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

Abstract

To identify strength of predetermined search intention from a search query.SOLUTION: An information processing apparatus includes: an identifying unit which identifies, related tokens input as search query together with reference tokens; a classifying unit which classifies each of the related tokens into axes on the basis of similarities between the related tokens identified by the identifying unit and character strings indicating predetermined axes corresponding to search intentions of the reference tokens; an estimation unit which estimates strength of search intentions corresponding to the axes, on the basis of the number of input related tokens classified into the axes by the classifying unit; and a providing unit which provides a content indicating the strength of the search intentions estimated by the estimation unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for analyzing a user's search intent based on a search query entered by the user. One example of such a technique is to obtain multiple groups of co-occurring queries based on the search query, and extract co-occurring queries that are common to different groups from the multiple groups of co-occurring queries as common queries, thereby extracting search intent that is not directly expressed in the search query. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5256273 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques cannot be said to be capable of grasping the strength of a predetermined search intent from a search query.

[0005] For example, the above-mentioned techniques merely extract the user's hidden search intent, and may not be able to grasp the strength of a given search intent from a search query.

[0006] The present application has been made in view of the above, and aims to grasp the strength of a predetermined search intent from a search query. [Means for solving the problem]

[0007] The information processing device according to the present application is characterized by having an identification unit that identifies related tokens input together with a reference token as a search query; a classification unit that classifies each of the related tokens identified by the identification unit into a predetermined axis corresponding to the search intent of the reference token based on the similarity between the related tokens identified by the identification unit and a string indicating the predetermined axis corresponding to the search intent of the reference token; an estimation unit that estimates the strength of the search intent corresponding to the axis based on the number of input related tokens classified into the axis by the classification unit; and a provision unit that provides content indicating the strength of the search intent estimated by the estimation unit. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to obtain an effect that the strength of a predetermined search intention can be grasped from a search query. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram showing an example of content provided by the information processing device 10. As shown in FIG. [Figure 3] FIG. 3 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the search history database 31 according to the embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. In the following embodiments, the same components are denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] 1. Embodiment Information processing implemented by an information processing device or the like according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that in Fig. 1, it is assumed that the information processing according to the embodiment is implemented by an information processing device 10, which is an example of the information processing device according to the present application.

[0012] As shown in FIG. 1, an information processing system 1 according to the embodiment includes an information processing device 10, a user terminal 100, and a destination terminal 200. The information processing device 10, the user terminal 100, and the destination terminal 200 are connected to each other via a network N (see, for example, FIG. 3) so as to be able to communicate with each other via a wired or wireless connection. The network N is, for example, a wide area network (WAN) such as the Internet. Note that the information processing system 1 shown in FIG. 1 may include a plurality of information processing devices 10, a plurality of user terminals 100, and a plurality of destination terminals 200.

[0013] 1 is an information processing device that performs information processing, and is realized by, for example, a server device or a cloud system. For example, the information processing device 10 acquires information indicating a history of search queries entered by a user in a predetermined search service. Then, the information processing device 10 identifies related tokens that were entered as the search query together with the reference token, and provides content that indicates a predetermined strength of search intent of the reference token to a predetermined destination based on the identified related tokens.

[0014] In this embodiment, each character string separated by a space in the search query may be used as a token, or each character string (part of speech) obtained by dividing the search query through morphological analysis may be used as a token.

[0015] The user terminal 100 shown in Fig. 1 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example shown in Fig. 1, the user terminal 100 is a smartphone used by a user.

[0016] The destination terminal 200 shown in Fig. 1 is an information processing device used by a destination of content. The destination terminal 200 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, etc. In the example shown in Fig. 1, the destination terminal 200 is a notebook PC used by an administrator of the destination.

[0017] An example of information processing performed by information processing device 10 will be described below with reference to FIG. 1. In the following description, user terminal 100 will be described as user terminals 100-1 to 100-N (N is any natural number) depending on the user using user terminal 100. For example, user terminal 100-1 is the user terminal 100 used by a user (user U1) identified by user ID "U1". In the following description, user terminals 100-1 to 100-N will be referred to as user terminal 100 when there is no particular distinction between them. In the following description, user terminal 100 may be considered to be the same as the user. That is, in the following description, user U1 can also be read as user terminal 100-1.

[0018] An example will be shown in which the destination terminal 200 is used by an administrator M1. In the following description, the destination terminal 200 may be regarded as the same as the administrator M1. In other words, hereinafter, the administrator M1 may be read as the destination terminal 200.

[0019] First, the information processing device 10 acquires a search query input by a user (step S1). For example, the information processing device 10 acquires from the user terminal 100 information indicating a history of search queries input by each user in a search service provided to the user terminal 100, identification information for identifying the user (user ID), and the like.

[0020] Next, the information processing device 10 identifies, from the search query input by the user, the related tokens input as the search query together with the reference token #1 (for example, the name of a product provided by the administrator M1) designated by the administrator M1, who is the recipient of the content (step S2). For example, the information processing device 10 identifies, as related tokens, the character strings "after-sales service," "color scheme," "best seller," "impressions," and so on, from the search query "reference token #1 after-sales service," "reference token #1 color scheme," "reference token #1 best seller," "reference token #1 impressions," and so on, input by the user.

[0021] Next, the information processing device 10 classifies each related token into each axis based on the similarity between the identified related token and the character string indicating the axis corresponding to the search intent of the reference token (step S3). For example, the information processing device 10 calculates the similarity between the related token and character strings indicating each axis corresponding to the search intent, such as "review," "service," "price," "compensation," "discount," "location," "performance," and so on, and classifies the related token into an axis corresponding to a character string whose similarity to the related token is equal to or greater than a predetermined threshold. As a specific example, the information processing device 10 calculates the similarity between the related token and each of the list of character strings indicating the axis "review," such as "review," "impression," "best seller," and so on, and classifies the related token into the axis "review" if the similarity to any of the character strings included in the list is equal to or greater than a predetermined threshold.

[0022] Here, the information processing device 10 converts related tokens and each character string indicating an axis into a vector using, for example, a model that converts character strings into vectors, and classifies each related token into each axis based on the similarity between the vector of the related token and the vector of each character string indicating the axis. Note that the learning of the above model may be performed using, for example, various techniques related to word2vec.

[0023] Furthermore, the information processing device 10 may determine a list of character strings indicating an axis using the above model. For example, the information processing device 10 converts the character string "review" indicating the axis and a predetermined group of character strings (for example, a group of character strings extracted using a thesaurus) into vectors using the above model, extracts a predetermined number (for example, 10) of character strings from the group of character strings in descending order of similarity to the vector of "review", and sets the extracted character strings as a list of character strings indicating the axis "review".

[0024] The axes may be specified by the administrator M1 or may be set by the information processing device 10. The number of axes may be more than eight or less than eight.

[0025] Next, the information processing device 10 estimates the strength of search intent (score) of each reference token #1 corresponding to each axis based on the number of inputs of related tokens classified on each axis (step S4). For example, the information processing device 10 estimates a score based on the number of times the related tokens classified on each axis were input by users, a score based on the number of users (number of unique users) who input the related tokens classified on each axis, or a score based on the lift value of basket analysis.

[0026] Next, the information processing device 10 generates content showing the strength of each search intent for the reference token #1 (step S5). For example, the information processing device 10 generates content showing a radar chart L1 showing the search intent score corresponding to each axis. The information processing device 10 also generates content showing a bar graph G1 showing the score based on the number of times related tokens classified on each axis were input by users, or the score based on the number of users who input related tokens classified on each axis.

[0027] Next, the information processing device 10 provides the generated content to the administrator M1 (step S6). For example, by referring to the radar chart L1 or the bar graph G1, the administrator M1 can understand the user's image and needs regarding the product (reference token #1) provided by the administrator M1, which are indicated by the strength of each search intention for the product.

[0028] It should be noted that the content provided by the information processing device 10 is not limited to the above. Here, the content provided by the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of content provided by the information processing device 10.

[0029] For example, the information processing device 10 receives the designation of reference tokens #2 and #3 (e.g., product names provided by other companies) in addition to reference token #1 from the administrator M1. The information processing device 10 then performs the above-described steps S2 to S4 for reference tokens #2 and #3 to estimate the search intent scores for reference token #2 and reference token #3. The information processing device 10 then generates a radar chart L2 showing the search intent scores for reference tokens #1 to #3 and provides it to the administrator M1. Here, in the example of FIG. 2, the administrator M1 can determine that the search intent corresponding to the axis "location" of reference token #1 is stronger than that of reference tokens #2 and #3, and can therefore determine the difference between reference token #1 and other companies' products.

[0030] Furthermore, the information processing device 10 identifies the attributes (e.g., gender and age) of the user who input the search query based on the identification information of the user who input the search query. Then, the information processing device 10 generates a bar graph G2 showing the proportion of users by gender and age who input search queries containing character strings corresponding to each axis, and provides this to the administrator M1. This allows the administrator M1 to understand the search intentions of users of each gender and age group regarding the reference token #1.

[0031] As described above, the information processing device 10 according to the embodiment identifies related tokens that were entered as a search query together with a reference token from a search query entered by a user, classifies the identified related tokens into axes corresponding to the search intent of the reference token, and provides content indicating the strength of the search intent of each reference token corresponding to each axis based on the number of related tokens entered into each axis. This allows the information processing device 10 according to the embodiment to ascertain the strength of a predetermined search intent from the search query.

[0032] [2. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are listed below.

[0033] [2-1. Providing content showing related tokens categorized into axes] In the example of Fig. 1, the information processing device 10 may provide content (e.g., a word cloud) showing related tokens classified for each axis. For example, the information processing device 10 provides content showing related tokens whose similarity to a character string showing an axis is equal to or greater than a predetermined threshold. The information processing device 10 also provides content showing related tokens whose number of times input by users or the number of users who have input the tokens is equal to or greater than a predetermined threshold.

[0034] [2-2. Specifying tokens to narrow down and compare] In the example of FIG. 1 , the information processing device 10 may perform the above process by receiving, from the administrator M1, the designation of multiple comparison tokens for narrowing down and comparing related tokens in addition to the reference token. For example, the information processing device 10 receives a reference token #4 indicating a product category and comparison tokens #1 (e.g., the name of manufacturer #1) and #2 (e.g., the name of manufacturer #2) corresponding to manufacturers of products in the category. Then, from the search query entered by the user, the information processing device 10 identifies a related token group #1 entered as a search query together with the reference token #4 and the comparison token #1, and a related token group #2 entered as a search query together with the reference token #4 and the comparison token #2. Then, the information processing device 10 classifies the related token #1 into each axis based on the similarity between the reference token #1 and the comparison token #1 and the character string indicating the axis corresponding to the search intent. Based on the number of input related tokens classified into each axis, the information processing device 10 estimates the strength of the search intent of the reference token #1 and the comparison token #1 corresponding to each axis. The information processing device 10 also classifies the related tokens #2 into each axis based on the similarity between the character strings of the reference token #1 and the comparison token #2 that indicate the axis corresponding to the search intent, and estimates the strength of the search intent of the reference token #1 and the comparison token #2 corresponding to each axis based on the number of input related tokens classified into each axis.The information processing device 10 then provides content indicating the strength of the search intent of the reference token #1 and the comparison token #1, as well as the strength of the search intent of the reference token #1 and the comparison token #2.As a specific example, the information processing device 10 provides content showing a radar chart indicating the strength of the search intent of the reference token #1 and the comparison token #1, as well as the strength of the search intent of the reference token #1 and the comparison token #2.

[0035] By providing such content, for example, administrator M1 can understand the differences in users' search intent (in other words, their image or needs) between manufacturers #1 and #2, even among products in the same category.

[0036] [2-3. Processing based on extracted tokens] 1, the information processing device 10 may extract tokens corresponding to nouns from the related tokens and limit processing to search queries that include the extracted tokens. For example, the information processing device 10 extracts token #1 indicating a manufacturer name from the related tokens input as a search query together with reference token #4, and identifies the related tokens input as a search query together with reference token #4 and token #1 from the search query input by the user. The information processing device 10 then provides content indicating the strength of search intent of reference token #4 and the strength of search intent of reference token #4 and token #1.

[0037] By providing such content, for example, the administrator M1 can understand what manufacturers are being searched for and what search intents are being shown in the category of products that the administrator M1 is trying to sell.

[0038] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 10 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. As shown in Fig. 3, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0039] (Regarding the communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC), etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100, the destination terminal 200, etc.

[0040] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3 , the storage unit 30 has a search history database 31.

[0041] (About Search History Database 31) The search history database 31 stores various information related to the search history of users in search services. An example of information stored in the search history database 31 will now be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the search history database 31 according to the embodiment. In the example of FIG. 4, the search history database 31 has items such as "user ID," "attribute information," and "search history."

[0042] "User ID" indicates identification information for identifying a user. "Attribute information" indicates the user's attributes. "Search history" indicates the user's search history in the search service, and includes items such as "search query" and "input date and time." "Search query" indicates the search query entered by the user. "Input date and time" indicates the date and time when the user entered the search query.

[0043] That is, FIG. 4 shows an example in which the attribute information of a user identified by user ID "UID#1" is "attribute information #1" and the search query input at input date and time "date and time #1" is "search query #1."

[0044] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 40 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 3 , the control unit 40 according to the embodiment has an identification unit 41, a classification unit 42, an estimation unit 43, and a provision unit 44, and realizes or executes the functions and actions of information processing described below.

[0045] (Regarding the specific unit 41) The identification unit 41 identifies related tokens that have been input as search queries together with the reference token. For example, in the example of Fig. 1, the identification unit 41 refers to the search history database 31 and identifies related tokens that have been input as search queries together with the reference token #1 from among the search queries input by the user.

[0046] The identification unit 41 may also identify a related token input as a search query together with a reference token designated by a predetermined recipient. For example, in the example of Fig. 1, the identification unit 41 identifies a related token input as a search query together with a reference token #1 designated by an administrator M1 who is a recipient of the content.

[0047] The identification unit 41 may further identify the attributes of the user who input the search query. For example, in the example of Fig. 1, the identification unit 41 identifies the attributes of the user who input the search query based on the identification information of the user who input the search query.

[0048] The identification unit 41 may also accept the designation of multiple comparison tokens and identify related tokens that have been input as a search query together with a reference token and the comparison tokens for each combination of the reference token and the comparison tokens. For example, in the example of Fig. 1, the identification unit 41 accepts a reference token #4 that indicates a product category and comparison tokens #1 and #2 that correspond to manufacturers that produce products in that category, and identifies, from the search query input by the user, a related token group #1 that has been input as a search query together with the reference token #4 and the comparison token #1, and a related token group #2 that has been input as a search query together with the reference token #4 and the comparison token #2.

[0049] Furthermore, the identification unit 41 may identify related tokens input as a search query together with a reference token and extracted tokens extracted based on predetermined conditions from a search query including the reference token. For example, in the example of Fig. 1, the identification unit 41 extracts token #1 indicating a manufacturer name from the related tokens input as a search query together with reference token #4, and identifies the related tokens input as a search query together with reference token #4 and token #1 from the search query input by the user.

[0050] (Regarding classification unit 42) The classification unit 42 classifies each of the related tokens identified by the identification unit 41 into each of the axes based on the similarity between the related tokens identified by the identification unit 41 and character strings indicating a predetermined axis corresponding to the search intent of the reference token. For example, in the example of Fig. 1, the classification unit 42 calculates the similarity between the related tokens and character strings indicating each axis corresponding to the search intent, such as "review," "service," "price," "compensation," "discount," "location," "track record," and "performance," and classifies the related token into an axis corresponding to a character string whose similarity with the related token is equal to or greater than a predetermined threshold.

[0051] Furthermore, the classification unit 42 may classify each of the related tokens into each axis based on the similarity between the related token and a character string indicating the axis specified by a predetermined destination. For example, in the example of Fig. 1, the classification unit 42 classifies each of the related tokens into each axis based on the similarity between the related token and a character string indicating the axis specified by the administrator M1.

[0052] The classification unit 42 may also classify each of the related tokens into each axis based on the similarity between the related token and a similar string that is similar to the string indicating the axis. For example, in the example of FIG. 1, the classification unit 42 extracts a predetermined number of strings from a predetermined group of strings in descending order of similarity to "review." Then, the classification unit 42 calculates the similarity between the related token and each of the extracted strings, and if the similarity with any of the extracted strings is equal to or greater than a predetermined threshold, classifies the related token into the axis "review."

[0053] The classification unit 42 may also classify each related token into an axis based on the similarity between the related token identified for each combination and the character strings indicating the axis corresponding to the search intent of the reference token and the comparison token. For example, in the example of FIG. 1 , the classification unit 42 classifies related token #1 into each axis based on the similarity between reference token #1 and the character strings indicating the axis corresponding to the search intent of the comparison token #1. The classification unit 42 also classifies related token #2 into each axis based on the similarity between reference token #1 and the character strings indicating the axis corresponding to the search intent of the comparison token #2.

[0054] Furthermore, the classification unit 42 may classify each of the related tokens into each axis based on the similarity between the related token and the character string indicating the axis corresponding to the search intent of the reference token and the extracted token. For example, in the example of Fig. 1, the classification unit 42 classifies the related tokens input as a search query together with reference token #4 and token #1 into each axis based on the similarity between the related token and the character string indicating the axis corresponding to the search intent of reference token #4 and token #1.

[0055] (Regarding the estimation unit 43) The estimation unit 43 estimates the strength of search intention corresponding to an axis based on the number of inputs of related tokens classified into each axis by the classification unit 42. For example, in the example of Fig. 1, the estimation unit 43 estimates a score based on the number of times related tokens classified into each axis were input by users, a score based on the number of users (number of unique users) who input related tokens classified into each axis, and a score based on the lift value of basket analysis.

[0056] The estimation unit 43 may also estimate the strength of search intent corresponding to each axis for each combination based on the number of input related tokens classified on each axis. For example, in the example of FIG. 1, the estimation unit 43 estimates the strength of search intent for each reference token #1 and comparison token #1 corresponding to each axis based on the number of input related tokens classified on each axis. The estimation unit 43 also estimates the strength of search intent for each reference token #1 and comparison token #2 corresponding to each axis based on the number of input related tokens classified on each axis.

[0057] (About the provider 44) The providing unit 44 provides content indicating the strength of search intention estimated by the estimation unit 43. For example, in the example of Fig. 1, the providing unit 44 provides content indicating the strength of search intention corresponding to each axis.

[0058] The providing unit 44 may also provide content to the providing destination. For example, in the example of Fig. 1, the providing unit 44 provides content indicating the strength of search intention corresponding to each axis to the administrator M1.

[0059] The providing unit 44 may also provide content including a radar chart showing the strength of search intent corresponding to each axis. For example, in the example of Fig. 1, the providing unit 44 provides content showing a radar chart L1 showing the score of search intent corresponding to each axis.

[0060] The providing unit 44 may also provide content that indicates the lift values ​​of the related tokens classified into axes as the strength of the search intent corresponding to the axes. For example, in the example of Fig. 1, the providing unit 44 provides content that indicates a score based on the lift values ​​of the related tokens classified into each axis.

[0061] The providing unit 44 may also provide content indicating related tokens classified into axes. For example, in the example of Fig. 1, the providing unit 44 provides content indicating related tokens whose similarity to the character string indicating the axis is equal to or greater than a predetermined threshold. The providing unit 44 also provides content indicating related tokens whose number of times input by users or the number of users who have input the tokens is equal to or greater than a predetermined threshold.

[0062] The providing unit 44 may also provide content showing attributes of users who input search queries containing related tokens categorized on the axes. For example, in the example of Fig. 1, the providing unit 44 provides content showing a bar graph G2 showing the proportion of users by gender and age group who input search queries containing character strings corresponding to each axis.

[0063] The providing unit 44 may also provide content indicating the strength of search intent estimated for each combination. For example, in the example of Fig. 1, the providing unit 44 provides content showing a radar chart indicating the strength of search intent for each of the reference token #1 and the comparison token #1, and the strength of search intent for each of the reference token #1 and the comparison token #2.

[0064] The providing unit 44 may also provide content indicating the strength of search intent for the reference token and the extracted token. For example, in the example of Fig. 1, the providing unit 44 provides content showing a radar chart indicating the strength of search intent for reference token #4 and the strength of search intent for reference token #4 and token #1.

[0065] [4. Information processing flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0066] 5, the information processing device 10 determines whether or not a reference token has been designated (step S101). If a reference token has not been designated (step S101; No), the information processing device 10 waits until a reference token is designated.

[0067] On the other hand, if a reference token is specified (step S101; Yes), the information processing device 10 identifies related tokens that were input as a search query together with the reference token (step S102). Next, the information processing device 10 classifies each of the identified related tokens into each of the axes based on the similarity between the identified related tokens and a character string indicating a predetermined axis corresponding to the search intent of the reference token (step S103). Next, the information processing device 10 estimates the strength of the search intent corresponding to the axis based on the number of input related tokens classified into each axis (step S104). Note that the number of input related tokens is not limited to the number of searches for the related token, and may also be the search rate of the related token, the ratio of users who input the related token, or the like.

[0068] Next, the information processing device 10 provides content indicating the strength of the search intention (step S105), and ends the process.

[0069] [5. Modifications] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0070] [5-1. Axis according to field] In the above-described embodiment, the axis corresponding to the search intent of the reference token may be set arbitrarily depending on the field to which the reference token belongs. For example, if the reference token belongs to the medical field (for example, if the reference token is a disease such as "cold"), the axes may be set to "hospital," "medicine," "symptoms," etc., and by estimating the strength of search intent corresponding to each axis, it is possible to provide content indicating the names of hospitals and medicines that are important to the user when they contract the disease indicated by the reference token, and the symptoms that they are concerned about (or are currently experiencing).

[0071] Furthermore, when the reference token indicates the name of a specific service, by setting the axes as "like," "dislike," "easy to use," "difficult to use," etc., and estimating the strength of search intent corresponding to each axis, it is possible to provide content that indicates the user's evaluation of the impression of the service indicated by the reference token, or information such as the results of a survey (for example, specific points that are difficult to use).

[0072] Furthermore, if the reference token belongs to the food category (for example, if the reference token is a food such as "pasta"), by setting the axes as "meat," "vegetables," "fish," etc. and estimating the strength of search intent corresponding to each axis, it is possible to provide content that indicates what ingredients the user considers important to combine with the food indicated by the reference token, food combinations, menu names, etc.

[0073] [5-2. Content for each user attribute] In the above-described embodiment, the information processing device 10 may provide content indicating the strength of search intent of a reference token for each user attribute (segment). For example, the information processing device 10 receives, from a content provider, a designation of a reference token and a designation of attribute #1 (e.g., working woman) and attribute #2 (e.g., housewife) of a target user. The information processing device 10 then identifies related tokens #11 that were input as search queries together with the reference token from among search queries input by users having attribute #1. The information processing device 10 also identifies related tokens #12 that were input as search queries together with the reference token from among search queries input by users having attribute #2. The information processing device 10 then classifies the related tokens #11 into each axis based on the similarity between the character strings indicating the axes corresponding to the search intent of the reference token, and estimates the strength of search intent of each reference token of a user having attribute #1 based on the number of input related tokens classified into each axis. The information processing device 10 also classifies related tokens #12 into each axis based on the similarity between the reference token and the character string indicating the axis corresponding to the search intent, and estimates the strength of search intent of each reference token of a user having attribute #2 based on the number of input related tokens classified into each axis.The information processing device 10 then provides content indicating the strength of search intent of a reference token of a user having attribute #1 and the strength of search intent of a reference token of a user having attribute #2.As a specific example, the information processing device 10 provides content showing a radar chart indicating the strength of search intent of a reference token of a user having attribute #1 and the strength of search intent of a reference token of a user having attribute #2.

[0074] [5-3. Processing mode] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above text and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0075] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0076] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0077] [6. Effects] As described above, the information processing device 10 according to the embodiment includes the identification unit 41, the classification unit 42, the estimation unit 43, and the provision unit 44. The identification unit 41 identifies related tokens input together with a reference token as a search query. The classification unit 42 classifies each of the related tokens into a predetermined axis corresponding to the search intent of the reference token based on the similarity between the related tokens identified by the identification unit 41 and a character string indicating the axis. The estimation unit 43 estimates the strength of search intent corresponding to the axis based on the number of input related tokens classified into each axis by the classification unit 42. The provision unit 44 provides content indicating the strength of search intent estimated by the estimation unit 43.

[0078] This makes it possible to provide content indicating the strength of search intent for each reference token, thereby making it possible to grasp the strength of a specific search intent from a search query.

[0079] In the information processing device 10 according to the embodiment, for example, the identification unit 41 identifies related tokens input as a search query together with a reference token specified by a predetermined destination. Then, the providing unit 44 provides content to the destination. Furthermore, the classification unit 42 classifies each of the related tokens into each axis based on the similarity between the related tokens and character strings indicating the axes specified by the predetermined destination. Then, the providing unit 44 provides the content to the destination.

[0080] As a result, the information processing device 10 according to the embodiment can improve convenience because the content provider can specify the reference token or axis.

[0081] Furthermore, in the information processing device 10 according to the embodiment, for example, the classification unit 42 classifies each of the related tokens into each of the axes based on the similarity between the related token and a similar string that is similar to a string indicating the axis.

[0082] As a result, the information processing device 10 according to the embodiment can classify related tokens into each axis based on similar strings that are similar to the strings indicating the axis, and therefore can provide appropriate content.

[0083] In addition, in the information processing device 10 according to the embodiment, for example, the providing unit 44 provides content including a radar chart indicating the strength of search intent corresponding to an axis. The providing unit 44 also provides content indicating the lift values ​​of related tokens classified on the axis as the strength of search intent corresponding to the axis. The providing unit 44 also provides content indicating the related tokens classified on the axis.

[0084] As a result, the information processing device 10 according to the embodiment can provide content indicating the strength of search intent of a reference token in various formats, thereby improving convenience.

[0085] Furthermore, in the information processing device 10 according to the embodiment, for example, the identification unit 41 further identifies the attributes of the user who input the search query. Then, the provision unit 44 provides content indicating the attributes of the user who input the search query including the related tokens classified into the axes.

[0086] As a result, the information processing device 10 according to the embodiment can provide content indicating the attributes of a user who inputs a search query including a related token, thereby improving convenience.

[0087] Furthermore, in the information processing device 10 according to the embodiment, for example, the identification unit 41 accepts the designation of multiple comparison tokens and identifies related tokens input as a search query together with a reference token and the comparison token for each combination of the reference token and the comparison token. The classification unit 42 then classifies each related token into each axis based on the similarity between the related tokens identified for each combination and strings indicating the axis corresponding to the search intent of the reference token and the comparison token. The estimation unit 43 then estimates the strength of search intent corresponding to each axis for each combination based on the number of input related tokens classified into each axis. The provision unit 44 then provides content indicating the strength of search intent estimated for each combination.

[0088] As a result, the information processing device 10 according to the embodiment can compare the strength of search intention between comparison tokens, thereby improving convenience.

[0089] The identification unit 41 also identifies related tokens input as a search query together with a reference token and extracted tokens extracted based on predetermined conditions from a search query containing the reference token. The classification unit 42 then classifies each of the related tokens into each axis based on the similarity between the related tokens and character strings indicating the axes corresponding to the search intent of the reference token and extracted token. The provision unit 44 then provides content indicating the strength of the search intent of the reference token and extracted token.

[0090] As a result, the information processing device 10 according to the embodiment can grasp the search intent of the manufacturer or the like indicated by the extracted token, which is a noun or the like, and can therefore improve convenience.

[0091] [7. Hardware Configuration] The information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 6. The information processing device 10 will be described below as an example. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0092] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0093] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0094] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0095] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0096] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1300 to realize the functions of the control unit 40. The HDD 1400 also stores various data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0097] [8. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0098] Furthermore, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing, depending on the function.

[0099] Furthermore, the term "unit" in the claims can be read as "means" or "circuit," etc. For example, a reception unit can be read as a reception means or a reception circuit. [Explanation of symbols]

[0100] 10. Information processing equipment 20 Communications Department 30 Storage section 31 Search History Database 40 Control Unit 41 Specific part 42 Classification Department 43 Estimation part 44 Providing Department 100 user terminals 200 Destination terminal

Claims

1. An identification unit that identifies, from among character strings indicated by a search query that include a reference token that is a predetermined character string, character strings that are different from the reference token as related tokens; a classification unit that classifies each of the related tokens identified by the identification unit into a predetermined axis corresponding to the search intent of the reference token based on the similarity between the related tokens identified by the identification unit and a character string indicating the predetermined axis; an estimation unit that estimates the strength of search intention corresponding to each axis based on the number of inputs of the related tokens classified into each axis by the classification unit; a providing unit that provides content indicating the strength of the search intent estimated by the estimation unit; and The identification unit extracting character strings belonging to a predetermined category from character strings indicated by a search query including the reference token as extracted tokens for limiting the search query, and identifying the related tokens that are different from the reference token and the extracted tokens from character strings indicated by the search query including the reference token and the extracted tokens; The classification unit classifying each of the related tokens into each of the axes based on the similarity between the related tokens and character strings indicating the axes corresponding to the search intent of the reference token and the extracted token; The providing unit Providing content indicating the strength of search intent of the reference token and the extracted token 1. An information processing device comprising:

2. The identification unit Identifying related tokens input as a search query together with the reference token designated by a predetermined provider; The providing unit Provide the content to the recipient 2. The information processing apparatus according to claim 1, wherein:

3. The classification unit classifying each of the related tokens into each of the axes based on a similarity between the related tokens and a character string indicating the axis designated by a predetermined provider; The providing unit Provide the content to the recipient 2. The information processing apparatus according to claim 1, wherein:

4. The classification unit Each of the related tokens is classified into each of the axes based on the similarity between the related token and a similar string similar to the string indicating the axis.

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

5. The providing unit Provide content that includes a radar chart showing the strength of search intent corresponding to the axis.

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

6. The providing unit To provide content that indicates the lift value of the related tokens classified on the axis as the strength of search intent corresponding to the axis.

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

7. The providing unit providing content showing the related tokens categorized on the axis; 2. The information processing apparatus according to claim 1, wherein:

8. The identification unit Further identify the attributes of the user who entered the search query, The providing unit providing the content indicating the attributes of a user who inputs a search query including the related tokens classified on the axis; 2. The information processing apparatus according to claim 1, wherein:

9. The identification unit A method for identifying, for each combination of a reference token and a comparison token, a plurality of comparison tokens that are different from the reference token and are used to narrow down the related tokens and compare the strength of search intent corresponding to the axis, and a search query including the reference token and the comparison token, and the method for identifying, for each combination of the reference token and the comparison token, a plurality of comparison tokens that are different from the reference token and the comparison token, and a search query including ... The classification unit classifying each of the related tokens into each of the axes based on the similarity between the related tokens identified for each of the combinations and character strings indicating the axes corresponding to the search intents of the reference token and the comparison token; The estimation unit Estimating the strength of search intent corresponding to each axis for each combination based on the number of inputs of the related tokens classified into each axis; The providing unit Providing content that indicates the strength of search intent estimated for each of the combinations 2. The information processing apparatus according to claim 1, wherein:

10. 1. A computer-implemented information processing method, comprising: an identifying step of identifying related tokens input together with the reference token as a search query; a classification step of classifying each of the related tokens identified in the identification step into each of the predetermined axes based on the similarity between the related tokens identified in the identification step and a character string indicating the predetermined axis corresponding to the search intent of the reference token; an estimation step of estimating the strength of search intention corresponding to each axis based on the number of inputs of the related tokens classified into each axis by the classification step; a providing step of providing content indicating the strength of the search intent estimated by the estimating step; Including, The identifying step includes: extracting character strings belonging to a predetermined category from character strings indicated by a search query including the reference token as extracted tokens for limiting the search query, and identifying the related tokens that are different from the reference token and the extracted tokens from character strings indicated by a search query including the reference token and the extracted tokens; The classification step includes: classifying each of the related tokens into each of the axes based on the similarity between the related tokens and character strings indicating the axes corresponding to the search intent of the reference token and the extracted token; The providing step includes: Providing content indicating the strength of search intent of the reference token and the extracted token An information processing method comprising:

11. an identification step of identifying related tokens input as a search query together with a reference token; a classification step of classifying each of the related tokens identified by the identification step into a predetermined axis corresponding to the search intent of the reference token based on the similarity between the related tokens identified by the identification step and a character string indicating the predetermined axis; an estimation step of estimating the strength of search intention corresponding to each axis based on the number of inputs of the related tokens classified into each axis by the classification step; a providing step of providing content indicating the strength of the search intent estimated by the estimating step; on the computer, The identification procedure includes: extracting character strings belonging to a predetermined category from character strings indicated by a search query including the reference token as extracted tokens for limiting the search query, and identifying the related tokens that are different from the reference token and the extracted tokens from character strings indicated by a search query including the reference token and the extracted tokens; The classification procedure comprises: classifying each of the related tokens into each of the axes based on the similarity between the related tokens and character strings indicating the axes corresponding to the search intent of the reference token and the extracted token; The providing step comprises: Providing content indicating the strength of search intent of the reference token and the extracted token An information processing program characterized by:

Images