JP2019149200A - Provision device, provision method, and provision program - Google Patents

Abstract

To provide a user with useful information.SOLUTION: A provision device comprises: an identification unit to identify other transaction objects similar in a user's impression to a transaction object specified by a business operator; and a provision unit to provide the business operator with information on the specified transaction object on the basis of information on the other transaction objects identified by the identification unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a providing device, a providing method, and a providing program.

  In recent years, with the rapid spread of the Internet, for example, a technology for selling goods or services on an EC (Electronic Commerce) site is provided. For example, a technique is known in which customers are analyzed in consideration of time trends and information corresponding to the analysis results is provided.

JP2015-146145A

  However, the above-described conventional technology cannot always provide useful information to the user.

  For example, in the above-described conventional technology, only an analysis in consideration of a trend based on designation of a period is performed, and thus information on a trend that is not useful to the user may be provided.

  The present application has been made in view of the above, and an object thereof is to provide useful information to a user.

  The providing apparatus according to the present application is based on a specification unit that specifies another transaction target similar to the transaction target specified by the business operator and an information related to the other transaction target specified by the specifying unit. And a providing unit for providing information relating to the designated transaction object to the business operator.

  According to one aspect of the embodiment, useful information can be provided to the user.

FIG. 1 is a diagram illustrating an example of an information providing apparatus according to the embodiment. FIG. 2 is a diagram illustrating an example of a functional configuration of the information providing apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of information registered in the distributed representation space database according to the embodiment. FIG. 4 is a flowchart illustrating an example of a flow of providing processing executed by the information providing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of a hardware configuration.

  Hereinafter, modes for implementing a providing device, a providing method, and a providing program according to the present application (hereinafter referred to as “embodiments”) will be described in detail with reference to the drawings. In addition, the providing apparatus, the providing method, and the providing program according to the present application are not limited by this embodiment. In the following embodiments, the same parts are denoted by the same reference numerals, and redundant description is omitted.

Embodiment
[1. Overview of information providing device)
Hereinafter, an example of the information providing apparatus 10 as an example of the providing apparatus will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an information providing apparatus according to the embodiment. In the example illustrated in FIG. 1, an example of providing processing that provides, as auxiliary information, another context having a relationship with a context when the information providing apparatus 10 accepts a context has been described.

  Here, the context is any content indicating a predetermined target. For example, a predetermined target is any product, service, company, store, brand, facility, etc., as long as the information is transmitted to any user by distribution information such as advertisements and news. Can be adopted. The predetermined target may be, for example, a person such as an actor, various contents such as animals, movies and music. The context may be any type of content related to the target, such as text, image, audio, or other content that reminds the user of various targets.

  The information providing apparatus 10 is an information processing apparatus that can communicate with the operator terminal 100 and the external server 200 via a predetermined network N (for example, see FIG. 2) such as the Internet. Realized by a system or the like. It is assumed that the information providing apparatus 10 can communicate with an arbitrary number of business entity terminals 100 and an arbitrary number of external servers 200.

  The provider terminal 100 is a terminal device used by an arbitrary provider, and is realized by a PC (Personal Computer), a smart device, a mobile communication terminal, or the like. For example, the business entity terminal 100 transmits the context input by the business operator to the information providing apparatus 10. In such a case, the information providing apparatus 10 acquires another context having relevance with the received content as auxiliary information, and transmits the acquired auxiliary information to the business entity terminal 100. As a result, the operator terminal 100 can provide the operator with auxiliary information of the context input by the operator.

  The external server 200 is an information processing apparatus that provides an arbitrary web service to a user, and is realized by, for example, a server apparatus or a cloud system. For example, the external server 200 is a server device that provides various SNSs (Social Networking Services) that provide information posted by a user to other users. When the external server 200 accepts postings of various contents such as blogs, microblogs, web pages, messages, still images, moving images, audio, etc., the external server 200 publishes the accepted contents, thereby publishing various information regarding the contents to the public. In general, it may be a server device that spreads.

  In addition, the external server 200 may be a server device that provides information about various dictionaries, news, and the like to the user. The external server 200 also provides arbitrary web services such as a portal site, Internet auction, online shopping mall, web search, route search, map search, game, real estate information provision, financial information provision, accommodation facility reservation service, etc. The server apparatus to provide may be sufficient. In addition, the external server 200 may be a server device that accepts a user's evaluation on an arbitrary target and provides a service that provides an evaluation result. Further, the external server 200 may be a server device that collects a log indicating an action history in the real world or on a network such as a user's location information and purchase history. Such an external server 200 manages various contents posted by an arbitrary user, an action history of an arbitrary user, a search history of an arbitrary user, information on a target of electronic commerce, and the like.

[1-1. About provision processing)
Here, a method of performing promotion and merchandising based on information highly relevant to the transaction target can be considered. For example, explain the attributes of users who are presumed to like the transaction target, the region with high affinity with the transaction target, other transaction targets with high affinity with the transaction target, actors with high affinity with the transaction target, and the transaction target. When using effective wording (for example, effective copywriting), the location of the store supplying the transaction target, the attributes of the user as the advertising destination, various advertising contents indicating the transaction target, and sales with the transaction target A method of determining other transaction targets to be considered can be considered.

  However, simply performing an analysis that considers trends may provide information on trends that are not useful to businesses. For example, when posting information including a context indicating a new transaction target is frequently posted on the SNS, it can be specified that the transaction target is a trend, but the transaction target is highly compatible with others It is not always possible to provide supplementary information indicating the context of the.

  Therefore, the information providing apparatus 10 executes the following providing process. First, the information providing apparatus 10 specifies another target whose impression the user has is similar to the target specified by the business operator. And the information provision apparatus 10 provides a provider with the information regarding a designated drawing object based on the information regarding the other identified object. For example, the information providing apparatus 10 specifies another target having co-occurrence with the specified target in the input information input by the user as another target similar to the target with the specified user impression. .

  For example, another context input as a search query together with the context of a certain target is considered to suggest a user's impression of the target. For this reason, when the contexts of different targets are input with a context that suggests the user's impression and a common context, the user has a common impression for these targets. Presumed to have. Therefore, the information providing apparatus 10 specifies a target having a common impression from the contents of the search query, and sets the specified target as a target having co-occurrence. That is, the information providing apparatus 10 identifies another target having co-occurrence with a target specified in the search query input by the user (hereinafter, may be referred to as “specified target”).

  Similarly, it is considered that other contexts that are input together with the context of a certain target with respect to the same posting information or continuous posting information suggest an impression of the user with respect to the target. For this reason, if the context is different and the context suggests the user's impression and the common context is given in the post information, the user is common to these targets. It is presumed to have an impression of Therefore, the information providing apparatus 10 specifies a target having a common impression from the contents of the posted information, and sets the specified target as a target having co-occurrence. That is, the information providing apparatus 10 specifies another target having co-occurrence with the specified target in the posted information posted by the user.

  Here, it is presumed that the information related to the other target having the co-occurrence with the specified target (hereinafter sometimes referred to as “co-occurrence target”) is useful information for co-occurrence target promotion and merchandising. Is done. On the other hand, considering that the designated object and the co-occurrence object have a common impression, there is a high possibility that the information is related to the co-occurrence object and useful for promotion and merchandising of the designated object. Therefore, the information providing apparatus 10 acquires information about the co-occurrence target, and generates auxiliary information for the specified target from the acquired information.

  For example, the information providing apparatus 10 acquires information regarding a place having a relationship with the co-occurrence target as information regarding the co-occurrence target. Moreover, the information provision apparatus 10 acquires the information regarding the person who has relevance with a co-occurrence target as information regarding a co-occurrence target. And the information provision apparatus 10 provides a provider with the information regarding the acquired place and the information regarding a person as auxiliary information.

[1-2. (Target)
Here, when the information providing apparatus 10 accepts an arbitrary target as the designated target, the information providing apparatus 10 may specify an arbitrary target having co-occurrence with the designated target as the co-occurrence target. Here, the information providing apparatus 10 may limit a target to be designated or a co-occurrence target to a transaction target that is traded in an arbitrary manner such as a product or a service. For example, the information providing apparatus 10 identifies another transaction target similar to the transaction target specified by the business operator, acquires information having co-occurrence with the other transaction target as information related to the other transaction target, and acquires the information. Based on the information, the information regarding the designated transaction object may be provided to the operator.

  In other words, the information providing apparatus 10 specifies another transaction target that is similar to the designated transaction target and the user's impression. Then, the information providing apparatus 10 may provide information such as a region or a person highly related to the other specified transaction object as information of a region or a person highly related to the designated transaction object.

[1-3. About auxiliary information)
Here, the information providing apparatus 10 may generate auxiliary information of any content as long as auxiliary information regarding a specified target is generated based on information regarding another specified target. For example, the information providing apparatus 10 may generate auxiliary information used for promotion and merchandising of other designated objects. That is, the information providing apparatus 10 may generate information related to the sales mode of the specified target as auxiliary information based on the information related to the other specified target, and provide the generated auxiliary information to the operator.

  Here, the information providing apparatus 10 may generate auxiliary information having an arbitrary content. For example, when the designation target is related to a food, another food is selected as a co-occurrence target, and another food or beverage highly related to the selected food is specified. And the information provision apparatus 10 may produce | generate the auxiliary information which shows that the specified food and drink are food and drink with high affinity with designation | designated object. Such auxiliary information can be used, for example, for menu selection in restaurants.

  In addition, for example, the information providing apparatus 10 identifies an area highly related to the co-occurrence target, and generates auxiliary information in which the identified area is highly related to the designated target. Such auxiliary information indicating the area can be used for a store opening plan related to the designated target. For example, the information providing apparatus 10 identifies and identifies a person highly related to the co-occurrence target. Auxiliary information in which a person is highly related to the designated target is generated. Such auxiliary information indicating a person can be used for selecting a person who contributes to a commercial or the like to be designated.

  That is, the information providing apparatus 10 performs persona design of the designation target by regarding the information highly relevant to the co-occurrence target as information highly relevant to the designation target. For this reason, the information provision apparatus 10 can implement | achieve the production | generation of the auxiliary information about a designation | designated object, for example, also when information with high relevance with a designation | designated object is unknown.

[1-4. About the use of distributed expressions)
Here, the information providing apparatus 10 uses a distributed expression technique to identify a co-occurrence target having a similar impression to the designated target and the user, or to identify information highly relevant to the co-occurrence target. Also good. For example, the information providing apparatus 10 specifies a context similar to the context corresponding to the specified target from the distributed representation of each context generated based on the relative relevance of each context included in the input information, A target corresponding to the specified context may be specified as another target. Further, the information providing apparatus 10 identifies another context whose distributed representation is similar to the context corresponding to the other target, and provides information on the specified target to the operator based on the information corresponding to the specified context. May be.

  For example, the information providing apparatus 10 acquires various types of information managed by the external server 200 and contexts various contents such as various texts and images such as company names, product names, service names, brand names, facility names, and personal names. And And the information provision apparatus 10 produces | generates the distributed expression of each context using the technique which converts each context into a multidimensional quantity based on the relative relevance which a context has, such as w2v (word2vec). Note that the information providing apparatus 10 may adopt any technique other than w2v as long as it is a technique that converts each context into a multidimensional quantity based on the relative relevance of each context.

  In addition, the information providing apparatus 10 acquires the designation target name, appearance, and the like as the designation target context, and converts the specified designation target context into a distributed representation. Then, the information providing apparatus 10 searches for another distributed expression similar to the distributed expression of the context to be specified on the distributed expression space generated in advance. For example, the information providing apparatus 10 is another distributed expression having a hamming distance or a cosine distance that is close to the distributed expression of the context of the specified target, and the context of the target (for example, a target that can be a transaction target) similar to the specified target. Search for a distributed representation of. Then, the information providing apparatus 10 sets the context corresponding to the searched distributed expression as the context of the co-occurrence target.

  Subsequently, the information providing apparatus 10 searches for other contexts that are similar to the context of the co-occurrence target and whose distributed representation is similar and that indicates a target that can be a source of auxiliary information, such as a context indicating a region or a context indicating a person. To do. Then, the information providing apparatus 10 sets the searched context as a related target context related to the co-occurrence target. Thereafter, the information providing apparatus 10 generates auxiliary information using the related target context.

  Note that the information providing apparatus 10 may specify the designation target, the co-occurrence target, and the related target using any technique other than the distributed expression. For example, the information providing apparatus 10 specifies a context that is frequently input together with the specified target in the input information, and specifies another context that is frequently input together with the specified context as a co-occurrence target context. And the information provision apparatus 10 is good also considering the context with high frequency input into input information with the context of the identified co-occurrence object as a context of a related object.

[1-5. (Specifying information type)
Note that the information providing apparatus 10 may adopt an arbitrary type of target as a designation target or a co-occurrence target, and may set an arbitrary type of target as a related target. For example, the information providing apparatus 10 may set a transaction target as a designation target or a co-occurrence target and a region or a person as a related target. In such a case, the information providing apparatus 10 can set the information of the area or person highly relevant to other transaction objects similar to the transaction object as auxiliary information of the specified transaction object. Further, the information providing apparatus 10 may set a person as a designation target or a co-occurrence target and a region or a transaction target as a related target. In such a case, the information providing apparatus 10 can use the region or transaction target information highly related to another person similar to the designated person as auxiliary information of the designated person.

  Further, the information providing apparatus 10 may adopt different types of targets as the designation target and the co-occurrence target. For example, the information providing apparatus 10 may set a transaction target as a specified target, a region as a co-occurrence target, and a person as a related target. In such a case, the information providing apparatus 10 identifies an area having an impression similar to the designated transaction object as a co-occurrence object, and information on a person highly related to the identified area is specified for the designated transaction object. It can be auxiliary information.

  In addition, the information provision apparatus 10 may receive designation | designated from a provider about what kind of object is made into a designation | designated object, a co-occurrence object, or a related object. In addition, the information providing apparatus 10 may automatically set a target having the same type as the input designation target as a co-occurrence target. In addition, the information providing apparatus 10 may use another type of target corresponding to the type of the specified target as a co-occurrence target or a related target.

[1-6. About selection using product categories)
Further, the information providing apparatus 10 may select a co-occurrence target based on the category to which the designated target belongs. For example, the information providing apparatus 10 may select a co-occurrence target from targets belonging to a category similar to the category to which the specified target belongs in an online shopping mall or the like. For example, when “珈 琲” is selected as the designation target, the information providing apparatus 10 selects and selects another category similar to the category “珈 琲 -related category” to which “珈 琲” belongs, for example, “tea related category”. A target whose user impression is similar to “珈 琲” may be selected as a co-occurrence target from the targets belonging to the selected category.

  In addition, for example, when the category has a hierarchical structure, the information providing apparatus 10 specifies a higher category of the category to which the specified target belongs, and is a category included in the specified higher category, to which the specified target belongs. You may specify the object with which the impression which a user has is similar from the object which belongs to categories other than a category. For example, the information providing apparatus 10 may specify a target having a similar impression that the user has from among the targets belonging to the same category as the category to which the specified target belongs.

  For example, when “珈 琲” is selected as the designation target, the information providing apparatus 10 specifies the category “珈 琲 -related category” to which “珈 琲” belongs, and the upper category “food / drink” including the specified “珈 琲 -related category”・ Specify “Liquor category”. Subsequently, the information providing apparatus 10 selects a category other than the “boil-related category” among the lower categories included in the identified “food / drink / alcohol category”. For example, the information providing apparatus 10 identifies a “sake category” that belongs to the same level as the “boil-related category” (that is, a category at a level one level lower than the “food / drink / sake category”). Then, the information providing apparatus 10 may select a target whose user impression is similar to “対 象” from among the identified targets as a co-occurrence target.

  In addition, the information providing apparatus 10 may specify a target having a similar impression that the user has from among targets belonging to a category of a hierarchy different from the category to which the designated target belongs. For example, if there is a category such as “Wine” or “Craft Beer” in the lower hierarchy of the “Liquor Category”, the information providing apparatus 10 can share information from objects belonging to the category “Wine” or “Craft Beer”. You may select a starting target. Further, the information providing apparatus 10 may select a co-occurrence target from transaction targets belonging to a category that is higher by a predetermined hierarchy than the category to which the specified target belongs.

  That is, the information providing apparatus 10 specifies a target having a similar impression as the other target from among targets having a category similar to the specified target. More specifically, the information providing apparatus 10 has, as another object, an impression that the user has among the objects belonging to the category of the same hierarchy as the category of the specified object among the categories having a hierarchical structure. Identify similar objects. For this reason, the information providing apparatus 10 can appropriately select a target similar to the specified target.

[1-7. (Example of provision processing)
Next, an example of a providing process executed by the information providing apparatus 10 will be described with reference to FIG. First, the information providing apparatus 10 collects various types of input information such as search query history, posted information, and news articles from the external server 200 (step S1). In such a case, the information providing apparatus 10 generates a distributed representation of the context included in the collected input information (Step S2).

  The information providing apparatus 10 performs transactions such as “craft beer is delicious”, “delicious rice cake”, “珈 琲 _Kiyosumi Shirakawa”, “actor #A likes rice cake”, “Yakiniku party!”, Etc. as input information. Information including a context indicating an object, a place name, a person, and the like is acquired. In such a case, the information providing apparatus 10 uses a technique such as morphological analysis to create a context such as “craft beer”, “delicious”, “mochi”, “Kiyosumi Shirakawa”, “actor #A”, “barbecue”, etc. To extract. Then, the information providing apparatus 10 uses w2v to convert each context into a distributed expression so as to reflect the relative relevance of the impression that the user has.

  For example, the information providing apparatus 10 generates a distributed expression so that the distributed expression of “珈 琲” and “craft beer” input by the user with the same “delicious” context is similar to the distributed expression of “delicious”. Do. Further, the information providing apparatus 10 generates a distributed expression so that the distributed expressions of “珈 琲” and “Kiyosumi Shirakawa” are similar, and the distributed expressions of “珈 琲” and “Actor #A” are similar.

  Subsequently, the information providing apparatus 10 accepts designation of “craft beer” as a designation target (step S3). In such a case, the information providing apparatus 10 identifies, from the distributed expression space, a transaction object having a similar distributed expression to the specified transaction object as a co-occurrence object having co-occurrence with the specified transaction object (step) S4). For example, the information providing apparatus 10 specifies a distributed expression corresponding to the context of the designated object “craft beer” from the distributed expression space, and is a distributed expression similar to the specified distributed expression, and corresponds to the transaction target context. The expression is specified as a distributed expression corresponding to the context of the co-occurrence target. For example, the information providing apparatus 10 specifies a distributed expression corresponding to the context “珈 琲”. As a result, the information providing apparatus 10 sets “珈 琲” as a co-occurrence target.

  Subsequently, the information providing apparatus 10 specifies a target other than the target indicating the transaction target, which is information similar to the co-occurrence target in the distributed representation (step S5). For example, the information providing apparatus 10 specifies “delicious”, “Kiyosumi Shirakawa”, and “actor #A” as contexts in which the distributed expression is similar to the co-occurrence target “珈 琲”. Subsequently, the information providing apparatus 10 specifies the context indicating information other than the information indicating the transaction target and the impression of the user, “Kiyosumi Shirakawa”, and “Actor #A” among the specified contexts.

  And the information provision apparatus 10 provides the auxiliary information based on the specified related object (step S6). For example, the information providing apparatus 10 generates auxiliary information indicating that targets such as “Kiyosumi Shirakawa” and “Actor #A” have high affinity with “craft beer”, and supplies the generated auxiliary information to the operator terminal 100. provide. As a result, the information providing apparatus 10 can provide useful information to the user.

[2. Configuration of information providing device]
Subsequently, an example of a functional configuration of the information providing apparatus 10 will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of a functional configuration of the information providing apparatus according to the embodiment. As illustrated in FIG. 2, the information providing apparatus 10 includes a communication unit, a storage unit 30, and a control unit 40.

  The communication unit 20 is realized by, for example, a NIC (Network Interface Card). The communication unit 20 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the business operator terminal 100 and the external server 200.

  The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. In addition, the storage unit 30 stores a distributed representation space database 31.

  In the distributed representation space database 31, information related to the distributed representation is registered. For example, FIG. 3 is a diagram illustrating an example of information registered in the distributed representation space database according to the embodiment. As illustrated in FIG. 3, information such as “context ID”, “context”, “type”, and “distributed representation” is registered in the distributed representation space database 31. In addition to the information shown in FIG. 3, arbitrary information related to the distributed representation space may be registered in the distributed representation space database 31.

  Here, the “context ID” is an identifier for identifying a context that is a source of distributed representation. A “context” is a context that is a source of distributed representation, and is, for example, a character string that indicates various objects. The “type” is information indicating the type of the target indicated by the context. For example, it indicates whether the target is a transaction target, a person, a place name, or a user impression. Information. The “distributed expression” is a distributed expression indicating a context. In the example shown in FIG. 3, a conceptual value such as “dispersion expression # 1” is described, but in reality, “distribution expression” is a multidimensional quantity such as a vector having an arbitrary number of dimensions. .

  For example, in the example illustrated in FIG. 3, information such as the context ID “ID # 1”, the context “珈 琲”, the type “transaction object”, and the distributed expression “distributed expression # 1” is registered in the distributed expression space database 31. The Such information indicates that the context indicated by the context ID “ID # 1” is the context “珈 琲” and the context indicates the type “transaction target”. Further, such information indicates that the distributed representation of the context “で” is the distributed representation “distributed representation # 1”.

  Returning to FIG. 2, the description will be continued. The control unit 40 is a controller. For example, various programs stored in a storage device inside the information providing apparatus 10 are stored in a RAM or the like by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Is implemented as a work area. The control unit 40 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated in FIG. 2, the control unit 40 includes a collection unit 41, a generation unit 42, a specification unit 43, and a provision unit 44. The collection unit 41 collects input information. For example, the collection unit 41 is input by the user from the external server 200, such as a search query history, post information such as SNS, distributed news, explanation of a transaction target in an online shopping mall, evaluation contents at various evaluation sites, and the like. Collected input information.

  The generation unit 42 generates a distributed expression space of the context included in the input information. For example, the generation unit 42 performs morphological analysis of the input information collected by the collection unit 41 and extracts a context indicating each target. Further, the generation unit 42 specifies the type of the object such as whether the object indicated by each context is a transaction object, a person, or a region, using morphological analysis, an appearance position, a dictionary, and the like. Then, the generation unit 42 generates a distributed representation of the context using a technique such as w2v, and registers the context, the type, and the distributed representation in the distributed representation space database 31 in association with each other.

  The specifying unit 43 specifies another target whose impression the user has is similar to the target specified by the business operator. For example, the specifying unit 43 specifies another target having co-occurrence with the target specified in the input information input by the user as another target whose user impression is similar to the specified target. For example, the specifying unit 43 may specify another target that has co-occurrence with the target specified in the search query input by the user, and co-occurs with the target specified in the posted information posted by the user. Other subjects having sex may be specified. The specifying unit 43 may specify another transaction target similar to the transaction target specified by the business operator. Further, the specifying unit 43 specifies and identifies a context similar to the context corresponding to the specified target from the distributed representation of each context generated based on the relative relevance of each context included in the input information. You may specify the object corresponding to the performed context as another object.

  For example, the specifying unit 43 receives the context to be specified from the provider terminal. In such a case, the specifying unit 43 refers to the distributed representation space database 31 and specifies the distributed representation of the context to be specified and the type of the specification target. Subsequently, the specifying unit 43 searches for another distributed expression similar to the specified distributed expression, in which the associated type is the same as the type to be specified. Then, the specifying unit 43 sets the searched distributed expression as a co-occurrence target distributed expression. That is, the specifying unit 43 specifies a co-occurrence target that is the same type as the specified target.

  Subsequently, the specifying unit 43 searches for another distributed expression similar to the co-occurrence target distributed expression, and whose associated type is other than “transaction target”. For example, the specifying unit 43 specifies a distributed expression similar to the co-occurrence target distributed expression as the related target distributed expression among the target distributed expressions of the type “person” or “place name”. Then, the specifying unit 43 provides the providing unit 44 with the context and type associated with the specified distributed representation as the context and type of the related target.

  The providing unit 44 provides information related to the specified target to the operator based on the information related to the other specified target. For example, the providing unit 44 acquires information having co-occurrence with other transaction objects as information regarding the other transaction objects, and provides information on the specified transaction object to the operator based on the acquired information. It becomes. For example, the providing unit 44 identifies other contexts whose distributed representations are similar to the contexts corresponding to the other objects, and provides information related to the specified objects to the operator based on the information corresponding to the identified contexts. It will be. In addition, the providing unit 44 acquires information about a place, information about a person, and the like as information about other objects. Further, the providing unit 44 may generate information related to the sales mode of the specified target based on information related to other targets, and provide the generated information to the business operator.

  For example, the providing unit 44 acquires the context and type of the related target. In such a case, the providing unit 44 estimates the utilization mode of the related target with respect to the sales mode of the designated target based on the type of the related target, and generates auxiliary information from the context of the related target based on the estimation result. For example, when the type of the related target is “person”, the providing unit 44 may generate auxiliary information with a content such as “it is estimated that the affinity of this person is high” together with the context of the related target. In addition, for example, when the type of the related target is “place name”, the providing unit 44 generates auxiliary information with a content such as “it is estimated that the affinity of this region is high” together with the context of the related target. Also good.

  Then, the providing unit 44 distributes the generated auxiliary information to the business operator terminal 100. As a result, the information providing apparatus 10 can provide useful information to users such as business operators.

[3. Example of flow of processing executed by information providing apparatus]
Next, an example of the flow of processing executed by the information providing apparatus 10 will be described with reference to FIG. FIG. 4 is a flowchart illustrating an example of a flow of providing processing executed by the information providing apparatus according to the embodiment. First, the information providing apparatus 10 receives a transaction target designation from a business operator (step S101). In such a case, the information providing apparatus 10 specifies another transaction target having a similar distributed expression as the specified transaction target as a co-occurrence target (step S102). Then, the information providing apparatus 10 specifies related objects other than transaction objects such as regions and persons whose distributed expressions are similar to the co-occurrence objects (step S103). Then, the information providing apparatus 10 provides supplementary information based on the identified related object to the business operator (step S104), and ends the process.

[4. (Modification)
In the above, an example of the control process by the information providing apparatus 10 has been described. However, the embodiment is not limited to this. Hereinafter, variations of the control process will be described.

[4-1. About auxiliary information)
In the example described above, the information providing apparatus 10 generates auxiliary information based on a place name or a related object of a person. Here, the information providing apparatus 10 may generate auxiliary information that considers a plurality of related objects in an integrated manner. For example, when a plurality of related objects of the same type are specified, the information providing apparatus 10 generates a ranking of the related objects based on the similarity of the distributed expression between the related object and the co-occurrence target, and assists the generated ranking It may be information. Further, the information providing apparatus 10 calculates a score indicating the relevance with the designated target based on the similarity of the distributed representation between the related target and the co-occurrence target and the similarity of the distributed representation between the designated target and the related target. Then, auxiliary information of contents based on the calculated score value may be provided.

[4-2. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, and conversely, the processes described as being performed manually. All or a part of the above can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments can be appropriately combined within a range in which processing contents do not contradict each other.

[4-3. program〕
The information providing apparatus 10 according to the above-described embodiment is realized by a computer 1000 configured as shown in FIG. 5, for example. FIG. 5 is a diagram illustrating an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. Have

  The arithmetic device 1030 operates based on a program stored in the primary storage device 1040 and the secondary storage device 1050, a program read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various arithmetic operations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, such as ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, and the like. It is realized by.

  The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), This is realized by a standard connector such as HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB.

  The input device 1020 includes, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), and a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), and a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. The input device 1020 may be an external storage medium such as a USB memory.

  The network IF 1080 receives data from other devices via the network N and sends the data to the arithmetic device 1030, and transmits data generated by the arithmetic device 1030 to other devices via the network N.

  The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

  For example, when the computer 1000 functions as the information providing apparatus 10 according to the embodiment, the arithmetic device 1030 of the computer 1000 is a program or data (for example, a learning model) loaded on the primary storage device 1040 or the secondary storage device 1050. By executing the above, the function of the control unit 40 is realized. The arithmetic device 1030 of the computer 1000 reads and executes these programs or data (for example, a learning model) from the primary storage device 1040 or the secondary storage device 1050. As another example, the arithmetic device 1030 from other devices via the network N You may acquire these programs.

[5. effect〕
As described above, the information providing apparatus 10 specifies another target whose impression an user has is similar to the target specified by the business operator. And the information provision apparatus 10 provides a provider with the information regarding the designated object based on the information regarding the other identified object. For this reason, the information provision apparatus 10 can provide a user with useful information regarding the designated object.

  Further, the information providing apparatus 10 identifies another target having co-occurrence with the target specified in the input information input by the user as another target whose user impression is similar to the specified target. . For example, the information providing apparatus 10 specifies another target having co-occurrence with the target specified in the search query input by the user as the input information. In addition, for example, the information providing apparatus 10 specifies another target having co-occurrence with the target specified in the posted information posted by the user as the input information. For this reason, the information providing apparatus 10 can specify another target in which the specified target and the user's impression co-occur, and can provide information based on the information regarding the other target as information regarding the specified target. .

  In addition, the information providing apparatus 10 identifies another transaction target similar to the transaction target specified by the operator, acquires information having co-occurrence with the other transaction target as information related to the other transaction target, and acquires the information. Based on the information, the information regarding the specified transaction object is provided to the business operator. For this reason, the information providing apparatus 10 can acquire information on a target similar to a specified target (that is, a co-occurrence target) and information on a target having co-occurrence as related target information, and can provide the acquired information.

  Further, the information providing apparatus 10 specifies a context similar to the context corresponding to the specified target from the distributed representation of each context generated based on the relative relevance of each context included in the input information, The target corresponding to the identified context is specified as another target. For this reason, the information providing apparatus 10 can appropriately specify the co-occurrence target in which the designation target and the user's impression have co-occurrence.

  Further, the information providing apparatus 10 identifies another context whose distributed representation is similar to the context corresponding to the other target, and provides information on the specified target to the operator based on the information corresponding to the specified context. To do. For example, the information providing apparatus 10 acquires information regarding a location as information regarding other objects. For example, the information providing apparatus 10 acquires information about a person as information about another target. For this reason, the information providing apparatus 10 can provide information that is estimated to be highly relevant to the designation target, that is, useful information to the user.

  Moreover, the information provision apparatus 10 produces | generates the information regarding the sales aspect of the designated object based on the information regarding another object, and provides the produced | generated information to a provider. For this reason, the information providing apparatus 10 can provide information that is estimated to be highly relevant to the designation target as information related to the sales mode of the designation target, and thus can provide useful information to the user. .

  Moreover, the information provision apparatus 10 specifies the object with which the impression which a user has is similar from the object with a category similar to the designated object as another object. For example, the information providing apparatus 10 identifies the upper category of the category to which the designated target belongs, and is a category included in the identified higher category, and is selected from the targets belonging to the category other than the category to which the designated target belongs. , The object with which the impression which a user has is similar is specified. For example, the information providing apparatus 10 may specify a target having a similar impression of a user from among the categories belonging to the same hierarchy as the category to which the designated target belongs, and the category to which the designated target belongs. You may specify the object with which the impression which a user has is similar from the object which belongs to the category of a hierarchy different from. For this reason, the information providing apparatus 10 can appropriately select a target similar to the specified target.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art It is possible to implement the present invention in other forms with improvements.

  Moreover, the above-mentioned “section (module, unit)” can be read as “means”, “circuit”, and the like. For example, the specifying unit can be read as specifying means or a specific circuit.

DESCRIPTION OF SYMBOLS 10 Information provision apparatus 20 Communication part 30 Storage part 31 Distributed expression space database 40 Control part 41 Collection part 42 Generation part 43 Identification part 44 Provision part 100 Provider terminal 200 External server

Claims (16)

A specific unit that identifies other objects whose user impressions are similar to those specified by the operator;
A providing device, comprising: a providing unit that provides information relating to the designated target to the provider based on information related to the other target specified by the specifying unit. The specifying unit specifies another target having co-occurrence with the specified target in the input information input by the user as another target whose user impression is similar to the specified target. The providing device according to claim 1. The providing device according to claim 2, wherein the specifying unit specifies, as the input information, another target having co-occurrence with the specified target in a search query input by the user. The provision according to claim 2 or 3, wherein the specifying unit specifies, as the input information, another target having co-occurrence with the specified target in post information posted by the user. apparatus. The specifying unit specifies another transaction object similar to the transaction object specified by the operator,
The providing unit acquires information having co-occurrence with the other transaction target as information regarding the other transaction target, and provides the operator with the information regarding the specified transaction target based on the acquired information. The providing device according to any one of claims 1 to 4, wherein The specifying unit obtains a context similar to the context corresponding to the specified target from the distributed representation of each context generated based on the relative relevance of each context included in the input information input by the user. The providing device according to any one of claims 1 to 5, characterized in that the target corresponding to the specified context is specified as the other target. The providing unit identifies another context whose distributed representation is similar to the context corresponding to the other target, and provides information regarding the specified target to the operator based on information corresponding to the specified context. The providing device according to claim 6. The providing device according to claim 1, wherein the providing unit acquires information about a location as information about the other object. The providing device according to claim 1, wherein the providing unit acquires information about a person as information about the other target. The said provision part produces | generates the information regarding the sales aspect of the said designated object based on the information regarding the said other object, and provides the produced | generated information to the said provider. The providing device according to any one of the above. The said specific | specification part specifies the object with which the impression which the said user has is similar from the object with the category similar to the said designated object as said other object. The providing device according to any one of the above. The specifying unit specifies a higher category of a category to which the specified target belongs, and is a category included in the specified higher category, and from among targets belonging to a category other than the category to which the specified target belongs, The providing device according to any one of claims 1 to 11, wherein an object having a similar impression of the user is specified. The providing unit according to claim 12, wherein the specifying unit specifies a target having a similar impression of the user from targets belonging to a category of the same hierarchy as the category to which the specified target belongs. apparatus. The said specific | specification part specifies the object with which the impression which the said user has is similar from the object which belongs to the category of the hierarchy different from the category to which the said designated object belongs. Providing device. A providing method executed by a providing device,
A specific process for identifying other transaction objects whose user impressions are similar to the transaction objects specified by the operator;
And a providing step of providing information relating to the designated transaction object to the operator based on information relating to the other transaction object identified by the identifying step. A specific procedure for identifying other transactional objects whose user impressions are similar to those specified by the operator,
A providing program for causing a computer to execute a providing procedure for providing information relating to the specified transaction object to the operator based on information relating to another transaction object specified by the specifying procedure.

Images