JP7292040B2 - Information processing program, information processing apparatus, and information processing method - Google Patents

Description

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

Conventionally, techniques for analyzing information to which annotations have been added have been provided. For example, a technology is provided that receives a plurality of input documents annotated by users and clusters the input documents based on general terms included in the input documents and user terms that are annotated character strings. It is

JP 2015-60581 A

However, the conventional techniques described above do not always provide appropriate annotations. For example, in the conventional technology described above, strokes such as underlines, enclosures, deletion lines, and comments in an input document are regarded as annotations, and annotations cannot always be appropriately added.

The present application has been made in view of the above, and an object thereof is to provide an information processing program, an information processing apparatus, and an information processing method that can appropriately add annotations.

An information processing program according to the present application includes: a display procedure for displaying candidates for tag information to be assigned to a predetermined target based on target information relating to the specified target; and a receiving procedure for receiving an operation regarding whether or not the tag information is appropriate as tag information indicating the object of the tag information.

According to one aspect of the embodiment, there is an effect that annotations can be appropriately added.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to the embodiment; FIG. 3 is a diagram illustrating a configuration example of a shopping server according to the embodiment; 4 is a diagram illustrating an example of a product information storage unit according to the embodiment; FIG. FIG. 5 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; FIG. 6 is a flowchart illustrating an example of an information processing procedure according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Embodiments for implementing an information processing program, an information processing apparatus, and an information processing method according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the information processing program, the information processing apparatus, and the information processing method according to the present application are not limited to this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. embodiment]
Information processing realized by the information processing apparatus and the like according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. In the example shown in FIG. 1, the information processing system 1 has a shopping server 10, a store terminal 20, a user terminal 30, and an information processing device 100. FIG. The shopping server 10, the store terminal 20, the user terminal 30, and the information processing device 100 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). The information processing system 1 shown in FIG. 1 may include multiple shopping servers 10 , multiple store terminals 20 , multiple user terminals 30 , and multiple information processing apparatuses 100 .

The shopping server 10 shown in FIG. 1 is a server device that provides electronic commerce services. In the example shown in FIG. 1 , the shopping server 10 stores product information on products handled in electronic commerce (information on products transmitted from the store terminal 20 and the user terminal 30 ) in the product information storage unit 13 . Based on the product information stored in the product information storage unit 13 and the model stored in the model storage unit 14, the shopping server 10 extracts candidates for tag information from the product information, store in

A store terminal 20 shown in FIG. 1 is an information processing device used by a seller who sells products handled in an electronic commerce service provided by the shopping server 10 . For example, the store terminal 20 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. The store terminal 20 transmits to the shopping server 10 the input information regarding the product input by the seller. In the example shown in FIG. 1, the store terminal 20 is a notebook PC used by the seller.

A user terminal 30 shown in FIG. 1 is an information processing device used by a user. The user terminal 30 is realized by, for example, a smart phone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In addition, the user terminal 30 displays information distributed by the shopping server 10 using a web browser or application. Further, when the user terminal 30 receives from the shopping server 10 the control information for realizing the display processing of the information distributed by the shopping server 10, the user terminal 30 realizes the display processing according to the control information. In addition, the user terminal 30 transmits to the shopping server 10 review information regarding product reviews input by the user. In the example shown in FIG. 1, the user terminal 30 is a smart device such as a smart phone or a tablet used by the user.

Conventionally, when tag information is assigned to a predetermined object using a model, creating learning data for the model has been a heavy burden. Here, the information processing apparatus 100 described below can add information (annotations) regarding whether or not the tag information candidate extracted by the model is appropriate, thereby reducing the burden in creating learning data for the model. can.

The information processing apparatus 100 shown in FIG. 1 is an information processing apparatus used by a judge to determine whether a candidate for tag information corresponding to a product is suitable as tag information indicating the product. For example, the information processing device 100 is a desktop PC, a notebook PC, a tablet terminal, a mobile phone, a PDA, or the like. Here, the information processing apparatus 100 receives product information including candidates for tag information corresponding to the product to be determined, and displays the received information on the output unit (display screen). Then, the information processing apparatus 100 receives an operation regarding whether or not the candidate of tag information is appropriate through an input unit realized by a keyboard, a mouse, operation keys, etc., and transmits operation information regarding the operation to the shopping server 10. . In the example shown in FIG. 1, the information processing apparatus 100 is a notebook PC used by the judge.

Information processing performed by the information processing apparatus 100 will be described below with reference to FIG. In the following description, it is assumed that models for extracting candidates for tag information from product information are stored in the model storage unit 14 . Further, in the following description, the model stored in the model storage unit 14 is defined as "purchase purpose of product (hereinafter, sometimes simply referred to as "purchase purpose")" or "usability of product (hereinafter, simply Candidates for tag information relating to one of the categories of "feeling of use" in some cases) shall be extracted.

First, the process of extracting candidates for tag information by the shopping server 10 will be described.

First, the shopping server 10 receives input information transmitted from the store terminal 20 and review information transmitted from the user terminal 30 (step S11). For example, in the example of FIG. 1, the shopping server 10 inputs information about the image of the product "Health drink A" and the description of the product "Health drink A" (for example, text information such as the maker and catchphrase) as input information. is received from the store terminal 20. Further, in the example of FIG. 1 , the shopping server 10 receives reviews (for example, numerical values (scores) indicating product evaluations) input by users who have purchased the product “Health Drink A” in the electronic commerce service provided by the shopping server 10 . and text information indicating the content of product evaluation) is received from the user terminal 30 as review information. Then, the shopping server 10 stores the received input information and review information in the product information storage unit 13 in association with the product “Healthy drink A”.

Subsequently, the shopping server 10 extracts candidates for tag information from the input information and the review information (step S12). For example, in the example of FIG. 1, the shopping server 10 inputs the text information included in the input information and the review information into the model stored in the model storage unit 14, and converts the character string included in the input text information into tag information. Extract as a candidate. Then, the shopping server 10 stores the extracted tag information candidates and the category of the tag information candidates in the product information storage unit 13 in association with the product “healthy drink A”.

Next, information display processing by the information processing apparatus 100 when a candidate for tag information is determined by a determiner will be described. It is assumed that the information processing apparatus 100 shown in the example of FIG. 1 is used by the judge J1.

First, the information processing device 100 receives product information from the shopping server 10 (step S21). For example, in the example of FIG. 1, the information processing apparatus 100 receives product information including the tag information candidates extracted by the shopping server 10 in step S12.

Subsequently, the information processing device 100 displays product information (step S22). For example, in the example of FIG. 1, the information processing apparatus 100 displays a screen W1 including an area AR1 for displaying input information and an area AR2 for displaying review information. Further, in the example of FIG. 1, the information processing apparatus 100 displays areas AR1-1 to AR1-5 for displaying character strings extracted as tag information candidates from the input information in the area AR1. In the example of FIG. 1, the information processing apparatus 100 displays areas AR2-1 to AR2-10 for displaying character strings extracted as tag information candidates from the review information in the area AR2. In the following description, when the areas AR1-1 to AR1-5 and the areas AR2-1 to AR2-10 are not particularly distinguished, they may be simply referred to as "tag information display areas".

Here, in the tag information display area shown in FIG. 1, the information processing apparatus 100 displays the character strings extracted as tag information candidates in a rectangular area indicated by solid lines, and displays the tag information candidates above the rectangle. View the categories of

Subsequently, the information processing apparatus 100 receives the operation of the judge J1 on the candidate of tag information, and displays the screen in a display mode according to the operation (step S23). For example, in the example of FIG. 1, the information processing apparatus 100 displays the screen W2 in which the tag information display area is displayed according to the operation of the judge J1.

In the example of FIG. 1, the information processing apparatus 100 corresponds the operation of the judge J1 regarding whether or not each candidate of tag information is appropriate as tag information indicating the product "Healthy drink A" to each candidate of tag information. It is accepted for each tag information display area. Specifically, in the example of FIG. 1 , the information processing apparatus 100 detects the product “healthy drink A” such as the purchase purpose and usability of the product “healthy drink A” in the context including the character string extracted as the tag information candidate. As a characteristic of "beverage A", the candidate for the tag information is "appropriate", "inappropriate", or "it is not possible to determine whether it is appropriate (hereinafter, it may be simply described as "impossible to determine")". Accepts the operation of the judge J1 regarding any of the above.

Then, the information processing apparatus 100 displays the tag information display area in a display mode according to the operation of the judge J1. For example, in the example of FIG. 1, the information processing apparatus 100 displays a circle on the right side of the rectangle in the tag information display area when an operation indicating that the tag information candidate is "appropriate" is received, and the tag information candidate is When an "inappropriate" operation is accepted, a cross mark is displayed on the right side of the rectangle in the tag information display area. Further, for example, in the example of FIG. 1, the information processing apparatus 100 superimposes oblique lines within the rectangle of the tag information display area and displays it when an operation indicating that the candidate of the tag information is "undistinguishable" is received.

Here, for example, in the example of FIG. 1, the information processing apparatus 100 converts the character string "workplace" included in the sentence "It has already arrived when I got home from work." Beverage A” is displayed as a candidate for tag information. However, in the context of this document, the string “workplace” characterizes the e-commerce service provided by the shopping server 10 . Therefore, the judge J1 judges that the character string "workplace" is inappropriate as a candidate for the tag information of the product "health drink A" relating to the category "purchase purpose". Then, the information processing apparatus 100 accepts the operation of the judge J1 indicating that the character string displayed in the area AR2-1 is "inappropriate", and displays a cross mark on the right side of the rectangle displayed in the area AR2-1. do.

Further, for example, in the example of FIG. 1, the information processing apparatus 100 converts the character string "moderately sweet" included in the sentence "moderately sweet and easy to drink." A” is displayed as a candidate for the tag information. In the context of this text, the character string "moderately sweet" indicates the characteristics of the product "health drink A." Therefore, the judge J1 judges that the character string "moderately sweet" is appropriate as a candidate for the tag information of the product "healthy drink A" relating to the category "feeling of use". Then, the information processing apparatus 100 receives the operation of the judge J1 indicating that the character string displayed in the area AR2-2 is "appropriate", and displays a circle on the right side of the rectangle displayed in the area AR2-2. .

Further, for example, in the example of FIG. 1, the information processing apparatus 100 classifies the character string "continuation" included in the sentence "Compared to the one from maker C, people will continue to drink." is displayed as a candidate for the tag information of the product "Health drink A". In the context of this text, it is difficult to determine whether the character string "continuity (continuity)" indicates the characteristics of the product "health drink A." Therefore, the determiner J1 determines that it is impossible to determine whether or not the character string "continue" is appropriate as a candidate for the tag information of the product "healthy drink A" relating to the category "usability". Then, the information processing apparatus 100 accepts the operation of the judge J1 indicating that the character string displayed in the area AR2-9 is "undistinguishable", and superimposes a diagonal line in the rectangle displayed in the area AR2-9. indicate.

Note that the information processing apparatus 100 may accept the operation of the judge J1 by any method. For example, in the example of FIG. 1, the information processing apparatus 100 changes the display mode of the tag information display area to a tag information candidate each time the judge J1 performs a selection operation (for example, a click operation) on the tag information display area. is determined to be "appropriate," the tag information candidate is determined to be "inappropriate," and the tag information candidate is determined to be "indistinguishable." as information indicating the operation by the judge J1.

Further, for example, in the example of FIG. 1, when the information processing apparatus 100 receives the selection of the tag information display area, the information processing apparatus 100 may display "appropriate", "inappropriate", and "indistinguishable" as options in a pull-down list format. good. Then, the information processing apparatus 100 takes the option selected by the judge J1 from the list as the operation of the judge J1 on the tag information candidate displayed in the tag information display area.

In addition, the information processing apparatus 100 may change the display mode of the tag information display area by any method such as graphics, symbols, display colors, etc., according to the operation of the judge J1.

Subsequently, the information processing device 100 transmits to the shopping server 10 the operation information regarding the operation of the judge J1 on the tag information candidate (step S24). For example, in the example of FIG. 1, the information processing apparatus 100 indicates any of the operations "appropriate", "inappropriate", or "undistinguishable" performed by the judge J1 on each tag information candidate in step S24. Information in which the information is associated with the tag information candidate is acquired as operation information and transmitted to the shopping server 10 .

Subsequently, the shopping server 10 performs model learning using the operation information received from the information processing device 100 (step S25). Here, in model learning (machine learning), various techniques such as linear regression, logistic regression, support vector machine, decision tree, and hazard analysis may be used.

In the above embodiment, the shopping server 10 may extract rule-based tag information candidates using a model.

As described above, the information processing apparatus 100 according to the embodiment displays information (annotations) about whether or not a candidate for tag information extracted by a model is appropriate on a character string from which the candidate for tag information is extracted. It can be given intuitively by operating with . That is, the information processing apparatus 100 according to the embodiment can appropriately add annotations.

As a result, the shopping server 10 according to the embodiment receives the operation information from the information processing device 100, for example, learns the information about the candidate of the tag information to which the information indicating that it is "appropriate" is given, as a positive example. Information about candidates for tag information to which information indicating "inappropriate" is added can be used as negative learning data for model learning. In addition, the shopping server 10 according to the embodiment, in the electronic commerce service provided by the shopping server 10, uses the candidate tag information to which information indicating "appropriate" is given as a search tag for the corresponding product. On the other hand, it is not necessary to use the candidate tag information to which the information indicating "inappropriate" is attached on the electronic commerce service.

[2. Configuration of information processing system]
Next, the information processing system 1 for realizing the information processing described above will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to the embodiment; As shown in FIG. 2, the information processing system 1 according to the embodiment includes a shopping server 10, a store terminal 20, a user terminal 30, a learning server 40, and an information processing device 100. The shopping server 10, the store terminal 20, the user terminal 30, the learning server 40, and the information processing device 100 are connected via a network N by wire or wirelessly so that they can communicate with each other. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (mobile telephone network, fixed telephone network, etc.), a local IP (Internet Protocol) network, or the Internet. The network N may include wired networks or wireless networks. The information processing system 1 shown in FIG. 2 includes a plurality of shopping servers 10, a plurality of store terminals 20, a plurality of user terminals 30, a plurality of learning servers 40, and a plurality of information processing Apparatus 100 may be included.

The shopping server 10 is a server device that provides electronic commerce services. The shopping server 10 manages the input information transmitted from the store terminal 20 and the review information transmitted from the user terminal 30 as product information regarding products handled in the electronic commerce service. The shopping server 10 also transmits to the information processing apparatus 100 candidates for tag information extracted from product information using a model, and receives operation information regarding whether the candidates for tag information are appropriate. Moreover, the shopping server 10 learns a model based on the received operation information. Note that the model learning process may be implemented by the learning server 40 .

Moreover, the shopping server 10 may be a server that distributes application data itself relating to electronic commerce services. The shopping server 10 may also function as a distribution device that distributes control information to the user terminal 30 and the information processing device 100 . Here, the control information is described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). In addition, you may regard the application itself regarding the content delivered from the shopping server 10 as control information. The configuration of the shopping server 10 will be described later.

The store terminal 20 is an information processing device used by an exhibitor who sells products handled in the electronic commerce service provided by the shopping server 10 . The store terminal 20 transmits to the shopping server 10 the input information regarding the product input by the seller.

The user terminal 30 is an information processing device used by a user. The user terminal 30 displays information delivered by the shopping server 10 using a web browser or an application. Further, when the user terminal 30 receives from the shopping server 10 the control information for realizing the display processing of the information distributed by the shopping server 10, the user terminal 30 realizes the display processing according to the control information. In addition, the user terminal 30 transmits to the shopping server 10 review information regarding product reviews input by the user.

The learning server 40 is a server device that executes learning processing of a model used for extracting candidates for tag information. The learning server 40 executes a model learning process using, as learning data, information related to an operation regarding whether a candidate for tag information is appropriate as tag information indicating a predetermined target, and target information on which the operation has been performed.

The information processing apparatus 100 is an information processing apparatus used by a judge to determine whether a candidate for tag information corresponding to a product is appropriate as tag information indicating the product. The information processing device 100 receives from the shopping server 10 product information including candidates for tag information corresponding to the product to be determined. Further, when the user terminal 30 receives from the shopping server 10 the control information for realizing the display processing of the information distributed by the shopping server 10, the user terminal 30 realizes the display processing according to the control information. Then, the information processing apparatus 100 receives an operation regarding whether or not the tag information candidate is appropriate from the determiner, and transmits operation information regarding the operation to the shopping server 10 . The configuration of the information processing apparatus 100 will be described later.

[3. Configuration of shopping server]
Next, the configuration of the shopping server 10 will be described using FIG. FIG. 3 is a diagram illustrating a configuration example of a shopping server according to the embodiment; As shown in FIG. 3 , the shopping server 10 has a communication section 11 , a storage section 12 and a control section 15 .

(Regarding communication unit 11)
The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the store terminal 20, the user terminal 30, the learning server 40, the information processing device 100, and the like.

(Regarding storage unit 12)
The storage unit 12 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3 , the storage section 12 has a product information storage section 13 and a model storage section 14 .

(Regarding product information storage unit 13)
The product information storage unit 13 stores product information related to products. An example of query-related information stored in the product information storage unit 13 will now be described with reference to FIG. 4 . 4 is a diagram illustrating an example of a product information storage unit according to the embodiment; FIG. In the example of FIG. 4, the product information storage unit 13 stores "product ID", "product name", "input information", "first tag information", "first operation information", "review information", "second It has items such as "tag information" and "second operation information".

"Product ID" indicates identification information for identifying the product. "Product name" indicates the name of the product. “Input information” indicates the input information regarding the product input by the exhibitor using the store terminal 20 . FIG. 4 shows an example in which conceptual information such as "input information 1" is stored in "input information", but in reality, text information related to products, images, videos, and links related to products are stored. Concrete information such as destination, file path name indicating the storage location, URL, and the like are stored.

"First tag information" indicates information about a candidate for tag information extracted from the information stored in the "input information" item. "First tag information" has items such as "tag information" and "category". "Tag information" indicates candidates for tag information extracted from the information stored in the "input information" item. "Category" indicates the category to which the candidate for tag information stored in the item "tag information" belongs.

The “first operation information” is the operation “appropriate” or “inappropriate” performed by the judge using the information processing apparatus 100 on the candidate of the tag information extracted from the information stored in the “input information” item. or information indicating an operation of "undistinguishable" (in other words, information regarding whether or not a candidate for tag information is appropriate).

“Review information” indicates review information regarding product reviews input by the user using the user terminal 30 . "Second tag information" indicates information about candidates for tag information extracted from the information stored in the item "review information". "Second tag information" has items such as "tag information" and "category". "Tag information" indicates candidates for tag information extracted from the information stored in the item "review information". "Category" indicates the category to which the candidate for tag information stored in the item "tag information" belongs.

"Second operation information" is the operation "appropriate" or "inappropriate" performed by the judge using the information processing apparatus 100 on the candidate of tag information extracted from the information stored in the item of "review information". or "unidentifiable".

(Regarding the model storage unit 14)
The model storage unit 14 stores models for extracting candidates for tag information from the product information stored in the product information storage unit 13 .

(Regarding the control unit 15)
The control unit 15 is a controller, and various programs stored in a storage device inside the shopping server 10 are executed by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, using the RAM as a work area. It is realized by being executed. Also, the control unit 15 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 15 according to the embodiment includes a reception unit 16, an extraction unit 17, a transmission unit 18, and a learning unit 19, as shown in FIG. Realize or carry out.

(Regarding the reception unit 16)
The receiving unit 16 receives product information and stores the received product information in the product information storage unit 13 . For example, in the example of FIG. 1 , the reception unit 16 receives input information about the product input by the seller from the store terminal 20 . In the example of FIG. 1 , the receiving unit 16 receives from the user terminal 30 review information regarding product reviews input by the user. The reception unit 16 also processes operation information regarding an operation indicating whether or not a candidate for tag information extracted from product information by an extraction unit 17, which will be described later, is suitable as tag information indicating a product corresponding to the product information. Received from device 100 .

(Regarding the extraction unit 17)
The extraction unit 17 extracts candidates for tag information from product information. For example, in the example of FIG. 1, the extraction unit 17 inputs the text information included in the input information and the review information into the model stored in the model storage unit 14, and converts the character strings included in the input text information into tag information. Extract as a candidate. Then, the extraction unit 17 stores the extracted tag information candidate and the tag information candidate category in the product information storage unit 13 in association with the product.

(Regarding the transmission unit 18)
The transmission unit 18 transmits product information to the information processing device 100 . For example, in the example of FIG. 1 , the transmission unit 18 transmits product information including candidates for tag information extracted by the extraction unit 17 to the information processing device 100 .

(Regarding the learning unit 19)
The learning unit 19 learns the model stored in the model storage unit 14 . For example, in the example of FIG. 1 , the learning unit 19 performs model learning using operation information received from the information processing apparatus 100 .

In addition, when the shopping server 10 and the learning server 40 operate in cooperation, the learning server 40 may have the model storage unit 14 and the learning unit 19 .

[4. Configuration of Information Processing Device]
Next, the configuration of the information processing apparatus 100 will be described using FIG. FIG. 5 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; As shown in FIG. 5 , information processing apparatus 100 includes communication section 110 , storage section 120 , input section 130 , output section 140 and control section 150 .

(Regarding communication unit 110)
The communication unit 110 is implemented by, for example, a NIC. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the shopping server 10, the store terminal 20, the user terminal 30, the learning server 40, and the like.

(Regarding storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM or flash memory, or a storage device such as a hard disk or an optical disk.

(Regarding the input section 130 and the output section 140)
The input unit 130 is an input device that receives various operations from the user. For example, the input unit 130 is implemented by a keyboard, mouse, operation keys, and the like. The output unit 140 is a display device for displaying various information. In other words, the output unit 140 corresponds to the display screen of the information processing device 100 . For example, the output unit 140 is realized by a liquid crystal display or the like. Note that when the information processing apparatus 100 employs a touch panel, the input unit 130 and the output unit 140 are integrated.

(Regarding the control unit 150)
The control unit 150 is a controller, and is implemented, for example, by executing various programs stored in a storage device inside the information processing apparatus 100 using a RAM as a work area by a CPU, MPU, or the like. Also, the control unit 150 is a controller, and is implemented by an integrated circuit such as an ASIC or FPGA, for example. The control unit 150 according to the embodiment includes a display unit 151, a reception unit 152, a display control unit 153, an acquisition unit 154, and a transmission unit 155, as shown in FIG. Realize or perform the function or action of a process.

(Regarding the display unit 151)
The display unit 151 displays candidates for tag information to be given to a predetermined target based on target information about the predetermined target. For example, in the example of FIG. 1, the display unit 151 displays product information including candidates for tag information extracted from the input information and review information of the product "health drink A."

The display unit 151 may display candidates for tag information based on character strings extracted from the target information. For example, in the example of FIG. 1, the display unit 151 displays the character strings included in the text information included in the input information and review information of the product "health drink A" as candidates for tag information.

In addition, the display unit 151 may display candidates for target information and tag information. For example, in the example of FIG. 1, the display unit 151 displays product information including candidates for tag information as shown on the screen W1.

Further, the display unit 151 may display candidates for tag information to be added to the product based on target information, which is information about the product. For example, in the example of FIG. 1, the display unit 151 displays candidates for tag information extracted from product information that is information about the product "Healthy drink A".

In addition, the display unit 151 may display candidates for tag information related to the purchase purpose of the product or the usability of the product. For example, in the example of FIG. 1, the display unit 151 displays candidates for tag information related to either category of "purchase purpose of product" or "usability of product".

In addition, the display unit 151 may display candidates of tag information extracted by a model that performs extraction processing of candidates of tag information from target information. For example, in the example of FIG. 1 , the display unit 151 displays candidates for tag information extracted from models stored in the model storage unit 14 of the shopping server 10 .

(Regarding the reception unit 152)
The receiving unit 152 receives an operation regarding whether or not the tag information candidate displayed by the display unit 151 is appropriate as tag information indicating a predetermined target. For example, in the example of FIG. 1, the reception unit 152 determines whether the tag information candidate is "appropriate,""inappropriate," or "indistinguishable" as a characteristic of the product "health drink A." Accepts the operation of J1.

The receiving unit 152 may also receive an operation on a character string from which a candidate for tag information is extracted. For example, in the example of FIG. 1, the receiving unit 152 receives an operation on a tag information display area displaying a character string extracted as a candidate for tag information among product information.

In addition, the receiving unit 152 may receive an operation regarding whether or not a candidate for tag information is appropriate as tag information indicating a product. For example, in the example of FIG. 1, the receiving unit 152 receives an operation regarding whether or not the candidate tag information is appropriate as indicating the characteristics of the product "health drink A."

(Regarding the display control unit 153)
The display control unit 153 displays the candidate tag information in a display mode according to the operation regarding whether the candidate tag information is appropriate. For example, when an operation on a character string is accepted, the display control unit 153 displays the character string in a display mode according to the operation. For example, in the example of FIG. 1, the display control unit 153 displays a circle on the right side of the rectangle in the tag information display area when an operation indicating that the tag information candidate is "appropriate" is received, and the tag information candidate is When an "inappropriate" operation is accepted, a cross mark is displayed on the right side of the rectangle in the tag information display area. Further, for example, in the example of FIG. 1, the display control unit 153 superimposes oblique lines within the rectangle of the tag information display area and displays it when an operation indicating that the tag information candidate is "unidentifiable" is received.

(Regarding the acquisition unit 154)
The acquisition unit 154 acquires the information about the operation and the target information on which the operation was performed as model learning data. For example, the acquisition unit 154 acquires, as model learning data, information about whether each tag information candidate is appropriate or not, and product information on which an operation has been performed. For example, in the example of FIG. 1, the acquisition unit 154 obtains information indicating whether the operation performed by the judge J1 on each tag information candidate is "appropriate", "inappropriate", or "undistinguishable", and tag information The operation information, which is information associated with the candidates for , is acquired as learning data for the model.

(Regarding the transmission unit 155)
The transmission unit 155 transmits model learning data to a predetermined learning server that executes model learning processing. For example, in the example of FIG. 1, the transmission unit 155 transmits operation information to the shopping server 10 as model learning data.

In addition, when the shopping server 10 and the learning server 40 operate in cooperation, the transmitting unit 155 may transmit the learning data to the learning server 40 .

[5. Information processing flow]
Here, the information processing procedure of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 6 . FIG. 6 is a flowchart illustrating an example of an information processing procedure according to the embodiment.

As shown in FIG. 6, the information processing apparatus 100 displays candidates for tag information (step S101). For example, in the example of FIG. 1, the information processing apparatus 100 displays product information including candidates for tag information. Subsequently, the information processing apparatus 100 receives an operation regarding whether or not the tag information candidate is appropriate (step S102). Subsequently, the information processing apparatus 100 displays candidates for tag information in a display mode according to the operation (step S103). For example, in the example of FIG. 1, the information processing apparatus 100 displays the tag information display area in a display mode according to the operation.

Subsequently, the information processing apparatus 100 acquires learning data (step S104). For example, in the example of FIG. 1, the information processing apparatus 100 stores operation information, which is information indicating an operation performed on each candidate of tag information and information in which the candidate of tag information is associated, as learning data of the model. to get as Subsequently, the information processing device 100 transmits the learning data to the shopping server 10 (step S105), and terminates the process.

[6. Modification]
The above-described embodiment is an example, and various modifications and applications are possible.

[6-1. About product information]
In the above-described embodiment, the information processing apparatus 100 displays candidates for tag information to be added to the product based on product information on the product, and receives an operation for the candidate for the tag information. However, the information processing apparatus 100 displays candidates for tag information to be added to information including character strings composed of characters used in various natural languages, not limited to product information, and allows operations on the candidates for tag information. may be accepted.
[6-2. Candidates for tag information]
In the above-described embodiment, the information processing apparatus 100 shows an example of displaying a character string extracted from product information as a candidate for tag information. Not limited. For example, the information processing apparatus 100 may display words having a common concept, such as synonyms of character strings extracted from the target information, as candidates for tag information. For example, in the example of FIG. 1, the information processing apparatus 100 may display the synonym "high calorie" of the character string "high calorie" extracted from the product information on AR2-5 as a candidate for tag information. Further, for example, in the example of FIG. 1, the information processing apparatus 100 may display the word "health consciousness", which is a hypernym concept of the character string "lack of vegetables" extracted from the product information, as a candidate for the tag information on the AR1-4. good

[7. effect〕
As described above, the information processing apparatus 100 according to the embodiment has the display unit 151, the reception unit 152, the display control unit 153, the acquisition unit 154, and the transmission unit 155. The display unit 151 displays candidates for tag information to be given to a predetermined target based on target information about the predetermined target. The receiving unit 152 receives an operation regarding whether or not the tag information candidate displayed by the display unit 151 is appropriate as tag information indicating a predetermined target. The display control unit 153 displays the candidate tag information in a display mode according to the operation regarding whether the candidate tag information is appropriate. The acquisition unit 154 acquires the information about the operation and the target information on which the operation was performed as model learning data. The transmission unit 155 transmits model learning data to a predetermined learning server that executes model learning processing.

Accordingly, the information processing apparatus 100 according to the embodiment receives an operation regarding whether or not a candidate for tag information is appropriate as tag information, and acquires information regarding the operation, so that an annotation can be appropriately added.

In the information processing apparatus 100 according to the embodiment, for example, the display unit 151 displays candidates for tag information based on character strings extracted from target information. Further, for example, the display unit 151 displays candidates for target information and tag information. Then, the receiving unit 152 receives an operation on the character string from which the candidate for tag information is extracted.

As a result, the information processing apparatus 100 according to the embodiment receives an operation on the extraction source of the tag information candidate, so that the annotation can be appropriately added.

Further, in the information processing apparatus 100 according to the embodiment, for example, when an operation on a character string is accepted, the display control unit 153 displays the character string in a display mode according to the operation.

As a result, the information processing apparatus 100 according to the embodiment makes it possible to visually recognize the information to which the annotation has been added, thereby improving convenience.

Further, in the information processing apparatus 100 according to the embodiment, for example, the display unit 151 displays candidates for tag information to be attached to the product based on target information, which is information about the product. Then, the receiving unit 152 receives an operation regarding whether or not the tag information candidate is appropriate as tag information indicating a product. Further, for example, the display unit 151 displays candidates for tag information related to the purchase purpose of the product or the usability of the product.

As a result, the information processing apparatus 100 according to the embodiment can add annotations to candidates for tag information extracted from product information, thereby reducing the burden of processing information used for e-commerce services and the like.

Further, in the information processing apparatus 100 according to the embodiment, for example, the display unit 151 displays candidates of tag information extracted by a model that performs extraction processing of candidates of tag information from target information.

As a result, the information processing apparatus 100 according to the embodiment can apply annotations to the information output by the model, thereby utilizing the information for model learning processing and the like.

[8. Hardware configuration]
Also, the information processing apparatus according to each of the embodiments described above is implemented by a computer 1000 configured as shown in FIG. 7, for example. The information processing apparatus 100 will be described below as an example. FIG. 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus. Computer 1000 has CPU 1100 , ROM 1200 , RAM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400 and controls each section. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs dependent on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via communication network 500 (corresponding to network N in the embodiment) and sends it to CPU 1100, and also transmits data generated by CPU 1100 via communication network 500 to other devices. Send to device.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . Also, CPU 1100 outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1300 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1300 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing apparatus 100 , the CPU 1100 of the computer 1000 implements the functions of the control unit 150 by executing programs loaded on the RAM 1300 . Further, each data in the storage device of the information processing apparatus 100 is stored in the HDD 1400 . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via a predetermined communication network.

[9. others〕
As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

In addition, the configuration of the information processing apparatus 100 described above can be flexibly changed, for example, by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like, depending on the function.

In addition, the "unit" described in the claims can be read as "means", "circuit", or the like. For example, the display section can be read as display means or a display circuit.

10 shopping server 11 communication unit 12 storage unit 13 product information storage unit 14 model storage unit 15 control unit 16 reception unit 17 extraction unit 18 transmission unit 19 learning unit 20 store terminal 30 user terminal 40 learning server 100 information processing device 110 communication unit 120 Storage unit 130 Input unit 140 Output unit 150 Control unit 151 Display unit 152 Reception unit 153 Display control unit 154 Acquisition unit 155 Transmission unit

Claims (9)

Target information relating to a product provided in a prescribed e-commerce service , which is tag information attached to the product based on the target information indicating the review input by the purchaser of the product, and which is the characteristic of the product a display procedure for displaying candidates for tag information indicating
a reception procedure for accepting an operation regarding whether or not the tag information candidate displayed by the display procedure is appropriate as tag information indicating characteristics of the product in the electronic commerce service from a judge different from the purchaser; An information processing program characterized by being executed by a computer. The display procedure is
2. The information processing program according to claim 1, wherein candidates for said tag information based on character strings extracted from said target information are displayed. The display procedure is
displaying candidates for the target information and the tag information;
The reception procedure includes:
3. The information processing program according to claim 2, wherein the operation for the character string from which the candidate for the tag information is extracted is accepted. 4. The information processing program according to claim 3, further comprising a display control procedure for displaying the character string in a display mode according to the operation when the operation on the character string is accepted. The display procedure is
5. The information processing program according to any one of claims 1 to 4, wherein candidates for the tag information relating to the purchase purpose of the product or the usability of the product are displayed. The display procedure is
6. The information processing program according to any one of claims 1 to 5, wherein the tag information candidates extracted by a model that performs extraction processing of the tag information candidates from the target information are displayed. 7. The information processing program according to claim 6, further comprising an acquisition step of acquiring the information about the operation and the target information on which the operation was performed as learning data for the model. Target information relating to a product provided in a prescribed e-commerce service , which is tag information attached to the product based on the target information indicating the review input by the purchaser of the product, and which is the characteristic of the product a display unit that displays candidates for tag information indicating
a receiving unit that receives an operation regarding whether or not the tag information candidate displayed by the display unit is appropriate as tag information indicating characteristics of the product in the electronic commerce service from a judge different from the purchaser; An information processing device comprising: A computer-executed information processing method comprising:
Target information relating to a product provided in a prescribed e-commerce service , which is tag information attached to the product based on the target information indicating the review input by the purchaser of the product, and which is the characteristic of the product a display step of displaying candidates for tag information indicating
a receiving step of receiving , from a judge different from the purchaser, an operation regarding whether or not the tag information candidate displayed in the displaying step is appropriate as tag information indicating characteristics of the product in the electronic commerce service; An information processing method characterized by comprising:

Images