JP7008152B1 - Information processing equipment, information processing methods and information processing programs - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device, an information processing method and an information processing program capable of appropriately estimating a relationship between queries. An information processing apparatus according to the present application includes an acquisition unit, an extraction unit, and an estimation unit. The acquisition unit acquires history information regarding the user's search behavior when a search result using a second query different from the first query is provided based on the search request by the first query input by the user. The extraction unit extracts the characteristic information of the search behavior including the context in the search behavior based on the history information acquired by the acquisition unit. The estimation unit estimates the relationship between the first query and the second query based on the change in the feature information extracted by the extraction unit. [Selection diagram] FIG. 5

Description

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

Conventionally, there has been provided a technique for performing a search service for various information by using a character string input by a user as a search query (hereinafter, simply referred to as a "query"). In such a search service, when a query entered by a user contains an error, a technique is provided in which the error is converted and then searched, and the search result is provided to the user (for example, a patent). See Document 1).

Japanese Patent No. 6529456

However, when the above-mentioned conventional technique is used, it is difficult to determine the relationship between the input query and the query to be used for the actual search. For example, in the prior art, when the second character string is input by using a dictionary in which the first character string and the second character string that can be input as an erroneous description of the first character string are associated with each other, the second character is input. It's just converting the column to the first string.

Therefore, in the prior art, if the user wants to use the second character string input by the user as a query as it is, the user may not be able to obtain the desired search result. Therefore, it is desired to properly estimate the relationship between queries.

The present application has been made in view of the above, and an object of the present application is to provide an information processing apparatus, an information processing method, and an information processing program capable of appropriately estimating the relationship between queries.

The information processing apparatus according to the present application includes an acquisition unit, an extraction unit, and an estimation unit. The acquisition unit acquires history information regarding the search behavior of the user when a search result using a second query different from the first query is provided based on a search request by the first query input by the user. do. The extraction unit extracts characteristic information of the search behavior including a context for the search behavior based on the history information acquired by the acquisition unit. The estimation unit estimates the relationship between the first query and the second query based on the change in the feature information extracted by the extraction unit.

According to one aspect of the embodiment, there is an effect that the relationship between queries can be appropriately estimated.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a processing explanatory diagram (No. 1) of information processing according to the embodiment. FIG. 3 is a process explanatory diagram (No. 2) of information processing according to the embodiment. FIG. 4 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 5 is a block diagram showing a configuration example of the information processing apparatus according to the embodiment. FIG. 6 is a process explanatory diagram (No. 1) of the estimation process according to the embodiment. FIG. 7 is a process explanatory diagram (No. 2) of the estimation process according to the embodiment. FIG. 8 is a process explanatory diagram (No. 3) of the estimation process according to the embodiment. FIG. 9 is a flowchart showing a processing procedure executed by the information processing apparatus according to the embodiment. FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus according to the embodiment.

Hereinafter, an information processing apparatus, an information processing method, and an embodiment for implementing an information processing program (hereinafter referred to as “embodiments”) according to the present application will be described in detail with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate explanations are omitted.

[1. An example of information processing]
First, an example of information processing according to the embodiment will be described with reference to FIGS. 1 to 3. FIG. 1 is a diagram showing an example of information processing according to an embodiment. Further, FIG. 2 is a processing explanatory diagram (No. 1) of information processing according to the embodiment. Further, FIG. 3 is a processing explanatory diagram (No. 3) of information processing according to the embodiment.

In FIGS. 1 to 3, the information processing apparatus 100 included in the information processing system 1 according to the embodiment uses a second query different from the first query based on the search request by the first query input by the user U. The history information about the search behavior of the user U when the searched result is provided is acquired, and the feature information of the search behavior including the context of the search behavior is extracted based on the acquired history information, and the extracted feature information is extracted. An example of executing a process of estimating the relationship between the first query and the second query based on the change of is shown.

As shown in FIG. 1, the information processing system 1 according to the embodiment includes a user terminal 10 and an information processing device 100.

The user terminal 10 is a user terminal 10-1, 10-2 ... Which is a terminal device used by the user U, that is, the users U1, U2 ... The user U uses the search service, which is one of the services provided by the information processing apparatus 100, by accessing the information processing apparatus 100 from the user terminal 10 via a network (not shown). In the following, "user U" can be appropriately read as "user terminal 10".

The information processing device 100 is a server device that provides various services to the user U. The service provided by the information processing apparatus 100 is, for example, a service that provides various information via various applications and browsers installed in the user terminal 10. In addition to search services, the services provided include, for example, news services, auction services, weather forecast services, shopping services, financial trading (stock trading, etc.) services, route search services, map providing services, travel services, and food and beverage services. Store introduction services, blog services, etc. may be included.

When using the search service, the user U inputs a query, which is a character string as a search keyword, from the user terminal 10 after accessing the information processing apparatus 100. Hereinafter, the query input by the user U is referred to as a "first query". Then, the user U transmits the search request by the first query to the information processing apparatus 100 (step S1).

Here, the first query may contain an error. The information processing apparatus 100 has dictionary information in which a first query that can be input as an erroneous description and a second query, which is a character string that is assumed to be correct for the first query, are associated with each other, and is used. When the first query is input, the first query is converted into the second query and the information is searched using the second query.

Then, the information processing apparatus 100 transmits the search result using the second query to the user U (step S2). The user U selects one of the search results to be browsed accordingly (step S3).

The flow from steps S1 to S3 is shown in FIG. 2 in an easy-to-understand manner. FIG. 2 shows a part of the search result list screen displayed on the user terminal 10. In FIG. 2, when the user U inputs the first query "XXXX" and executes the search, "XXXXX" is included in the error candidate of "YYYY", and the information processing apparatus 100 responds to "". An example of providing a search result using "YYYY" as a second query is shown.

As shown in the figure, the search result by the first query "XXXX" is also displayed below, and if the user U wants the search result by the first query, he / she can select this. can. However, because it is treated with a lower priority than the search result by the second query, such as being displayed at the bottom, it takes longer than the user U to select the search result by the second query before selecting this. It will take.

Returning to the description of FIG. The information processing apparatus 100 collects and stores historical information about the user U's behavior including the search behavior of the user U in steps S1 to S3 from the user terminal 10 at any time.

For the history information, for example, from the time when the search by the first query input by the user U is requested, the search result using the second query different from the first query is provided to the user U, and the search is performed by the user U. Includes the elapsed time to the point when the result was selected. Further, the history information includes, for example, a context estimated from the behavior of the user U.

The context is information indicating the situation of the user U when the user U takes various actions including the search action, the environment of the user U, and the like. Specifically, the context includes the geographic attribute of the user U (position when the search action is taken, etc.), the demographic attribute (age, gender, income, occupation, etc.), and the psychographic attribute (values, etc.). , Lifestyle, personality, taste, etc.) are included.

Then, the information processing apparatus 100 extracts feature information regarding the search behavior of the user U based on the history information at any time (step S4). The feature information includes the feature regarding the elapsed time until the selection described above and the feature regarding the context in the search behavior.

These features are, for example, statistical features. The information processing apparatus 100 extracts, for example, the standard deviation of the elapsed time described above. For example, FIG. 1 shows an example in which the information processing apparatus 100 extracts the standard deviation σ with respect to the median μ of the elapsed time. Further, the information processing apparatus 100 extracts, for example, the above-mentioned context distribution.

Then, the information processing apparatus 100 estimates the relationship between the queries, that is, between the first query and the second query, based on the change in the extracted feature information on the time series (step S5).

Specifically, as shown in FIG. 3, the information processing apparatus 100 estimates that the relationship between the first query and the second query is high, for example, while the degree of variation in the elapsed time is small. That is, the information processing apparatus 100 estimates that the first query is an error in the second query.

Further, the information processing apparatus 100 estimates that the relationship between the first query and the second query is low, for example, when the degree of variation in the elapsed time becomes large. That is, the information processing apparatus 100 estimates that the first query is not an error in the second query, but a new word. Thereby, the information processing apparatus 100 can exclude the first query from, for example, the above-mentioned error candidate of the second query.

Further, the information processing apparatus 100 estimates that the relationship between the first query and the second query is high, for example, while the degree of variation in the context distribution is small. That is, in this case, the information processing apparatus 100 estimates that the context of the user U's search behavior is uniform, and that the first query is used according to the known usage so far. Therefore, the case where the first query is an error of the second query is included.

Further, the information processing apparatus 100 estimates that the relationship between the first query and the second query is low, for example, when the degree of variation in the context distribution becomes large. That is, it is presumed that the information processing apparatus 100 is used in a new usage different from the known usage. Therefore, the case where the first query is input as a new word instead of the typographical error of the second query is included.

In this way, it is possible to presume that it is used in a new usage, in other words, by being able to detect that a new feature appears in a specific character string, various analyzes such as targeting and so-called "buzz" It can be used to detect the occurrence of an event such as ".

As described above, in the information processing method according to the embodiment, the user when the search result using the second query different from the first query is provided based on the search request by the first query input by the user U. The history information about the search behavior of U is acquired, the feature information of the search behavior including the context of the search behavior is extracted based on the acquired history information, and the first query and the first query are based on the change of the extracted feature information. Estimate the relationship with the second query.

Therefore, according to the information processing method according to the embodiment, the relationship between the queries can be appropriately estimated.

Hereinafter, the information processing apparatus 100 that performs the above-mentioned information processing and the information processing system 1 including the information processing apparatus 100 will be described in detail.

[2. Configuration of information processing system 1]
Next, the configuration of the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As illustrated in FIG. 4, the information processing system 1 according to the embodiment includes a plurality of user terminals 10-1 to 10-n and an information processing apparatus 100.

These various devices are connected so as to be communicable by wire or wirelessly via the network N. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (mobile telephone network, fixed telephone network, etc.), a regional IP (Internet Protocol) network, and the Internet. The network N may include a wired network or may include a wireless network.

As described above, the user terminal 10 is a terminal device used by the user U. The user terminal 10 is, for example, an information processing device such as a mobile phone including a smartphone, a tablet terminal, a desktop PC, a notebook PC, or a PDA (Personal Digital Assistant). Further, the user terminal 10 also includes a wearable device which is a glasses-type or watch-type information processing device.

The user terminal 10 acquires various information according to the operation by the user U and the function of the user terminal 10 (for example, a function of executing an application for using a search service, a browser function, etc.), and the acquired information. Generates and sends information according to the above. For example, the user terminal 10 accesses the site of the search service provided by the information processing apparatus 100 via the network N. Then, by designating a query that is a search keyword that the user U wants to search for, for example, the user terminal 10 transmits the query to the information processing apparatus 100.

The information processing device 100 is a server device that functions as a service providing server that provides a search service to the user terminal 10. Further, the information processing apparatus 100 extracts the feature information of the search behavior of the user U based on the history information of the search service, and estimates the relationship between the queries based on the change of the extracted feature information.

Note that FIG. 4 shows a case where one information processing device 100 has functions of providing a search service, extracting feature information, and estimating a relationship between queries. For example, a plurality of information processing devices 100 are shown. However, each of these functions may be shared.

[3. Information processing device 100]
Next, a configuration example of the information processing apparatus 100 will be described with reference to FIG. FIG. 5 is a block diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. Note that FIG. 5 shows only the components necessary for the explanation of the information processing apparatus 100, and the description of general components is omitted.

As shown in FIG. 5, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from an administrator or the like who uses the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. ) May have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10 via the network N.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. In the example of FIG. 5, the storage unit 120 is a storage unit 120. It has a history information storage unit 121, a feature information storage unit 122, and an estimation information storage unit 123.

(History information storage unit 121)
The history information storage unit 121 stores various information regarding the history of the search behavior of the user U acquired by the acquisition unit 131 described later, that is, the above-mentioned history information. Therefore, the history information storage unit 121 provides the user U with a search result using a second query different from the first query from the first time point when the search by the first query input by the user U is requested, for example. , The elapsed time up to the second time point when the search result is selected by the user U is stored. Further, the history information storage unit 121 stores, for example, the context estimated from the search behavior of the user U.

(Characteristic information storage unit 122)
The feature information storage unit 122 stores feature information related to the search behavior of the user U extracted by the extraction unit 132, which will be described later. As described above, the feature information includes the above-mentioned statistical features related to elapsed time and statistical features related to context.

(Estimated information storage unit 123)
The estimation information storage unit 123 stores information regarding the estimation result estimated by the estimation unit 133, which will be described later. For example, the estimation information storage unit 123 stores a new word estimated as a new word. Further, for example, the estimation information storage unit 123 stores the estimated new usage in association with a word (including a new word).

(About control unit 130)
The control unit 130 is a controller, and for example, various programs (information processing programs) stored in a storage device inside the information processing device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Corresponding to one example) is realized by executing RAM as a work area. Further, the control unit 130 is, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 130 includes an acquisition unit 131, an extraction unit 132, an estimation unit 133, a processing unit 134, and a provision unit 135, and has functions and operations of information processing described below. Realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be any other configuration as long as it can perform information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 5, and may be another connection relationship.

The control unit 130 acquires history information regarding the search behavior of the user U when a search result using a second query different from the first query is provided based on the search request by the first query input by the user U. Then, based on the acquired history information, the characteristic information of the search behavior including the context of the search behavior is extracted, and the relationship between the first query and the second query is based on the change of the extracted characteristic information. To estimate.

(About acquisition unit 131)
The acquisition unit 131 acquires history information regarding the search behavior of the user U when a search result using a second query different from the first query is provided based on the search request by the first query input by the user U. do.

Specifically, the acquisition unit 131 acquires the search request by the first query input by the user U via the communication unit 110. Further, the acquisition unit 131 acquires the search result selected by the user U via the communication unit 110. Further, the acquisition unit 131 acquires the history information via the communication unit 110 and stores it in the history information storage unit 121.

(About the extraction unit 132)
The extraction unit 132 extracts the characteristic information of the search behavior including the context in the search behavior of the user U based on the history information stored in the history information storage unit 121.

The extraction unit 132 extracts, for example, the standard deviation of the elapsed time described above. Further, the extraction unit 132 extracts, for example, the above-mentioned context distribution. The distribution of the context will be described later with reference to FIGS. 6 to 8. Further, the extraction unit 132 stores the extracted feature information in the feature information storage unit 122.

(About estimation unit 133)
The estimation unit 133 estimates the relationship between the first query and the second query based on the change in the feature information stored in the feature information storage unit 122. Further, the estimation unit 133 stores information about the estimated estimation result in the estimation information storage unit 123.

Here, the estimation process executed by the estimation unit 133 will be described more specifically. FIG. 6 is a process explanatory diagram (No. 1) of the estimation process according to the embodiment. Further, FIG. 7 is a process explanatory diagram (No. 2) of the estimation process according to the embodiment. Further, FIG. 8 is a process explanatory diagram (No. 3) of the estimation process according to the embodiment.

In the description using FIGS. 6 to 8, a case where the relationship between queries is estimated based on the above-mentioned context distribution will be described.

As shown in FIG. 6, for example, it is assumed that there is a known word "Kimetsu no Giant" regarding a known media work, and there is "Eradication Giant" as the first query for this. Initially, the "Giant of Eradication" is assumed to be a false candidate for the "Giant of Demon".

In such a case, the context group estimated from the search behavior of the user U to which the first query "Giant of Eradication" is input is, as shown in FIG. 7, at the time point T1, the age "teen" and the gender "male". And women, profession "student", search time zone "broadcast time zone of" demon giant "", location information "all over the country", etc.

On the other hand, as shown in the figure, at time point T2 after time point T1, age "20s or older", gender "male and female", occupation "worker", search time zone "B prefectural police" accident eradication " It is assumed that "Giants" campaign CM broadcast ", location information" B prefecture ", etc. It should be noted that there is usually a certain number of days between the time point T1 and the time point T2.

The estimation unit 133 estimates the relationship between queries by comparing the distribution of contexts at each of these time points T1 and T2. As shown in the figure, the contents of the context and its changes are various, in other words, it can be said that the context has multidimensional characteristics.

Therefore, the estimation unit 133 calculates the distribution of the context at each of the time points T1 and T2 using, for example, a machine learning algorithm.

Specifically, as shown in FIG. 8, for example, the estimation unit 133 calculates the distribution of the context by dimension reduction using UMAP (Uniform Manifold Approximation and Projection). UMAP is a machine learning non-linear dimensional compression technique that, based on Lehman geometry and algebraic topology, preserves the data structure of high dimensional space and converts it into low dimensional data while minimizing cross-entropy between topologies.

That is, the estimation unit 133 uses the UMAP to convert the feature amount in the high-dimensional space of the context of the search behavior at each of the time points T1 and T2 into a low-dimensional representation by dimension reduction. The figure shows an example in which the estimation unit 133 converts and embeds a feature amount in a high-dimensional space of a context into a three-dimensional low-dimensional space. Each of the circles in the figure corresponds to each of the search actions of the user U.

Here, as shown in the figure, for example, the distribution of the context was gathered in a certain region R1 at the time point T1, but at the time point T2, although the region R1 decreased, the region clearly different from the region R1. It is assumed that the R2 can be seen as a new group.

In such a case, the estimation unit 133 can determine that the degree of variation in the context distribution has increased in the three-dimensional feature space shown in the figure, and therefore it is estimated that the relationship between the first query and the second query is low. That is, the estimation unit 133 estimates that the first query "eradication giant" at time point T2 is used in a new usage different from the known usage. Whether or not the degree of variation in the context distribution is large can be determined, for example, by whether or not the amount of change in the context distribution from the time point T1 to the time point T2 in the above-mentioned three-dimensional space is equal to or greater than a predetermined threshold value. can.

Further, in the description using FIG. 8, an example in which UMAP is used as the dimension reduction algorithm is given, but the algorithm to be used is not limited. For example, as another algorithm, principal component analysis, t-distributed Stochastic Neighbor Embedding, or the like may be used.

(About processing unit 134)
Returning to the description of FIG. The processing unit 134 executes various processes. The processing unit 134 executes a search process based on the first query input by the user U. The processing unit 134 executes the search process using the first query input by the user U. Further, the processing unit 134 generates various information including contents to be provided to the user U.

Further, the processing unit 134 executes the search process using a second query different from the first query input by the user U. When the first query input by the user U is included in the above-mentioned error candidate, the processing unit 134 converts the first query into the second query associated with the first query. Then, the processing unit 134 executes the search process using the converted second query.

(About the provider 135)
The providing unit 135 transmits various information to the user terminal 10 via the communication unit 110. The providing unit 135 provides a search service to the user U. For example, the providing unit 135 transmits the search result, which is the result of the search processing by the processing unit 134, to the user terminal 10. Further, the providing unit 135 transmits various information generated by the processing unit 134 to the user terminal 10. Further, the providing unit 135 provides the estimation result estimated by the estimation unit 133 to the operator of the information processing apparatus 100 and the like.

[4. Processing procedure of information processing apparatus 100]
Next, a processing procedure executed by the information processing apparatus 100 according to the embodiment will be described. FIG. 9 is a flowchart showing a processing procedure executed by the information processing apparatus 100 according to the embodiment.

As shown in FIG. 9, first, the user U when the acquisition unit 131 provides a search result using a second query different from the first query based on the search request by the first query input by the user U. Acquire history information regarding the search behavior of (step S101).

Then, the extraction unit 132 extracts the characteristic information of the search action including the context in the search action based on the acquired history information (step S102).

Then, the estimation unit 133 estimates the relationship between the first query and the second query based on the change in the extracted feature information (step S103). Then, the process is terminated.

[5. Hardware configuration]
The information processing apparatus 100 and the user terminal 10 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the information processing apparatus 100 will be described as an example. FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100 according to the embodiment. The computer 1000 includes a CPU (Central Processing Unit) 1100, a RAM (Random Access Memory) 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, and an input / output interface (I). It includes a / F) 1600 and a media interface (I / F) 1700.

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

The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from another device via the communication network 500 (corresponding to the network N shown in FIG. 4) and sends the data to the CPU 1100, and the data generated by the CPU 1100 is transmitted to another device via the communication network 500. Send to the device.

The CPU 1100 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 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

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

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes each function of the control unit 130 by executing a program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 500.

[6. others〕
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown in the figure.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured.

For example, the acquisition unit 131 and the provision unit 135 shown in FIG. 5 may be integrated. Further, for example, the extraction unit 132 and the estimation unit 133 may be integrated. Further, for example, the information stored in the storage unit 120 may be stored in a predetermined storage device provided externally via the network N.

Further, in the above embodiment, when the information processing apparatus 100 is provided with a search result using a second query different from the first query based on the search request by the first query input by the user U, for example. For acquisition processing to acquire history information related to the search behavior of user U, extraction processing to extract feature information of the search behavior including the context of the search behavior based on the acquired history information, and change of the extracted feature information. Based on this, an example of performing estimation processing for estimating the relationship between the first query and the second query is shown. However, in the information processing device 100 described above, the acquisition device that performs the acquisition process, the extraction device that performs the extraction process, and the estimation device that performs the estimation process may be separated. In this case, the acquisition device has at least the acquisition unit 131. The extraction device has at least an extraction unit 132. The estimation device has at least an estimation unit 133. The processing by the information processing device 100 is realized by the information processing system 1 including the acquisition device, the extraction device, and the estimation device.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

[7. effect〕
The information processing apparatus 100 according to the embodiment includes an acquisition unit 131, an extraction unit 132, and an estimation unit 133. The acquisition unit 131 acquires history information regarding the search behavior of the user U when a search result using a second query different from the first query is provided based on the search request by the first query input by the user U. do. The extraction unit 132 extracts the feature information of the search behavior including the context for the search behavior based on the history information acquired by the acquisition unit 131. The estimation unit 133 estimates the relationship between the first query and the second query based on the change in the feature information extracted by the extraction unit 132.

Therefore, according to the information processing apparatus 100 according to the embodiment, the relationship between queries can be appropriately estimated.

In addition, the estimation unit 133 estimates the relationship between the first query and the second query based on the time-series changes in the statistical features related to the search behavior included in the feature information.

Therefore, according to the information processing apparatus 100 according to the embodiment, the relationship between queries can be appropriately estimated based on the time-series changes in statistical features.

Further, the estimation unit 133 estimates the relationship between the first query and the second query based on the degree of variation in the distribution of the context included in the feature information.

Therefore, according to the information processing apparatus 100 according to the embodiment, the relationship between queries can be appropriately estimated based on the degree of variation in the distribution of the context.

Further, the estimation unit 133 determines the degree of variation at the time point T1 (corresponding to an example of the "first time point") and the degree of variation at the time point T2 after the time point T1 (corresponding to an example of the "second time point"). Estimate the relationship between the first query and the second query by comparing.

Therefore, according to the information processing apparatus 100 according to the embodiment, the relationship between the queries can be appropriately estimated by comparing the degree of variation at the time point T1 with the degree of variation at the time point T2.

Further, the estimation unit 133 estimates that the first query is used in a new usage different from the known usage when the amount of change in the degree of variation from the time point T1 to the time point T2 is equal to or more than a predetermined threshold value. do.

Therefore, according to the information processing apparatus 100 according to the embodiment, it can be estimated that the first query is used in a new usage different from the known usage based on the above degree of variation. In addition, by being able to detect the appearance of a new feature in a specific character string, it can be utilized for various analyzes such as targeting and detection of the occurrence of an event such as so-called "buzz".

The embodiments of the present application have been described in detail with reference to the drawings, but this is an example, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other forms described above.

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

1 Information processing system 10 User terminal 100 Information processing device 110 Communication unit 120 Storage unit 121 History information storage unit 122 Feature information storage unit 123 Estimated information storage unit 130 Control unit 131 Acquisition unit 132 Extraction unit 133 Estimating unit 134 Processing unit 135 Providing unit

Claims (7)

An acquisition unit that acquires history information regarding the user's search behavior when a search result using a second query different from the first query is provided based on a search request by the first query input by the user.
An extraction unit that extracts characteristic information of the search behavior including a context for the search behavior based on the history information acquired by the acquisition unit, and an extraction unit.
An information processing apparatus including an estimation unit that estimates a relationship between the first query and the second query based on a change in the feature information extracted by the extraction unit. The estimation unit
Claim 1 is characterized in that the relationship between the first query and the second query is estimated based on the time-series changes in the statistical features of the search behavior included in the feature information. The information processing device described in. The estimation unit
The information processing apparatus according to claim 2, wherein the relationship between the first query and the second query is estimated based on the degree of variation in the distribution of the context included in the feature information. The estimation unit
To estimate the relationship between the first query and the second query by comparing the degree of variation at the first time point with the degree of variation at the second time point after the first time point. The information processing apparatus according to claim 3. The estimation unit
When the amount of change in the degree of variation from the first time point to the second time point is equal to or greater than a predetermined threshold value, it is estimated that the first query is used in a new usage different from the known usage. The information processing apparatus according to claim 4. It is an information processing method executed by a computer.
An acquisition process for acquiring history information regarding the user's search behavior when a search result using a second query different from the first query is provided based on a search request by the first query input by the user.
An extraction step of extracting characteristic information of the search behavior including a context for the search behavior based on the history information acquired in the acquisition step, and an extraction step.
An information processing method comprising an estimation step of estimating a relationship between the first query and the second query based on a change in the feature information extracted in the extraction step. An acquisition procedure for acquiring history information regarding the user's search behavior when a search result using a second query different from the first query is provided based on a search request by the first query input by the user, and an acquisition procedure.
An extraction procedure for extracting characteristic information of the search behavior including a context for the search behavior based on the history information acquired by the acquisition procedure, and an extraction procedure.
An information processing program characterized by causing a computer to execute an estimation procedure for estimating a relationship between the first query and the second query based on a change in the feature information extracted by the extraction procedure. ..

Images