recurrent Neural Network) also called a recurrent neural network, for vector generation (for example, distributed representation generation) to generate an interest model that outputs a vector (for example, a distributed representation) from information indicating an object such as a search term. Note that the method for generating the interest model that outputs a vector from the information indicating the object is not limited to the example described above.

[0023] The information processing apparatus 1 generates an interest model every predetermined period TA. For example, when the predetermined period TA is one month, the information processing apparatus 1 generates an interest model for each month of January, February, March,... in 2022.

[0024] Next, the information providing process will be described. The information processing apparatus 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 object represented by the vector is not limited to the object represented by the search term, and may be an object other than the object represented by the search term.

[0025] The information processing device 1 generates an interest space including the vectors of each target by performing, for each target, a process of inputting information indicating the target to the interest model generated in step S5 and acquiring the vector of the target output from the interest model. 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 included in the plurality of search queries transmitted from the terminal device 2 by the same user U to the interest model generated in step S5, and performs, for each search term, a process of acquiring the vector of the search term output from the interest model.

[0027] The information processing device 1 calculates an average vector by averaging the vectors of the search terms included in the plurality of search queries transmitted 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 specifies 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 increasing the weight of the vector of the search term for the search query with a newer received date and time, for example.

[0028] The information processing device 1 specifies the interest range of each user U for each period TA using the interest model for each period TA. The information processing device 1 specifies, for each user U, the interest range in the period TA based on, for example, a plurality of search queries transmitted from the terminal device 2 by the same user U within the period TA.

[0029] Next, the information processing device 1 specifies a first target that has come to be included in the interest range of the user U and a second target that was similar at a past time point (step S7). Next, the information processing device 1 specifies a third target that is similar to the reference, based on the second target that was similar to the first target at a past time point (step S8).

[0030] Then, the information processing apparatus 1 provides the information of the third target specified in step S8 to the user U (step S9). The processes in steps S6 to S9 are performed for each user U.

[0031] For example, assume that the generation period of the interest model is one month, and the interest model for February 2022 is the latest 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.

[0032] Also, in the interest space for January 2022, the target "tapioca" and the target "maritozzo" are similar, but assume that the target "tapioca" and the target "maritozzo" are not included in the interest range of user U1. Also, in the interest space for February 2022, assume that the target "maritozzo" continues to be not included in the interest range of user U1, but the target "tapioca" has come to be included in the interest range of user U1.

[0033] In this case, the information processing apparatus 1 specifies the target "tapioca" as the first target and the target "maritozzo" as the second target. Then, the information processing apparatus 1 specifies the target similar to the target "maritozzo" in the interest space for January 2022 in the interest space for February 2022 as the third target. For example, assume that the target similar to the target "maritozzo" in the interest space for January 2022 in the interest space for February 2022 is the target "pistachio". In this case, the information processing apparatus 1 specifies the target "pistachio" as the third target. Then, the information processing apparatus 1 provides the information of the target "pistachio" specified as the third target to the user U1.

[0034] In this way, the information processing apparatus 1 identifies a third object that is similar to a first object that has come to be included in the user U's area of interest in the area of interest space and a second object that was similar to the first object at a past time point, and provides information on the third object to the user U. As a result, the information processing apparatus 1 can appropriately provide information on an object that may be of interest to the user U.

[0035] [2. Configuration of Information Processing System] FIG. 2 is a diagram showing an example of the configuration of an information processing system including the information processing apparatus 1 according to the embodiment. As shown in FIG. 2, the information processing system 100 includes the information processing apparatus 1 and a plurality of terminal devices 21 to 2 n and so on. The information processing apparatus 1 and the plurality of terminal devices 21 to 2 n are communicably connected by wire or wirelessly via the network N.

[0036] The information processing apparatus 1 is an information processing apparatus that can communicate 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 apparatus 1 is communicably connected to other various devices via the network N.

[0037] In addition, the information processing apparatus 1 provides online services such as web services to the terminal devices 2 of each user U. For example, as online services, the information processing apparatus 1 provides, in addition to the above-described search service and information providing service, for example, services such as SNS (Social Networking Service), electronic commerce (EC: Electronic Commerce) sites, posting sites, electronic payment, online games, online banking, online trading, accommodation / ticket reservation, video / music distribution, news, maps, route search, route guidance, route information, operation information, weather forecast, and so on. Note that the information processing apparatus 1 can also cooperate with various servers that provide the above-described online services and mediate the online services.

[0038] The terminal device 2 is an information processing device utilized by a user U who accesses content such as web pages displayed on a browser or content for applications. For example, the terminal device 2 can be a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), etc. Note that the terminal device 2 does not have to be limited to the examples described above. For example, it can also be a smartwatch or a wearable device (Wearable Device), etc.

[0039] [3. Configuration of Information Processing Device 1] Hereinafter, an example of the functional configuration of the above-described information processing device 1 will be described. As shown in FIG. 2, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0040] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a NIC (Network Interface Card), etc. And the communication unit 10 is connected to the network N by wire or wirelessly, and performs information transmission and reception with various other devices. For example, the communication unit 10 n performs information transmission and reception with the terminal devices 21 to 2 via the network N.

[0041] [3.2. Storage Unit 11] The storage unit 11 is realized by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory (Flash Memory), or storage devices such as hard disks and optical disks. Also, the storage unit 11 includes 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.

[0042] [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 apparatus 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 the plurality of search targets is indexed and stored.

[0043] The information to be searched for is, for example, information on various contents such as web pages collected by a crawler or the like. The information to be searched for stored in the search information storage unit 20 is, for example, the URL (Uniform Resource Locator) and summary of the content, but is not limited to such examples.

[0044] [3.2.2. User Information Storage Unit 21] The user information storage unit 21 stores user information including information on users U1 to U n FIG. 3 is a diagram showing an example of a user information table stored in the user information storage unit 21 of the information processing apparatus 1 according to the embodiment.

[0045] As shown in FIG. 3, the user information table stored in the user information storage unit 21 includes information such as "User ID (Identifier)", "User Name", "Attribute", 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.

[0046] The "Attribute" is information indicating the attribute of the user U. The attribute of the user U is a demographic attribute or a psychographic attribute of the user U. The demographic attribute is a demographic attribute of the user U. The psychographic attribute is an attribute indicating the values, lifestyle, personality, interests, etc. of the user U.

[0047] 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, the job position of user U, the business responsibilities, the annual income, the address, the commuting route, the training history, the family composition, and the like. The preferences of user U include, for example, the degree of interest of user U in each target such as clothing, travel, cars, motorcycles, computers, and lunch.

[0048] The "search history" is information on the search history in the online service provided by the information processing apparatus 1 or the online service mediated by the information processing apparatus 1 by user U. Such "search history" includes, for example, information indicating the reception date and time of the search query by the information processing apparatus 1 and information on one or more search terms (search keywords) included in the search query for each search query.

[0049] [[3.2.3. Content storage unit 22]] The content storage unit 22 stores the content provided by the information processing apparatus 1 in an online service other than the search service. FIG. 4 is a diagram showing an example of a content table stored in the content storage unit 22 of the information processing apparatus 1 according to the embodiment. In the example shown in FIG. 4, the content storage unit 22 includes, for each content, a "content ID", "content", and the like.

[0050] The "Content ID" is unique identification information for each piece of content. The "content" is information regarding the content associated with the "Content ID". Specifically, the content may indicate information regarding the content of the content. For example, the content is content provided by an online service. For example, the content is content regarding a portal site, news site, auction site, weather forecast site, shopping site, or finance (stock price) site, etc. Further, the content may be content regarding a route search site, map providing site, travel site, restaurant introduction site, web blog site, posting site, music distribution site, video distribution site, or SNS site, etc.

[0051] For example, in FIG. 4, the content with the Content ID "C1" is "CO1". In the example shown in FIG. 4, the content is represented by an abstract symbol such as "CO1", but the content may be a file format including specific numerical values, specific character strings, and various types of information, etc. Note that the content storage unit 22 is not limited to the above-described example and may store various types of information according to the purpose.

[0052] [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 a plurality of objects arranged 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 such an example and may be, for example, one week, two weeks, or three months, etc. Further, the period TA may be a period in which the number of search queries newly received by the information processing apparatus 1 or the number of new search terms becomes equal to or greater than a preset threshold value.

[0053] FIG. 5 is a diagram showing an example of the area of interest space information stored in the area of interest space information storage unit 23 of the information processing apparatus 1 according to the embodiment. In the example shown in FIG. 5, the area of interest space information stored in the area of interest space information storage unit 23 includes, for each target, a "target ID", a "target", and a "vector".

[0054] The "target ID" is unique identification information for each target. The "target" is a target that can be the area of interest of the user U placed in the area of interest space, and belongs to various categories such as, for example, shopping, travel, news, sports, entertainment, finance, games, movies, or music.

[0055] For example, in FIG. 5, the target of the target ID "Q1" is "O1", and the vector is "V1". In the example shown in FIG. 5, the target is represented by an abstract symbol such as "O1", but the target may be indicated by a specific character string or may be indicated by an image or the like. Also, in the example shown in FIG. 5, the vector is represented by an abstract symbol such as "V1", but the vector is an M-dimensional vector and is indicated by, for example, the values of the vector components in each dimension.

[0056] [3.3. Processing Unit 12] The processing unit 12 is a controller and is realized, for example, by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (an example of an information processing program) stored in a storage device inside the information processing apparatus 1 with the RAM as a work area. Also, the processing unit 12 is a controller and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0057] As shown in FIG. 2, the processing unit 12 includes a reception unit 30, a search unit 31, a learning unit 32, an identification unit 33, a calculation unit 34, and a provision unit 35, and realizes or executes the functions and operations 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 be any other configuration as long as it can perform the information processing described later.

[0058] 〔3.3.1. Reception Unit 30〕 The reception unit 30 receives various requests. The reception unit 30 receives various requests from an external information processing device. For example, the reception unit 30 receives requests from each terminal device 2.

[0059] 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. Further, the reception unit 30 receives a content transmission request of the user U from the terminal device 2 via the network N and the communication unit 10. The content transmission request is a request for specifying content.

[0060] 〔3.3.2. Search Unit 31〕 The search unit 31 searches for information to be searched for corresponding to one or more search terms included in the search query received by the reception unit 30 from among a plurality of pieces of information to be searched for stored in the search information storage unit 20. The search unit 31 transmits the searched information to be searched for as a search result to the terminal device 2 that transmitted the search query via the network N and the communication unit 10.

[0061] In addition, the search unit 31 can also search for information to be searched for corresponding 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 content as a search result to the terminal device 2 that transmitted the search query via the network N and the communication unit 10.

[0062] 〔3.3.3. Learning Unit 32〕 The learning unit 32 generates, for each period TA, an interest model which is a learned model that has learned the features of each of a plurality of search terms on the assumption that two or more search terms satisfying predetermined conditions have similar features.

[0063] Two or more search terms satisfying predetermined conditions are search terms included in a plurality of search terms included in the same search query, or search terms included in a plurality of search queries transmitted from the terminal device 2 within a predetermined time by the same user U. Note that the learning unit 32 can also treat search terms included in search queries transmitted from the terminal device 2 by the same user U as two or more search terms satisfying predetermined conditions regardless of the transmission time of the search query.

[0064] The learning unit 32 generates learning data using the search terms included in the search query having the search date and time within the period TA. For example, the learning unit 32 acquires, for each period TA, two or more search terms satisfying predetermined conditions from the user information storage unit 21, and generates an interest model using the acquired two or more search terms as learning data. For example, the learning unit 32 performs learning so that the vectors of two or more search terms are similar to each other using two or more search terms satisfying predetermined conditions as learning data.

[0065] The learning unit 32 generates, for example, an interest model that outputs a vector from information indicating an object such as a search term, using the technology of DSSM that uses LSTM, which is a type of RNN also called a recurrent neural network, for vector generation. Note that the method for generating an interest model that outputs a vector from information indicating an object such as a search term is not limited to the above-described example, and it is sufficient that learning can be performed so that vectors indicating a plurality of similar objects are similar to each other, and various known technologies can be used.

[0066] The learning unit 32 uses the generated interest model for each period TA to acquire vectors of each of a plurality of objects, and stores, for each period TA, information including the information of the vectors of the acquired plurality of objects in the interest space information storage unit 23 in the storage unit 11 as interest space information.

[0067] [3.3.4. Specific part 33] The specific part 33 identifies a first object that comes to be included in the range of the user U's interests in an interest space where each of a plurality of objects is represented by a vector and the vector is updated every period TA, according to the relevance to the interests of the plurality of users U.

[0068] Then, the specific part 33 identifies a second object that was similar to the identified first object in the past, and identifies a third object that is similar to the reference based on the second object at the past time point that was similar to the first object. Also, the specific part 33 identifies a fourth object that was similar before the first object was similar to the second object. The specific part 33 includes a first specific part 40, a second specific part 41, and a third specific part 42. First, the first specific part 40 will be described.

[0069] [3.3.4.1. First specific part 40] The first specific part 40 identifies a first object that comes to be included in the range of the user U's interests in an interest space where each of a plurality of objects is represented by a vector and the vector is updated every period TA, according to the relevance to the interests of the plurality of users U.

[0070] The first specific part 40, for example, identifies the range of each user U's interests every period TA using an interest model for each period TA. The first specific part 40, for example, acquires, for each user U from the user information storage unit 21, the search terms included in each of all the search queries transmitted from the terminal device 2 by the same user U within each period TA. Then, the first specific part 40 calculates an average vector by averaging the vectors of the acquired plurality of search terms, and performs, every period TA, a process of determining the calculated average vector as a user interest vector for each user U. Note that the first specific part 40 can also calculate an average vector by increasing the weight of the vector of the search term as the received date and time is newer.

[0071] The first specifying unit 40 specifies, for each user U, a range similar to the user interest vector of the user U as the interest range of the user U. The range similar to the user interest vector is, for example, a range in which the cosine similarity is a predetermined range, but is not limited to such an example. Note that the first specifying unit 40 can also specify the interest range of the user U each time the number of new search queries or the number of new search terms of the same user U becomes equal to or greater than a preset threshold value.

[0072] The first specifying unit 40 specifies a first target that has come to be included in the interest range of the user U in the latest interest space among a plurality of targets. For example, when there is an interest space 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 by the interest models for each month from October 2021 to February 2022.

[0073] For example, the interest space for October 2021 is obtained by inputting information indicating each of a plurality of targets into the interest model for October 2021, and the interest space for February 2022 is obtained by inputting information indicating each of a plurality of targets into the interest model for February 2022. Further, the interest space is sequentially updated 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.

[0074] FIG. 6 is a diagram showing an example of a first target specified by the first specifying unit 40 of the information processing apparatus 1 according to the embodiment. In FIG. 6, a part of the interest space obtained by reducing the dimensionality of the M-dimensional interest space and visualizing it is shown. In the example shown in FIG. 6, the position P1(t -2 ) of the target O1 in the interest space two periods ago, the position P1(t -1 ) of the target O1 in the interest space one period ago, and the position P1(t0) of O1 in the latest interest space are shown.

[0075] As shown in FIG. 6, the target O1 was not within the area of interest of the user U1 in the area of interest space two periods ago and the area of interest space one period ago, but is within the area of interest of the user U1 in the latest area of interest space. In this case, the first specifying unit 40 specifies the target O1 as the first target. Note that when the latest area of interest space is the area of interest space in February 2022, the area of interest space one period ago is, for example, the area of interest space in January 2022, and the area of interest space two periods ago is, for example, the area of interest space in December 2021.

[0076] In addition, the first specifying unit 40 can specify, as the first target, a target that was not within the area of interest of the user U in the area of interest space up to a predetermined period in the past but has newly come to be included in the area of interest of the user U in the latest area of interest space.

[0077] Note that in the above example, whether the target is within the area of interest of the user U is determined by using the area of interest space obtained for each using the area of interest model for the same period TA and the area of interest of the user U, but the present invention is not limited to such an example. For example, the first specifying unit 40 can also determine whether the target is within the area of interest of the user U by using the vector of the target for each period TA in the area of interest space for each period TA obtained by using the area of interest model for each period TA and the area of interest of the user U obtained by using the latest area of interest model.

[0078] The first specifying unit 40 specifies a second target that was similar to the first target in the past. Specifically, the first specifying unit 40 specifies, as the second target, a target that was similar to the first target in the area of interest space one or more periods before the first target. The similarity range of the first target is, for example, a range in which the cosine similarity with the first target is predetermined, but the present invention is not limited to such an example.

[0079] FIG. 7 is a diagram showing an example of the second target specified by the first specifying unit 40 of the information processing apparatus 1 according to the embodiment. In FIG. 7, as in FIG. 6, a part of the area of interest space obtained by reducing the dimensionality of the M-dimensional area of interest space to a lower dimension and visualizing it is shown.

[0080] In the example shown in FIG. 7, similar to the example shown in FIG. 6, the position P1(t -2 ) of the object O1 in the region of interest two periods ago, the position P1(t -1 ) of the object O1 in the region of interest one period ago, and the position P1(t0) of the object O1 in the latest region of interest are shown. Also, in the example shown in FIG. 7, the position P2(t -2 ) of the object O2 in the region of interest two periods ago, the position P2(t -1 ) of the object O2 in the region of interest one period ago, and the position P2(t0) of the object O2 in the latest region of interest are shown.

[0081] In the region of interest two periods ago and the region of interest one period ago, the object O2 is included in the similar range of the object O1, and the first specifying unit 40 specifies the object O2 as the second object.

[0082] Also, the first specifying unit 40 can also determine whether or not the second object was not included in the user U's region of interest during a predetermined period in the past. FIG. 8 is a diagram showing an example of the second object specified by the first specifying unit 40 of the information processing apparatus 1 according to the embodiment. In FIG. 8, similar to FIGS. 6 and 7, a part of the region of interest obtained by reducing the M-dimensional region of interest to a lower dimension and visualizing it is shown.

[0083] In the example shown in FIG. 8, compared with the state shown in FIG. 7, the position P2(t -3 ) of the object O2 in the region of interest three periods ago is shown. In the region of interest three periods ago, the object O2 is included in the user U's region of interest. In this case, the first specifying unit 40 determines that the object O2 specified as the second object was included in the user U's region of interest during a predetermined period in the past.

[0084] The predetermined period is, for example, the period TC = TA×K up to K periods ago. K is, for example, an integer of 10 or more, but is not limited to such an example. Here, the second object was included in the user U's area of interest in the area of interest space before K + 1 periods ago, and the second object is not included in the user U's area of interest range 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 first specifying unit 40 determines that the second object was not included in the user U's area of interest range in a predetermined period in the past.

[0085] [3.3.4.2. Second specifying unit 41] The second specifying unit 41 specifies a third object that is similar to the reference in the area of interest space updated every period TA, based on the second object at a past time point that was similar to the first object. The reference similarity range is, for example, a range in which the cosine similarity to the reference is predetermined.

[0086] FIG. 9 is a diagram showing an example of the third object specified by the second specifying unit 41 of the information processing apparatus 1 according to the embodiment. In FIG. 9, as in FIG. 6, a part of the area of interest space in which the M-dimensional area of interest space is reduced in dimension and visualized is shown.

[0087] In the example shown in FIG. 9, as shown in FIG. 7, the object O2 at a past time point that was similar to the object O1 (an example of the first object) is shown as the reference Os. Specifically, in FIG. 9, the position P2(t -2 ) of the object O2 in the area of interest space two periods ago is shown as the position Ps(t -2 ) of the reference Os, and the position P2(t -1 ) of the object O2 in the area of interest space one period ago is shown as the position Ps(t -1 ) of the reference Os. In the example shown in FIG. 9, the second specifying unit 41 specifies the object O3 that is similar to the reference Os in the latest area of interest space as the third object.

[0088] The second specifying unit 41 can also specify, as a third target, a target that has the same attribute as the second target among the targets similar to the reference Os. The attributes of the target include various attributes corresponding to the target, such as category, usage scenario, specifications (specifications or functions of the transaction target, etc.), problems that can be solved by the target, and troubles of people that can be solved by the target. Thereby, the second specifying unit 41 can specify, as the third target, a target that has a high relevance to the second target. Note that the second specifying unit 41 can also specify, as the third target, a target that has the same attribute as the second target when a predetermined condition is satisfied. The predetermined condition is, for example, a condition that the number of targets similar to the reference Os is equal to or greater than a threshold value, or a condition that the second target is a specific category.

[0089] In addition, the second specifying unit 41 can also determine whether or not the third target was not included in the range of the user U's interests during a predetermined past period. The method for determining whether or not the third target was not included in the range of the user U's interests during a predetermined past period is the same as the determination method by the first specifying unit 40 for determining whether or not the second target was not included in the range of the user U's interests during a predetermined past period.

[0090] [3.3.4.3, Third Specifying Unit 42] The third specifying unit 42 specifies, in the interest space updated for each period TA, a fourth target that was similar to the first target before being similar to the second target. The similarity range of the first target is, for example, a range in which the cosine similarity with the first target is within a predetermined range.

[0091] FIG. 10 is a diagram showing an example of the fourth target specified by the third specifying unit 42 of the information processing apparatus 1 according to the embodiment. In FIG. 10, similar to FIGS. 6 to 9, a part of the interest space obtained by reducing the dimensionality of the M-dimensional interest space and visualizing it is shown. In the example shown in FIG. 10, compared with the state shown in FIG. 8, the position P4(t -3 ) of the target O4 in each interest space from the interest space three periods ago to the latest interest space, the position P4(t -2 ) of the target O4 in each interest space from the interest space three periods ago to the latest interest space, and the position P4(t -1) and positions such as P4(t0) are further shown.

[0092] In the example shown in FIG. 10, the target O2 is similar to the target O1 in the interest space for two periods, and the target O4 is similar to the target O1 in the interest space for three periods. Thus, since the target O1 is similar to the target O4 before being similar to the target O2, the third specifying unit 42 specifies the target O4 as the fourth target.

[0093] Also, the third specifying unit 42 can determine whether or not the fourth target was not included in the user U's interest range during a predetermined period in the past. The method for determining whether or not the fourth target was not included in the user U's interest range during a predetermined period in the past is the same as the determination method by the first specifying unit 40 for whether or not the second target was not included in the user U's interest range during a predetermined period in the past.

[0094] Also, the third specifying unit 42 can, for example, specify, as the fourth target, a target having an attribute in common with the second target among the first targets that were similar before the first target was similar to the second target. The attributes of the target include various attributes corresponding to the target, such as, for example, category, usage scene, specifications (specifications or functions of the transaction target, etc.), problems that can be solved by the target, and troubles of people that can be solved by the target. Thereby, the second specifying unit 41 can specify, as the third target, a target having a high relevance to the first target.

[0095] 〔3.3.5. Calculation unit 34〕 The calculation unit 34 calculates, for each third target, a score Sc3 of the third target based on at least one of the similarity period and the similarity degree of the third target with respect to the reference Os.

[0096] The past similar period is, for example, the total period in which the third target was similar to the reference Os from the period TA K periods ago to the latest period TA. For example, when K = 4 and TA = 1 month, in the period from 4 months ago to the latest month, the similar period of the third target that was not within the similar range of the reference Os in the period 3 months ago is 4 months. In this case, the calculation unit 34 sets the score Sc3 to 40 (= 10 × 4), for example.

[0097] Also, the calculation unit 34 can calculate the score Sc3 by weighting and adding the periods in which the third target was similar to the reference Os, with greater weight given to more recent similar periods. For example, when K = 10, the weights from the period TA K periods ago to the latest period TA are, in order, w K 、w K-1 、···、w1, w0, and assuming w K <w K-1 <···<w1<w0, the calculation unit 34 can calculate the score Sc3 using, for example, the following formula (1). Sc3 = w0 × a0 + w1 × a1 + ····· + w K-1 × a K-1 + w K × a K ···(1)

[0098] In the above formula (1), a0 is assigned "1" when similar in the latest period TA and "0" otherwise, a1 is assigned "1" when similar in the period TA one period ago and "0" otherwise. Also, a K-1 is assigned "1" when similar in the period TA K - 1 periods ago and "0" otherwise, and a K is assigned "1" when similar in the period TA K periods ago and "0" otherwise. In the following, when not individually distinguishing each of the weights w K 、w K-1 、···、w1, w0, they may be referred to as the weight w.

[0099] Further, the calculation unit 34 can calculate the score Sc3 of the third target based on the similarity to the reference Os of the third target. For example, the calculation unit 34 can calculate the score Sc3 using the above formula (1) by increasing the weight w for a period with a higher similarity to the reference Os of the third target.

[0100] In addition, the calculation unit 34 can calculate the score Sc3 of the third target based on the change pattern of the similarity to the reference Os of the third target. For example, the calculation unit 34 can increase the score Sc3 as the rising or falling speed of the similarity to the reference Os of the third target is higher. Also, the calculation unit 34 can increase the score Sc3 of the third target with a high similarity to the reference Os of the third target and little change in the similarity.

[0101] In addition, the calculation unit 34 calculates the score Sc4 for each fourth target based on at least one of the past similar periods and similarities between the fourth target and the first target. The calculation method of the score Sc4 is the same as that of the score Sc3. For example, the calculation unit 34 can calculate the score Sc4 using the following formula (2). In the following formula (“), the period when the fourth target was last similar is represented as “Q”. Sc4 = w Q × a Q + w Q+1 × a Q+1 + ······ + w K-1 × a K-1 + w K × a K ···(2)

[0102] In addition, the calculation unit 34 can calculate the score Sc4 of the fourth target based on the past similarity between the fourth target and the first target. For example, the calculation unit 34 can calculate the score Sc4 using the above formula (2) by increasing the weight w for a period with a higher similarity between the fourth target and the first target.

[0103] Further, the calculation unit 34 can calculate the score Sc4 of the fourth target based on the change pattern of the similarity between the fourth target and the first target. For example, the calculation unit 34 can increase the score Sc4 as the rising or falling speed of the similarity between the fourth target and the first target is higher. Also, the calculation unit 34 can increase the score Sc4 of the fourth target with a high similarity between the fourth target and the first target and little change in the similarity.

[0104] In this way, the calculation unit 34 can calculate the score Sc3 for each third target based on at least one of the similarity period and similarity between the third target and the reference Os. Also, the calculation unit 34 can calculate the score Sc4 for each fourth target based on at least one of the past similarity period and similarity between the fourth target and the first target.

[0105] [3.3.6. Providing Unit 35] The providing unit 35 provides the information of the third target specified by the specifying unit 33 to the user U. The provision of the information of the third target to the user U is performed by transmitting from the providing unit 35 to the terminal device 2 via the communication unit 10 and the network N. Thereby, the providing unit 35 can appropriately provide the information of the target that may have the user U's interest.

[0106] The information of the third target is, for example, the information of maritozzo when the third target is "maritozzo", and the information of tapioca when the third target is "tapioca". The providing unit 35 acquires the information of the third target from the contents stored in the content storage unit 22 of the storage unit 11, for example, and transmits the acquired information of the third target to the terminal device 2 via the communication unit 10 and the network N.

[0107] Also, when it is determined by the specifying unit 33 that the third target was not included in the user U's interest range during a predetermined period, the providing unit 35 provides the information of the third target to the user U. Thereby, the providing unit 35 can appropriately provide the information of the target that the user U is likely not to know but may have the user U's interest.

[0108] In addition, when the similarity between the third target and the user U's area of interest in the area of interest during the latest period TA is not outside a predetermined range, the providing unit 35 can provide the user with information on the third target. Also by this, the providing unit 35 can appropriately provide information on a target that the user U is highly likely not to know but that may be of interest to the user U.

[0109] In addition, the providing unit 35 can also provide the user U with information on a third target that satisfies a predetermined condition among the plurality of third targets in terms of the score Sc3 calculated by the calculating unit 34. For example, the providing unit 35 provides the user U with information on a third target for which the score Sc3 calculated by the calculating unit 34 among the plurality of third targets is equal to or higher than a threshold value. Also, the providing unit 35 provides the user U with information on the third target for which the score Sc3 calculated by the calculating unit 34 among the plurality of third targets is the highest.

[0110] In this way, since the providing unit 35 provides the user U with information on the third target based on the score Sc3 calculated by the calculating unit 34, when there are a plurality of third targets, the providing unit 35 can provide the user U with more appropriate information on the third target.

[0111] In addition, the providing unit 35 can also provide the user U with information on a fourth target specified by the specifying unit 33 in addition to the information on the third target specified by the specifying unit 33. The provision of the information on the fourth target to the user U is performed by transmitting it from the providing unit 35 to the terminal device 2 via the communication unit 10 and the network N. Thereby, the providing unit 35 can appropriately provide information on a target that may be of interest to the user U.

[0112] In addition, when the third specifying unit 42 determines that the fourth target was not included in the user U's range of interests during a predetermined period, the providing unit 35 provides the user U with information about the fourth target. In this way, since the providing unit 35 provides the user U with information about the fourth target that was similar to the first target in the past, it can appropriately provide information about targets that may have the user U's interests. Also, the providing unit 35 can bring the fourth target closer to the first target in the interest space after the next period TA, increasing the likelihood that the user U will be interested in the fourth target.

[0113] In addition, in the interest space in the latest period TA, when the similarity between the fourth target and the user U's range of interests is not outside a predetermined range, the providing unit 35 can provide the user with information about the fourth target. Also by this, the providing unit 35 can appropriately provide information about targets that are likely unknown to the user U but may have the user U's interests.

[0114] In addition, the providing unit 35 can also provide the user U with information about the fourth target among the plurality of fourth targets that satisfies a predetermined condition calculated by the calculating unit 34. For example, the providing unit 35 provides the user U with information about the fourth target among the plurality of fourth targets for which the score Sc4 calculated by the calculating unit 34 is equal to or greater than a threshold value. Also, the providing unit 35 provides the user U with information about the fourth target among the plurality of fourth targets for which the score Sc4 calculated by the calculating unit 34 is the highest.

[0115] In this way, since the providing unit 35 provides the user U with information about the fourth target based on the score Sc4 calculated by the calculating unit 34, when there are a plurality of fourth targets, it can provide the user U with more appropriate information about the fourth target.

[0116] Note that the providing unit 35 can provide the information on the third target and the information on the fourth target to the user U in a push type or a pull type. For example, the providing unit 35 can cause the information on the third target and the information on the fourth target to be pop-up displayed on the terminal device 2 by the application installed in the terminal device 2, or can transmit the information to the email address of the user U by email. Further, when the user U accesses the information processing device 1 using the terminal device 2, the providing unit 35 can also provide the information on the third target and the information on the fourth target to the user U by transmitting the information on the third target and the information on the fourth target to the terminal device 2. Note that the method of providing the information on the third target and the information on the fourth target to the user U is not limited to these methods.

[0117] [4. Processing Procedure] Next, with reference to FIG. 11, the processing procedure by the information processing device 1 according to the embodiment will be described. FIG. 11 is a flowchart showing the processing procedure by the processing unit 12 of the information processing device 1 according to the embodiment.

[0118] As shown in FIG. 11, the processing unit 12 of the information processing device 1 determines whether it is the timing for the learning process of the interest model (step S10). The timing for the learning process of the interest model is, for example, the timing that occurs every period TA, but is not limited to such an example.

[0119] When the processing unit 12 determines that it is the timing for the learning process of the interest model (step S10: Yes), the processing unit 12 generates an 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).

[0120] When the process in step S12 is completed, or when it is determined that it is not the timing for learning the interest model (step S10: No), the processing unit 12 determines whether it is the timing for determining the user's interest (step S13). The timing for determining the user's interest is, for example, the timing that occurs every period TA, but is not limited to such an example.

[0121] When the processing unit 12 determines that it is the timing for determining the user's interest (step S13: Yes), it identifies the user U's interest position based on the user U's search query (step S14).

[0122] When the process in step S14 is completed, or when it is determined that it is not the timing for determining the user's interest (step S13: No), the processing unit 12 determines whether it is the timing for determining the information provision target (step S15). The timing for determining the information provision target is the timing after the user U's interest position is identified in step S14. For example, the timing for determining the information provision target is the timing immediately after the user U's interest position is identified in step S14 or the timing when the user U accesses the information processing apparatus 1 using the terminal device 2.

[0123] When the processing unit 12 determines that it is the timing for determining the information provision target (step S15: Yes), it performs information provision processing (step S16). The process in step S16 is the process of steps S20 to S25 shown in FIG. 12, which will be described in detail later.

[0124] When the process in step S16 is completed, or when it is determined that it is the timing for determining the information provision target (step S15: No), the processing unit 12 determines whether it is the timing for ending the operation (step S17). The processing unit 12 determines that it is the timing for ending the operation, for example, when the power of the information processing apparatus 1 is turned off.

[0125] When the processing unit 12 determines that it is not the operation end timing (step S17: No), the process proceeds to step S10. When the processing unit 12 determines that it is the operation end timing (step S17: Yes), the process shown in FIG. 11 ends.

[0126] FIG. 12 is a flowchart showing an information providing procedure by the processing unit 12 of the information processing apparatus 1 according to the embodiment. As shown in FIG. 12, the processing unit 12 identifies a first target that has come to be included in the user U's area of interest in the area of interest indicated by the area of interest space information generated in step S12 of FIG. 11 (step S20).

[0127] Next, the processing unit 12 identifies a second target that was similar to the first target identified in step S20 in the past (step S21). Further, when the state at the past time point when the second target identified in step S21 was similar to the first target is set as the state of the reference Os, the processing unit 12 identifies a target similar to the state of such reference Os as the third target (step S22). Then, the processing unit 12 provides the information of the third target identified in step S22 to the user U (step S23).

[0128] Also, the processing unit 12 identifies, as a fourth target, a target that was similar to the first target before the second target (step S24), provides the information of the identified fourth target to the user U (step S25), and ends the process shown in FIG. 12.

[0129] 〔5. Modification Example〕 The above-described information processing apparatus 1 may be implemented in various different forms other than the above-described embodiment. Therefore, hereinafter, other embodiments of the information processing apparatus 1 will be described.

[0130] The processing unit 12 of the information processing apparatus 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 also generate an interest model for each region by learning the features of each of a plurality of search terms that satisfy a predetermined condition among a plurality of search terms used by a plurality of users U within a target region, where the plurality of search terms having similar features.

[0131] In addition, the processing unit 12 can form an interest space for each attribute of the user U based on the interest model for each attribute of the user U. For example, the processing unit 12 can also generate an interest model for each specific attribute by learning the features of each of a plurality of search terms that satisfy a predetermined condition among a plurality of search terms used by a plurality of users U having a specific attribute, where the plurality of search terms having similar features.

[0132] Also, the processing unit 12 generates an interest model for the period TA based on a plurality of search queries transmitted from a plurality of terminal devices 2 by a plurality of users U within the period TA, but is not limited to such an 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 transmitted from a plurality of terminal devices 2 by a plurality of users U within a period including the period TA before the P period and the latest period TA. P is an integer of 1 or more.

[0133] In addition, the processing unit 12 can also specify the interest range of the user U for each user U based on a plurality of search queries transmitted from the terminal device 2 by the same user U within each period TB. The period TB is, for example, a period longer or shorter than the period TA. Note that the period TB may be a period in which the number of search queries newly received from the same user U by the information processing apparatus 1 or the number of new search terms is equal to or greater than a preset threshold.

[0134] 〔6. Hardware Configuration〕 The information processing apparatus 1 according to the above-described embodiment is realized by a computer 80 configured as shown in FIG. 13, for example. FIG. 13 is a hardware configuration diagram showing an example of a computer 80 that realizes the functions of the information processing apparatus 1 according to the embodiment. The computer 80 includes 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.

[0135] The CPU 81 operates based on a program stored in the ROM 83 or the HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, a program dependent on the hardware of the computer 80, and the like.

[0136] The HDD 84 stores a program executed by the CPU 81, data used by such a program, and the like. 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.

[0137] The CPU 81 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 86. The CPU 81 acquires data from the input device via the input / output interface 86. Further, the CPU 81 outputs data generated via the input / output interface 86 to the output device.

[0138] The media interface 87 reads programs or data stored in the recording medium 88 and provides them to the CPU 81 via the RAM 82. The CPU 81 loads such a program 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 Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0139] The CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing the program loaded onto the RAM 82. Also, the data in the storage unit 11 is stored in the HDD 84. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88. As another example, these programs may be acquired from other devices via the network N.

[0140] 〔7. Others〕 Also, among the various processes described in the above-described embodiments and modified examples, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above-described documents and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0141] Also, each component of each device shown in the drawings is conceptually functional and does not necessarily need to be physically configured as shown in the drawings. That is, the specific form of the distribution and integration of each device is not limited to that shown, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads and usage situations.

[0142] In addition, the above-described embodiments and modifications can be appropriately combined within a range that does not cause inconsistency in the processing content.

[0143] 〔8. Effects〕 As described above, the information processing apparatus 1 according to the embodiment includes a first specifying unit 40, a second specifying unit 41, and a providing unit 35. The first specifying unit 40 specifies a first target and a second target that was similar in the past such that each of a plurality of targets including the first target is represented by a vector in an interest space where the vectors are updated every predetermined period and is included in the interest range of the user U according to the relevance to the interests of a plurality of users U. The second specifying unit 41 specifies a third target that is similar to the reference based on the second target at a past time point that was similar to the first target. The providing unit 35 provides the user U with information on the third target. Thereby, the information processing apparatus 1 can appropriately provide information on a target that may be of interest to the user U.

[0144] In addition, the second specifying unit 41 specifies, as the third target, a target that is similar to the reference and has an attribute in common with the second target. Thereby, the information processing apparatus 1 can specify, as the third target, a target that has a high relevance to the second target by the second specifying unit 41.

[0145] In addition, the information processing apparatus 1 includes a calculating unit 34 that calculates a score Sc3 for each third target based on at least one of the similarity period and the similarity degree of the third target with respect to the reference. The providing unit 35 provides the user U with information on the third target among the plurality of third targets that satisfies a predetermined condition calculated by the calculating unit 34. Thereby, the information processing apparatus 1 can more appropriately provide information on a target that may be of interest to the user U.

[0146] In addition, the providing unit 35 provides the user U with information on the third target when the third target is not outside a predetermined range from the interest range of the user U. Thereby, the information processing apparatus 1 can more appropriately provide information on a target that may be of interest to the user U.

[0147] Further, the information processing apparatus 1 includes a third specifying unit 42 that specifies a fourth target that was similar before the first target became similar to the second target. The providing unit 35 provides the user U with information that further includes the fourth target in addition to the information on the third target. Thereby, the information processing apparatus 1 can more appropriately provide information on targets that may be of interest to the user U.

[0148] Also, the first specifying unit 40 inputs the search term used by the user U into a learned model that has learned the features of each of the plurality of search terms such that two or more search terms satisfying predetermined conditions among the plurality of search terms used by the plurality of users U have similar features, and specifies the range of the user U's interests based on the vector of the search term obtained. Thereby, the information processing apparatus 1 can more appropriately provide information on targets that may be of interest to the user U.

[0149] Further, the information processing apparatus 1 includes a learning unit 32 that generates a learned model using a plurality of search terms used by a plurality of users U. Thereby, the information processing apparatus 1 can more appropriately provide information on targets that may be of interest to the user U.

[0150] As described above, the embodiments of the present application have been described in detail with reference to the drawings, but this is an example, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0151] Also, the "section (section, module, unit)" described above can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

Explanation of Reference Numerals

[0152] 1 Information processing apparatus 2, 21 to 2 n Terminal device 10 Communication unit 11 Memory unit 12 Processing unit 20 Search information memory unit 21 User information memory unit 22 Content memory unit 23 Interest space information memory unit 30 Reception unit 31 Search unit 32 Learning unit 33 Identification unit 34 Calculation unit 35 Provision unit 40 First identification unit 41 Second identification unit 100 Information processing system N Network

Claims

1. A first specifying unit that specifies a second object that was similar to a first object in the past so that each of a plurality of objects including the first object is represented by a vector in an interest space where the vectors are updated every predetermined period and are included in the user's interest range in accordance with the relevance to the interests of a plurality of users; A second specifying unit that specifies a third object that is similar to the reference when the reference is the second object at a past time point that was similar to the first object; And a providing unit that provides information on the third object to the user. An information processing apparatus characterized by the above.

2. The second specifying unit: Specifies, as the third object, an object that is similar to the reference and has an attribute common to the second object. The information processing apparatus according to claim 1, characterized by the above.

3. A calculating unit that calculates a score for each third object based on at least one of a similarity period and a similarity degree between the third object and the reference, The providing unit: Provides information on a third object that satisfies a predetermined condition calculated by the calculating unit among a plurality of the third objects to the user. The information processing apparatus according to claim 1 or 2, characterized by the above.

4. The providing unit: Provides information on the third object to the user when the third object is not outside a predetermined range from the user's interest range. The information processing apparatus according to any one of claims 1 to 3, characterized by the above.

5. A third specifying unit that specifies a fourth object that was similar before the first object was similar to the second object, The providing unit: Provides information including the fourth object in addition to the information on the third object to the user. The information processing apparatus according to any one of claims 1 to 4, characterized by the above.

6. The first specifying unit: Specifies the user's interest range based on a vector of the search term obtained by inputting the search term used by the user into a learned model that has learned features of each of the plurality of search terms such that two or more search terms that satisfy a predetermined condition among the plurality of search terms used by the plurality of users have similar features. The information processing apparatus according to any one of claims 1 to 5, characterized by the above.

7. A learning unit that generates the learned model using the plurality of search terms used by the plurality of users. The information processing apparatus according to claim 6, characterized by the above.

8. An information processing method executed by a computer, comprising: a first specifying step of specifying a second object that was similar to a first object in the past, such that the first object and each of a plurality of objects including the first object are represented by vectors according to the relevance to the interests of a plurality of users, and the vectors are updated every predetermined period, and the first object is included in the user's interest range in the interest space; a second specifying step of specifying a third object that is similar to the reference when the second object at a past time similar to the first object is used as the reference; a providing step of providing information on the third object to the user. An information processing method characterized by the above.

9. a first specifying procedure for specifying a second object that was similar to a first object in the past, such that the first object and each of a plurality of objects including the first object are represented by vectors according to the relevance to the interests of a plurality of users, and the vectors are updated every predetermined period, and the first object is included in the user's interest range in the interest space; a second specifying procedure for specifying a third object that is similar to the reference when the second object at a past time similar to the first object is used as the reference; causing a computer to execute a providing procedure for providing information on the third object to the user. An information processing program characterized by the above.

Images