JP6835786B2 - Estimator, estimation method and estimation program - Google Patents

Description

The present invention relates to an estimation device, an estimation method and an estimation program.

Conventionally, there is known a technique of searching or generating information related to the input information based on the analysis result of the information input via voice, and outputting the searched or generated information as a response. As an example of such information, a technique of identifying a topic from an input conversation and providing content related to the specified topic is known.

Special Table 2007-519047 Japanese Unexamined Patent Publication No. 2014-206998

Here, a method of applying the above-mentioned conventional technique to electronic commerce can be considered. For example, a method is conceivable in which a product or service desired by the user (hereinafter referred to as “transaction target”) is specified from the user's remarks, and a proposal or order for the specified transaction target is made.

However, such a technique may not always reflect the user's wishes. For example, in the prior art, when the user does not say information for identifying the desired transaction target such as the name of the transaction target, the user cannot appropriately specify the desired transaction target. There is.

The present application has been made in view of the above, and an object of the present application is to estimate a transaction target desired by the user without the user consciously speaking information on the transaction target.

The estimation device according to the present application is a detection device installed in a predetermined facility where the user stays, and the voice and environment of the user detected by the detection device from the detection device that detects the surrounding sound. It is characterized by having a collecting unit that collects sounds and an estimating unit that estimates the type of transaction target desired by the user based on the voice of the user and the environmental sound collected by the collecting unit. To do.

According to one aspect of the embodiment, it is possible to estimate the transaction target desired by the user without the user consciously speaking the information of the transaction target.

FIG. 1 is a diagram showing an example of estimation processing executed by the information providing device according to the embodiment. FIG. 2 is a diagram showing a configuration example of the information providing device according to the embodiment. FIG. 3 is a diagram showing an example of information registered in the voice database according to the embodiment. FIG. 4 is a diagram showing an example of information registered in the user database according to the embodiment. FIG. 5 is a diagram showing an example of information registered in the purchase history database according to the embodiment. FIG. 6 is a flowchart showing an example of a flow of estimation processing executed by the information providing device according to the embodiment. FIG. 7 is a diagram showing an example of a hardware configuration.

Hereinafter, an estimation device, an estimation method, and a mode for carrying out the estimation program according to the present application (hereinafter, referred to as “the embodiment”) will be described in detail with reference to the drawings. Note that this embodiment does not limit the estimation device, estimation method, and estimation program according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[Embodiment]
[1-1. An example of an information providing device]
First, an example of estimation processing executed by an information providing device, which is an example of an estimation device, will be described with reference to FIG. FIG. 1 is a diagram showing an example of estimation processing executed by the information providing device according to the embodiment.

The information providing device 10 is an information processing device that executes an estimation process described later, and is realized by, for example, a server device or a cloud system. In FIG. 1, the information providing device 10 can communicate with the terminal device 100 (for example, FIG. 2) used by the user U01 and the detection device S01 described later via a predetermined network N such as the Internet. .. The information providing device 10 may be capable of communicating with an arbitrary number of terminal devices 100 used by an arbitrary user and an arbitrary number of detection devices S01.

The detection device S01 is a device used by the user U01, and has a voice detection device such as a microphone that acquires surrounding voices. Then, the detection device S01 is a device that executes various processes according to the detected voice. For example, the detection device S01 is arranged in the residence H01 in which the user U01 resides, and detects the sound generated in the residence H01. It may be an arbitrary device that identifies the content of the words uttered by the user U01 using voice analysis technology, and realizes the provision of content, orders to various electronic shopping streets, etc. according to the specified content. .. For example, the detection device S01 may have a speaker, and when the user U01 generates information suggesting a song such as a song title or a composer, the detection device S01 may reproduce the song suggested by such information.

Further, the detection device S01 may be, for example, a device having a projector function of projecting an arbitrary image on a wall or the like, and may be, for example, a light bulb or a lighting device having a function of a microphone or a speaker. Further, the detection device S01 may be a so-called assistant robot.

[1-2. Example of estimation processing]
Here, for example, by analyzing the remarks made by the user consciously, such as "buy shampoo", the transaction target of the product or service desired by the user is specified, and the transaction target such as the product or service desired by the user is specified, and the transaction target is specified through the electronic shopping street. Then, a process such as purchasing a specified transaction target can be considered. However, in the prior art, the transaction target desired by the user cannot be specified unless the user consciously states the product name or the like.

Therefore, the information providing device 10 executes the following estimation process. First, the information providing device 10 collects the environmental sound detected by the detection device S01 that detects the surrounding environmental sound, that is, the sound in the house H01 as the environmental sound. Then, the information providing device 10 estimates the transaction target desired by the user based on the collected environmental sounds.

More specifically, the information providing device 10 collects the environmental sound around the user U01 detected by the detection device S01 as the environmental sound. For example, the information providing device 10 collects various environmental sounds in the house H01 such as the sound of water flowing in the house H01, the sound of opening and closing doors, and the sound of a television.

In addition, the information providing device 10 collects sounds unconsciously emitted by the user as environmental sounds. For example, the information providing device 10 collects sneezing and coughing of the user, unconsciously murmurs, unconsciously uttered remarks, and remarks whose target is unknown, such as "Ah! No!", As environmental sounds. To do. The information providing device 10 may collect conversations between the user U01 and other users as environmental sounds. Further, the information providing device 10 may collect any remarks other than the remarks made by the user U01 to the detection device S01 as environmental sounds. That is, the environmental sound is not only a sound generated from an object other than the user U01, but also a word unconsciously uttered by the user U01, a sound such as coughing or sneezing, a conversation with another person, or via a telephone. It includes sounds other than the voice of the user U01 generated for the detection device S01 such as a conversation.

Then, the information providing device 10 estimates the transaction target desired by the user U01 from the collected environmental sounds. More specifically, the information providing device 10 estimates a product or service that is a target of electronic commerce as a transaction target.

[1-3. Specific example of estimation processing]
Here, a specific example of the estimation process executed by the information providing device 10 will be described with reference to FIG. In the example shown in FIG. 1, it is assumed that the user U01 is in the bathroom BR in the residence H01 and is taking a bath. Further, in the example shown in FIG. 1, it is assumed that, for example, shampoo has disappeared as equipment in the bathroom BR.

For example, the detection device S01 is arranged in the house H01 and collects various environmental sounds in the house H01. Here, for example, the detection device S01 includes a voice SW01 such as "Ah! No!" By the user U01 who noticed that the shampoo has run out, and a voice SW02 such as "Shah" where water flows out from the shower. Is detected as an environmental sound, and the detected environmental sound is transmitted to the information providing device 10 (step S1). In such a case, the information providing device 10 estimates the transaction target desired by the user based on the environmental sound (step S2). For example, the information providing device 10 extracts the voice SW01 including the user's voice such as “Ah! No!” And the voice SW02 from which the shower water flows out from the environmental sound detected by the detection device S01 (step S3). ).

Here, it is possible to presume that the user wants something from the voice unconsciously emitted by the user U01, such as the voice SW01 such as "Ah! No!", But it is used. It is difficult to estimate what a person wants to trade. For example, when the voice SW01 does not include the product name or the product type, it is difficult to estimate the transaction target desired by the user.

Therefore, the information providing device 10 estimates the transaction target desired by the user U01 from the environmental sound collected at the same time as the voice SW01, that is, the voice SW02 which is an environmental sound other than the voice of the user U01 (step). S4). For example, when the information providing device 10 analyzes the voice SW02 such as "shear", the information providing device 10 can estimate the state of the user U01 such that the user U01 is taking a shower in the bathroom BR. Therefore, the information providing device 10 estimates the candidate for the transaction target estimated to be desired by the user from the voice SW02. More specifically, the information providing device 10 estimates the state of the user U01 such that the user U01 is taking a shower in the bathroom BR from the voice SW02, and the user U01 desires in the estimated state. Estimate potential trading targets. For example, the information providing device 10 sets "shampoo", "towel", "soap" and the like as candidates for trading.

Subsequently, the information providing device 10 raises the accuracy of the transaction target estimated from the remarks of the user U01 such as the voice SW01 (step S5). For example, in the example shown in FIG. 1, the user U01 makes a statement such as "Ah! No!", That is, a statement indicating the state of the transaction target. Therefore, the information providing device 10 estimates the state of the transaction target from the statement of the user U01, and sets a transaction target desired by the user as a state that can be estimated from the candidates estimated in step S4. select. For example, it is presumed that the information providing device 10 may be in a state where the transaction target may disappear without the user U01 noticing, from the statement such as "Ah! No!". Then, the information providing device 10 desires a "shampoo" from among "shampoo", "towel", "soap", etc., which is likely to disappear without the user U01 noticing. Select as the transaction target.

Then, the information providing device 10 delivers the proposal information that proposes the order of the selected transaction target and the advertisement of the product or service related to the selected transaction target to the user U01 (step S6). For example, the information providing device 10 delivers the advertisement C01 having the content such as "AA shampoo new release !!" to the detection device S01 and outputs it as a voice or the like to convey the content of the advertisement C01 to the user U01. Can be done.

[1-4. Variations in estimation processing]
As described above, the information providing device 10 estimates the transaction target desired by the user U01 based on the environmental sound detected by the detection device S01. However, the embodiments are not limited to this. Hereinafter, another example of the process in which the information providing device 10 estimates the transaction target from the environmental sound will be described. The example shown below is just an example, and the information providing device 10 can be used from any environmental sound if the voice other than the speech made by the user U01 to the detection device S01 is used as the environmental sound. The state of the person U01 and the state that the transaction target can take may be estimated, and any transaction target desired by the user U01 may be estimated based on the estimation contents.

For example, the information providing device 10 presumes that when the user U01 makes a statement such as "Ah! No!", The transaction target may disappear. In addition, when the information providing device 10 makes such a statement, if the voice of the dog or the sound of the tableware used by the dog being placed on the floor is detected, the user U01 feeds the dog. It is presumed that it is in a state of giving. From such estimation results, it can be estimated that the dog food is exhausted. Therefore, the information providing device 10 may presume that the transaction target desired by the user U01 is food for dogs.

Further, for example, when the user U01 makes a statement such as "I like it", the information providing device 10 presumes that the user U01 feels comfortable with the state of the user U01. Further, when the information providing device 10 makes such a statement, if the sound of a lot of water flowing, the sound of other people, the barking of a penguin or a dolphin, or the like is included, the user U01 Is presumed to be in the aquarium. From such an estimation result, it can be estimated that the user U01 likes the aquarium. Therefore, the information providing device 10 may presume that the transaction target desired by the user U01 is a book such as an aquarium, the sea, or fish. That is, even if the information providing device 10 estimates not only the transaction target directly desired by the user U01 but also the transaction target related to the desire of the user U01 as the transaction target desired by the user U01. Good.

In addition to the above-mentioned voice, the information providing device 10 further collects sounds emitted by an object existing around the user U01 due to the behavior of the user U01, and uses the sounds based on the collected sounds. The person U01 may estimate the desired transaction target. For example, if the pump-type container is pushed several times but the contents do not come out, it is estimated that there are no more trading targets to be filled in the pump-type container such as detergent or shampoo. You may. Further, when the information providing device 10 includes a sound when the contents are scattered from the tube-type container, it may be presumed that the transaction target filled in the tube-type container such as mayonnaise has disappeared. That is, the information providing device 10 may estimate the transaction target desired by the user U01 based on the characteristic voice generated when any transaction target disappears.

In addition to the above-mentioned voice, the information providing device 10 includes, for example, a sound of opening and closing the refrigerator, and when the user U01 makes a statement such as "No!", An egg or the like. , It may be presumed that there are no more trading targets placed in the refrigerator. Further, the information providing device 10 may presume that the laundry detergent and the bleaching agent have been exhausted when a statement such as "No!" Is made along with the operation sound of the washing machine.

As described above, the information providing device 10 is an arbitrary sound that can be used for estimating the transaction target from the environmental sounds detected by the detection device S01, and is used when estimating the state of the transaction target and the user U01. Extract characteristic sounds that serve as indicators. Then, the information providing device 10 may estimate the state of the user U01 and the transaction target from the extracted sound, and estimate the transaction target desired by the user U01 based on the estimation result.

The information providing device 10 may improve the estimation accuracy of the transaction target by combining the various processes described above. That is, the information providing device 10 may increase the accuracy of the transaction target by gradually limiting the state of the user U01 and the transaction target from various voices included in the environmental sound. Further, the information providing device 10 may estimate not only the instantaneous needs of the user but also the transaction target satisfying the potential needs based on the estimation process described above.

Further, the information providing device 10 not only collects the transaction target desired by the user U01 at the date and time when the environmental sound is collected, but also unconsciously desires the transaction target, the transaction target predicted to be desired in the future, and the like. You may estimate. For example, the information providing device 10 collects sounds unconsciously emitted by the user U01 (for example, sighing sounds, footsteps, etc.) as environmental sounds, and the user U01 unconsciously desires based on the collected environmental sounds. Then, the expected transaction target may be estimated. Further, the information providing device 10 predicts that the shampoo will disappear in the future when the number of times the pump of the pump type container is pressed changes, and the shampoo is a transaction target that the user U01 predicts to desire in the future. May be specified.

[1-5. Combination of multiple devices]
Further, the information providing device 10 may estimate the transaction target based on not only the detection device S01 but also the environmental sounds acquired by a plurality of detection devices. For example, the information providing device 10 may estimate the transaction target based on the environmental sounds collected by a plurality of microphones installed in the house H01 and the environmental sounds collected by the plurality of detection devices S01. Good. Further, for example, the information providing device 10 may estimate the transaction target based on the environmental sound acquired by, for example, a terminal device used by the user U01 or an arbitrary device such as a wearable device.

[1-6. Estimating processing using various information]
Further, the information providing device 10 may improve the estimation accuracy of the transaction target desired by the user U01 by adding other information in addition to the environmental sound. For example, the information providing device 10 may further collect the position information indicating the position of the user U01 and estimate the transaction target desired by the user based on the environmental sound and the position information. To give a specific example, the information providing device 10 uses GPS (Global Positioning System), beacons, various sensing technologies, and the like to determine the position (room, etc.) in the house H01 where the user U01 is located, and the user. Identify the facility where U01 is located. Further, the information providing device 10 collects, for example, environmental sounds detected by the terminal device or wearable device used by the user U01. Then, the information providing device 10 is a transaction target desired by the user U01, for example, depending on whether the user U01 is in the room, in which facility the user U01 is, what kind of environmental sound is collected, and the like. May be estimated.

Further, the information providing device 10 may estimate the transaction target desired by the user based on sounds other than the remarks made by the user. For example, when the information providing device 10 collects sounds such as coughing and sneezing, the information providing device 10 may estimate a cold medicine, a mask, or the like as a transaction target desired by the user U01. Further, for example, the information providing device 10 may estimate the physical state of the user U01 from footsteps and the like, and estimate the transaction target desired by the user U01 based on the estimation result. More specifically, the information providing device 10 may estimate that the user U01 has hurt his / her foot when the rhythm of the footsteps satisfies a predetermined condition, and may estimate the compress as a transaction target.

In addition, the information providing device 10 detects remarks made by the user U01 during a conversation with another user, tweets and soliloquy made by the user U01, remarks made by the user U01 during a telephone call, and the like. A voice other than a clear instruction to the device S01 or the like may be collected as an environmental sound, and the transaction target may be estimated based on the collected voice. Further, the information providing device 10 may collect, for example, the sound of a television or the like as an environmental sound, and estimate the transaction target based on the collected sound. For example, the information providing device 10 estimates the transaction target that the user U01 is watching from the sound of the television. Then, for example, when the information providing device 10 makes a statement such as "I like it", that is, a statement indicating that the user U01 has a favorable impression on the transaction target used, it is estimated. It may be determined that the user U01 wants the transaction target, and information, advertisements, etc. regarding the transaction target may be distributed to the user U01. Further, the information providing device 10 analyzes the conversation between the user U01 and another user, and if the desired transaction target or the remark of the favorite transaction target is included, the user U01 desires the transaction target. It may be a transaction target.

Further, the information providing device 10 may estimate the transaction target desired by the user U01 based on the history of the transaction target acquired by the user U01, that is, the history of the transaction target purchased by the user U01. For example, when it can be estimated from the environmental sound that the user U01 wants soap or shampoo, the information providing device 10 refers to the history of the transaction target purchased by the user U01. Then, for example, when the predetermined date and time has not passed since the user U01 purchased the shampoo, the information providing device 10 has passed the predetermined date and time since the purchase of the soap. It may be presumed that the soap is gone and that the user U01 wants soap.

[1-7. Information provision mode]
Here, the information providing device 10 may provide the user U01 with information indicating a transaction target presumed to be desired by the user U01 in an arbitrary format. For example, the information providing device 10 may deliver an advertisement related to the estimated transaction target, or may provide an inquiry as to whether or not to order the estimated transaction target. Further, the information providing device 10 may provide the user U01 with a list of estimated transaction targets at predetermined time intervals (for example, monthly). Further, when executing such a process, the information providing device 10 may exclude the transaction target actually purchased by the user U01 from the list.

Further, the information providing device 10 may provide information indicating a transaction target at a timing corresponding to the detected environmental sound, the current position of the user U01, and the like. More specifically, the information providing device 10 provides the user U01 with information on the transaction target that is related to the current position of the user U01 among the transaction targets estimated to be desired by the user U01. You may. For example, when the user U01 is in a bookstore, the information providing device 10 may provide the information of the book to the user U01 among the transaction targets presumed to be desired by the user U01.

Further, the information providing device 10 puts the estimated transaction target in, for example, a virtual cart in the electronic shopping district, and presents a list showing the contents of the cart to the user U01, so that the transaction target can be quickly dealt with. The purchase may be realized. Further, for example, when the probability that the user U01 desires the transaction target is higher than a predetermined threshold value, the information providing device 10 does not present the information of the transaction target, but directly places an order to the electronic shopping district. You may go.

[1-8. Others]
The information providing device 10 may execute the above-mentioned processes in combination in any manner. For example, the information providing device 10 improves the estimation accuracy of the transaction target estimated to be desired by the user U01 by arbitrarily combining arbitrary information such as environmental sounds, user's remarks, and user's position. May be good. Further, the information providing device 10 may estimate the transaction target based on, for example, the number of characteristic sounds (for example, the sound of pressing a pump-type container) included in the environmental sound.

The information providing device 10 may execute the above-mentioned processing based on a pre-modeled model. In such a model, a predetermined characteristic sound may be extracted from the environmental sounds detected by the detection device S01, and various sounds used for estimating the transaction target can be extracted. Such a model may be one in which various voice features used for estimating a transaction target are learned in advance, or may be one in which learning is performed by various learning techniques such as deep learning. ..

[2. Configuration of information providing device]
Hereinafter, an example of the functional configuration of the information providing device 10 that realizes the above estimation processing will be described. FIG. 2 is a diagram showing a configuration example of the information providing device according to the embodiment. As shown in FIG. 2, the information providing device 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

The communication unit 20 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 20 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the terminal device 100 and the detection device S01, which are various terminal devices used by the user. For example, the terminal device 100 is a smart device such as a smartphone or tablet, and can communicate with an arbitrary server device via a wireless communication network such as 3G (3rd Generation) or LTE (Long Term Evolution). It is a mobile terminal device.

The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. In addition, the storage unit 30 stores the voice database 31, the user database 32, and the purchase history database 33.

The voice detected by the detection device S01, that is, the environmental sound is registered in the voice database 31. For example, FIG. 3 is a diagram showing an example of information registered in the voice database according to the embodiment. In the example shown in FIG. 3, information having items such as "detection device", "voice data", and "collection date and time" is registered in the voice database 31. In addition to the information shown in FIG. 3, various information related to the detection device (for example, installation position, etc.) may be registered in the voice database 31.

Here, the "detection device" is information indicating a detection device that has detected an environmental sound. Further, the "voice data" is the voice detected by the detection device, that is, the environmental sound data. The "collection date and time" is information indicating the date and time when the environmental sound was collected. In the example shown in FIG. 3, conceptual values such as "voice data # 1" and "date and time # 1" are described, but in reality, a voice file of any format, a value indicating the date and time, and the like are registered. Will be done.

For example, in the example shown in FIG. 3, the detection device "S01", the voice data "voice data # 1", the collection date and time "date and time # 1", and the like are registered in association with the voice database 31. Such information indicates that the environmental sound data collected by the detection device S01 at "date and time # 1" is "voice data # 1".

Returning to FIG. 2, various information about the user is registered in the user database 32. For example, FIG. 4 is a diagram showing an example of information registered in the user database according to the embodiment. In the example shown in FIG. 4, information having the items "user" and "detection data" is registered in the user database 32. In addition to the information shown in FIG. 4, various information related to each user, for example, attribute information indicating various attributes such as gender and age, may be registered in the user database 32.

Here, the "user" is information indicating which user the associated detection data is related to. Further, the "detection data" is, for example, position information indicating the position of the user specified by GPS positioning technology or various sensing technologies, or various information detected by various sensing technologies for the user. is there. In the example shown in FIG. 4, a conceptual value such as "detection data # 1" is described, but in reality, information indicating the position and an arbitrary sensing result is registered.

For example, in the example shown in FIG. 4, the user "user # 1", the detection data "detection data # 1", and the like are registered in the user database 32 in association with each other. Such information indicates that the user (for example, user U01) indicated by user # 1 is present at the position indicated by the detection data “detection data # 1”. That is, the information detected by various sensing technologies related to IoT (Internet of Things) and related to each user is registered in the user database 32.

Returning to FIG. 2, the history of the transaction target purchased by the user U01 is registered in the purchase history database 33. For example, FIG. 5 is a diagram showing an example of information registered in the purchase history database according to the embodiment. In the example shown in FIG. 5, information having items such as "purchaser", "purchased item", and "purchase date and time" is registered in the purchase history database 33. In addition to the information shown in FIG. 5, information regarding the transaction target purchased by each user may be registered in the purchase history database 33.

Here, the "purchaser" is information indicating a user who has purchased the associated transaction target. Further, the "purchased item" is information indicating a transaction target such as a product or service purchased by the user. The "purchase date and time" is information indicating the date and time when the user purchased the transaction target. For example, in the example shown in FIG. 5, the purchaser "user # 1", the purchased item "shampoo", and the purchase date and time "date and time # 1" are registered in the purchase history database 33 in association with each other. Such information indicates, for example, that the purchased product "shampoo" was purchased by the user indicated by the purchaser "user # 1" at the date and time indicated by the purchase date and time "date and time # 1".

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

As shown in FIG. 2, the control unit 40 includes a collection unit 41, an estimation unit 42, and a providing unit 43. The collecting unit 41 collects the environmental sound detected by the detection device S01 that detects the ambient environmental sound. Then, the collecting unit 41 registers the environment detected by the detection device S01 in the voice database 31 in association with the information indicating the detection device S01 and the detection date and time of the environmental sound.

Here, the collecting unit 41 may collect environmental sounds around the user U01 as environmental sounds, or may collect sounds such as voices and footsteps unconsciously emitted by the user U01. Further, the collecting unit 41 may collect the environmental sounds detected by the plurality of detection devices S01 as the environmental sounds, and the user U01's remarks such as a conversation with a friend of the user U01, a telephone remark, a soliloquy, and the like. That is, various remarks other than the instruction to the detection device S01 may be collected as environmental sounds.

Further, the collecting unit 41 may collect sounds emitted by the user U01 such as a sneezing sound and a coughing sound, and the user such as a sound of pressing the pump of the pump type container and a sound of operating the washing machine. Sounds emitted by objects existing around the user U01 due to the actions of the U01 may be collected. In addition to the environmental sound, the collecting unit 41 may collect various kinds of information about the user U01, which is used for estimating the transaction target desired by the user U01. For example, the collecting unit 41 may collect position information indicating the position of the user U01.

Based on the collected environmental sounds, the estimation unit 42 estimates the goods or services that are the targets of electronic commerce as the transaction targets desired by the user. For example, the estimation unit 42 refers to the voice database 31 and extracts voice data associated with the user U01. Then, the estimation unit 42 estimates the state of the user U01, the state of the candidate for the transaction target desired by the user U01, etc. from the extracted voice data, that is, the environmental sound, and based on the estimation result, the user U01 Estimates the desired trading target.

The estimation unit 42 may improve the estimation accuracy (that is, the accuracy) of the transaction target based on various information registered in the user database 32 and the purchase history database 33. For example, the estimation unit 42 identifies the user U01 to be estimated as the transaction target from the environmental sound, and acquires the detection data and purchase history related to the user U01 from the user database 32 and the purchase history database 33. Further, the estimation unit 42 may estimate the transaction target desired by the user U01 based on the environmental sound and the position information, and the user U01 may estimate the transaction target desired by the user U01 based on the environmental sound and the user's remark included in the environmental sound. May estimate the desired trading object. Further, the estimation unit 42 may estimate the transaction target desired by the user U01 based on the sound emitted by the user U01, the sound of an object caused by the behavior of the user U01, and the like. Further, the estimation unit 42 may estimate the transaction target desired by the user U01 based on the history of the transaction target purchased by the user U01.

The providing unit 43 provides the user U01 with information indicating a transaction target presumed to be desired by the user U01. For example, the providing unit 43 may distribute the list of transaction targets estimated by the estimation unit 42, related advertisements, and the like to the terminal device 100 used by the user U01. Further, when the position of the user U01 is a position related to the transaction target estimated to be desired by the user U01, the providing unit 43 may provide information indicating the transaction target. For example, when the user U01 is located in or near the bookstore, the providing unit 43 may provide information on the transaction target related to the book among the transaction targets estimated to be desired by the user U01.

[3. Processing flow of information providing device]
Next, an example of the procedure of the estimation process executed by the information providing device 10 will be described with reference to FIG. FIG. 6 is a flowchart showing an example of a flow of estimation processing executed by the information providing device according to the embodiment. For example, the information providing device 10 collects environmental sounds (step S101). Then, the information providing device 10 identifies a candidate for a transaction target presumed to be desired by the user U01 from the voice included in the environmental sound (step S102), and the user's remarks and purchase history included in the environmental sound. Based on the current position of the user and the like, the certainty desired by the user U01 is obtained for each candidate (step S103). Then, the information providing device 10 estimates the candidate with the highest accuracy as the transaction target desired by the user U01 (step S104), and provides the estimated transaction target information to the user U01 (step S105). End the process.

[4. Modification example]
In the above, an example of the estimation process by the information providing device 10 has been described. However, the embodiments are not limited to this. Hereinafter, variations of the estimation process executed by the information providing device 10 will be described.

[4-1. About environmental sounds]
In the above example, the information providing device 10 estimates the transaction target desired by the user based on the environmental sound detected by the detection device S01. Here, the various estimation processes described above are merely examples, and the information providing device 10 may execute the estimation processing in any mode other than the estimation processing described above.

For example, when the information providing device 10 detects the sound of rain hitting the house H01 as an environmental sound, an umbrella, a raincoat, or the like may be a candidate for a transaction target desired by the user U01. Further, the information providing device 10 determines the state of the user U01 based on the environmental sound that can be acquired when the user U01 browses the content without sound, such as a mouse click sound or a keyboard press sound. It is estimated, and the transaction target desired by the user U01 may be estimated based on the estimation result. Also. The information management device 10 estimates the state of the user U01 from the environmental sound that can be acquired by the user U01 while eating and drinking, the environmental sound that can be acquired during exercise, the environmental sound that can be acquired during play, and the like, and the estimation result. The transaction target desired by the user U01 may be estimated based on the above. In addition to the above-mentioned example, the information providing device 10 may specify an arbitrary context from the environmental sound and estimate the transaction target desired by the user U01 according to the specified context.

Further, the information providing device 10 may use the voice of the user U01 included in the environmental sound as a trigger for processing. For example, when the detection device S01 detects the voice of the user U01, the detection device S01 transmits the voice acquired within a predetermined range from the date and time when the voice of the user U01 is included to the information providing device 10 as an environmental sound. You may. In addition, the above-mentioned estimation process may be executed and realized at an arbitrary timing.

[4-2. Information provision]
Further, for example, the information providing device 10 is a transaction target having a relationship with what the user U01 is visually recognizing by using, for example, a glasses-type wearable device worn by the user U01 in addition to the environmental sound. Information may be provided. Further, the information providing device 10 lists the degree of interest that the user U01 has in each transaction target by using the technology of the ability tracker, and estimates the transaction target desired by the user U01 based on the list. You may.

For example, the information providing device 10 may estimate not only the goods but also the services desired by the user U01 as the transaction target. For example, when it is presumed from the environmental sound that the user U01 wants to provide a predetermined service, the information providing device 10 tells the provider who provides the service to the user U01. You may notify us to provide the service. That is, the information providing device 10 may provide the information of the transaction target desired by the user U01 not only to the user U01 but also to other users related to the transaction target. For example, when it is estimated that the user U01 wants a certain product, the information providing device 10 notifies the seller who sells the product that the user U01 wants the product. You may.

[4-3. Device configuration〕
The information providing device 10 may be communicably connected to an arbitrary number of terminal devices 100, or may be communicably connected to an arbitrary number of detection devices S01. Further, the information providing device 10 is realized by the front-end server that communicates with the terminal device 100 and the back-end server that communicates with the detection device S01 and executes the estimation process described above in cooperation with each other. You may.

[4-4. Relationship between environmental sounds and user-related sounds]
Here, in the above description, the information providing device 10 collects the environmental sounds around the user U01 and the sounds unconsciously emitted by the user U01 as the environmental sounds collected by the detection device S01, and collects the environmental sounds. Based on, the transaction target desired by the user was estimated. Here, the information providing device 10 may estimate the transaction target desired by the user based on the sounds consciously emitted by the user U01 for various environments. For example, the information management device 10 makes a tweet such as "Like" or a sound of clapping or clapping a finger while browsing TV or the like, that is, a sound emitted due to the action of the user U01. Based on this, the transaction target desired by the user may be estimated.

That is, the information providing device 10 is a sound indicating a user's conscious or unconscious reaction to various environmental sounds and the state caused by the environmental sound itself or the environmental sound (that is, the user's remarks and usage). The transaction target desired by the user is estimated based on the sound produced by the user. In such processing, the information providing device 10 may include a sound unconsciously emitted by the user in the environmental sound. As a result of such processing, the information providing device 10 can improve the estimation accuracy of the transaction target desired by the user.

[4-5. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured. For example, the collecting unit 41, the estimating unit 42, and the providing unit 43 shown in FIG. 2 may be integrated.

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

[5. program〕
Further, the information providing device 10 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 7. FIG. 7 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to the output device 1010 and the input device 1020, and the arithmetic unit 1030, the primary storage device 1040, the secondary storage device 1050, the output IF (Interface) 1060, the input IF 1070, and the network IF 1080 are connected by the bus 1090. Has.

The arithmetic unit 1030 operates based on a program stored in the primary storage device 1040 or the secondary storage device 1050, a program read from the input device 1020, or 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 unit 1030 for various calculations. Further, the secondary storage device 1050 is a storage device in which data used by the calculation device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD, a flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), and the like. It is realized by a connector of a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Further, 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, USB.

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

The network IF1080 receives data from another device via the network N and sends it to the arithmetic unit 1030, and also transmits the data generated by the arithmetic unit 1030 to the other device via the network N.

The arithmetic unit 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 unit 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 device 10, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 40 by executing the program loaded on the primary storage device 1040.

[6. effect〕
As described above, the information providing device 10 collects the environmental sound detected by the detection device S01 that detects the ambient environmental sound. Then, the information providing device 10 estimates the transaction target desired by the user based on the collected environmental sounds.

More specifically, the information providing device 10 collects environmental sounds around the user, sounds unconsciously emitted by the user, environmental sounds detected by a plurality of detection devices S01, and the like.

Then, the information providing device 10 estimates a product or service that is a target of electronic commerce as a transaction target.

Further, the information providing device 10 further collects the position information indicating the position of the user, and estimates the transaction target desired by the user based on the environmental sound and the position information.

In addition, the information providing device 10 further collects the user's remarks, and estimates the transaction target desired by the user based on the environmental sound and the user's remarks.

In addition, the information providing device 10 further collects the sound emitted by the user, and estimates the transaction target desired by the user based on the environmental sound and the sound emitted by the user.

Further, the information providing device 10 further collects the sounds emitted by the objects existing around the user due to the behavior of the user, and the user makes a sound based on the environmental sound and the sound emitted by the object. Estimate the desired trading target.

In addition, the information providing device 10 estimates the transaction target desired by the user based on the history of the transaction target acquired by the user.

In addition, the information providing device 10 provides the user with information indicating the estimated transaction target. For example, the information providing device 10 further collects the position information indicating the position of the user, and when the position of the user indicated by the collected position information is a position related to the estimated transaction target, the transaction target. Provide information indicating.

As a result of at least one of the above-mentioned processes, the information providing device 10 can estimate the transaction target desired by the user without the user consciously speaking the information of the transaction target. In addition, the information providing device 10 can improve the estimation accuracy of the transaction target desired by the user by using the environmental sound in combination with other information.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

In addition, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the estimation unit can be read as a distribution means or a distribution circuit.

10 Information providing device 20 Communication unit 30 Storage unit 31 Voice database 32 User database 33 Purchase history database 40 Control unit 41 Collection unit 42 Estimating unit 43 Providing unit S01 Detection device 100 Terminal device

Claims (14)

A collection unit that is a detection device installed in a predetermined facility where the user stays and collects the user's voice and environmental sound detected by the detection device from the detection device that detects the surrounding sound. When,
Based on the user's voice and environmental sound collected by the collection unit, it is estimated that the transaction target desired by the user and provided to the user via the electronic shopping district is estimated. An estimation device characterized by having a part. The estimation device according to claim 1, wherein the collecting unit collects environmental sounds around the user as the environmental sounds. The estimation device according to claim 1 or 2, wherein the collecting unit collects a sound unconsciously emitted by the user as the voice of the user. The estimating unit, the user is a type of transaction target desired, claim 1, characterized in that for estimating the type of goods or services provided to the user via the electronic commerce shop street The estimation device according to any one of ~ 3. The estimation device according to any one of claims 1 to 4, wherein the collecting unit collects the environmental sound detected by the plurality of detection devices and the voice of the user. The collecting unit further collects position information indicating the position of the user, and collects the position information.
The estimation unit, said environmental sound, on the basis of said position information, estimation according to any one of claims 1 to 5, wherein the user and estimates a desired transaction Target apparatus. The collecting unit further collects the remarks of the user,
The estimation unit, said environmental sound, based on the speech of the user, according to any one of claims 1 to 6 wherein the user and estimates a desired transaction Target Estimator. The collecting unit further collects the sound emitted by the user.
The estimation unit, said environmental sound, based on the sound which the user uttered, any one of the claims 1 to 7, wherein the user and estimates a desired transaction Target The estimation device described in. The collecting unit further collects the sounds emitted by the objects existing around the user due to the behavior of the user.
The estimation unit, said environmental sound, on the basis of the sound of the object is emitted, to any one of claims 1 to 8, wherein the user and estimates a desired transaction Target The estimated device described. The estimating unit, based on the history of the transaction object the user has acquired, the user according to any one of claims 1 to 9, wherein the estimating the desired transaction Target Estimator. The estimation device according to any one of claims 1 to 10, further comprising a providing unit that provides the user with information indicating a type of transaction target estimated by the estimation unit. The collecting unit further collects position information indicating the position of the user, and collects the position information.
The providing unit, the position of the user location information collected by the collection unit is indicated, if the a position associated with the trading Target estimated by the estimation unit, the information indicating the person said mounting argument object The estimation device according to claim 11, wherein the estimation device is provided. It is a management method executed by the management device.
A collection process that collects the user's voice and environmental sound detected by the detection device from the detection device that is installed in the predetermined facility where the user stays and detects the surrounding sound. When,
Based on the user's voice and environmental sound collected by the collection process, it is estimated that the transaction target desired by the user and provided to the user via the electronic shopping district is estimated. An estimation method characterized by including steps. On the computer
A collection procedure for collecting the voice of the user and the environmental sound detected by the detection device from the detection device installed in the predetermined facility where the user stays and detecting the surrounding sound. When,
Based on the user's voice and environmental sound collected by the collection procedure, it is estimated that the transaction target desired by the user and provided to the user via the electronic shopping street is estimated. An estimation program to execute the procedure and.

Images