JP2021089551A - Commodity information retrieval system - Google Patents

Abstract

To provide a commodity information retrieval system for improving efficiency of retrieving information on a commodity.SOLUTION: A commodity information retrieval system 1 is a retrieval system for extracting commodity information on foods, and includes: a retrieval data generation unit 11 for generating text information including a commodity name and a name of attached information as retrieval data from data on the commodity name and data on attached information corresponding to the commodity name; a voice acquisition unit 14 for acquiring utterance of a user concerning a commodity as a voice signal; and a commodity information output unit 17 for outputting information on the commodity corresponding to the utterance of the user based on text information of the utterance obtained from the voice signal and the data for retrieval.SELECTED DRAWING: Figure 1

Description

The present invention relates to a product information retrieval system that extracts product information of food products.

As disclosed in Patent Document 1 (Japanese Unexamined Patent Publication No. 2018-130860), a label issuance including an extraction method designation means, a product information extraction means, a product information narrowing means, and a product extraction method switching means. The device is known. The extraction method specifying means specifies a product extraction method by voice when extracting product information. The product information extraction means extracts the product information by the product extraction method designated by the extraction method designation means. The product information narrowing-down means narrows down the product information from the product information extracted by the product information extraction means. The product extraction method switching means can switch the product extraction method based on voice at the stage of narrowing down the product information by the product information narrowing means.

In Patent Document 1, it is necessary to specify the product extraction method by voice before extracting the product information. Therefore, it takes time and effort to extract the product information.

An object of the present invention is to provide a product information search system that improves the efficiency of searching product information.

The product information search system according to the first aspect is a search system that extracts product information of food products. The product information search system includes a search data generation unit, a voice acquisition unit, and a product information output unit. The search data generation unit generates text information including the product name and the name of the attached information as the search data from the product name data and the attached information data corresponding to the product name. The voice acquisition unit acquires the utterance of the user's product as a voice signal. The product information output unit outputs product information corresponding to the user's utterance based on the utterance text information obtained from the audio signal and the search data.

In the product information search system of the first aspect, the search data generation unit generates text information including the product name and the name of the attached information as search data. The product information output unit can output product information corresponding to the user's utterance based on the generated search data and the utterance text information obtained from the voice signal acquired by the voice acquisition unit. Therefore, the user can search for product information by uttering the product name and attached information without specifying the product extraction method. Therefore, it is possible to improve the efficiency of searching for product information.

The product information retrieval system according to the second aspect is the product information retrieval system according to the first aspect, and further includes a voice recognition engine communication unit. The voice recognition engine communication unit transmits the voice signal to the voice recognition engine, and receives the text information of the voice signal from the voice recognition engine.

In the product information retrieval system of the second aspect, the text information of the utterance obtained from the voice signal can be easily obtained by using the voice recognition engine.

The product information search system according to the third viewpoint is a product information search system according to the first viewpoint or the second viewpoint, and further includes a pretending pseudonym conversion engine communication unit. The Furi-Kana conversion engine communication unit transmits the product name data and the attached information data to the Furi-Kana conversion engine, and receives the text information including the name of the product name and the attached information from the Furi-Kana conversion engine.

In the product information retrieval system of the third aspect, by using the pretending pseudonym conversion engine, it is possible to easily obtain the data of the product name and the attached information and the text information including the name of the product name and the attached information.

The product information search system according to the fourth viewpoint is a product information search system according to the first to third viewpoints, and the attached information includes at least the place of origin, size, calories, unit price, raw materials, additives, and allergies. Including one.

In the product information search system of the fourth aspect, the user can search for the above-mentioned information as ancillary information corresponding to the product name by vocalization.

The product information search system according to the fifth viewpoint is a product information search system according to the first to fourth viewpoints, and the product information output unit outputs information on a plurality of products corresponding to the voice of the user.

In the product information search system of the fifth viewpoint, when there is a plurality of product information corresponding to the user's utterance, the candidate can be output.

The product information search system according to the sixth viewpoint is the product information search system according to the fifth viewpoint, and further includes a narrowing unit that narrows down the information of a plurality of products.

In the product information search system of the sixth aspect, the user can further narrow down the information of the product to be output from the information of a plurality of products by the narrowing unit.

The product information search system according to the seventh viewpoint is the product information search system according to the first to sixth viewpoints, and the search data generation unit, the voice acquisition unit, and the product information output unit are stored in the voice recognition server. Will be done.

In the product information search system of the seventh aspect, the product information corresponding to the user's utterance can be output in the voice recognition server.

According to the present invention, it is possible to improve the efficiency of searching for product information.

It is a block diagram of the product information search system of an embodiment. This is an example of product name data. This is an example of attached information data. This is an example of search data. It is a flowchart which shows the generation method of the search data. It is a flowchart which shows the product information search method. This is an example of the screen of the terminal device. This is an example of the screen of the terminal device. This is an example of the screen of the terminal device. This is an example of the screen of the terminal device. It is a block diagram of the product information search system of a modification. It is a block diagram of the product information search system of a modification.

The product information retrieval system 1 according to the embodiment of the present invention will be described below.

(1) Overall Overview The product information search system 1 is a search system that extracts product information of food products. The product information retrieval system 1 of this embodiment is used for the label issuing device 2. That is, the product information search system 1 is a system for searching the product information of the label issued by the label issuing device 2.

As shown in FIG. 1, the product information search system 1 includes a search data generation unit 11, a pretending pseudonym conversion engine communication unit 12, a voice acquisition unit 14, a voice recognition engine communication unit 15, and a product information output unit 17. , An input unit 51, a narrowing unit 53, and a display unit 52 are mainly provided.

The search data generation unit 11, the voice acquisition unit 14, and the product information output unit 17 are stored in the voice recognition server 3. The search data generation unit 11, the voice acquisition unit 14, and the product information output unit 17 are included in the control unit of the voice recognition server 3.

The product information search system 1 uses the upper server 4. The upper server 4 stores the product name data 41 and the attached information data 42 to 44. The product name data 41 and the attached information data 42 to 44 are regularly updated due to changes in the product. For example, the product name data 41 and the attached information data 42 to 44 are transmitted from the label issuing device 2 to the upper server 4.

The upper server 4 is a server different from the voice recognition server 3. Here, the upper server 4 is connected to one label issuing device 2 by a communication line. The upper server 4 may be connected to a plurality of label issuing devices 2 installed in different stores by a communication line.

The product information search system 1 uses the pretending pseudonym conversion engine 13 and the voice recognition engine 16. The pretending pseudonym conversion engine 13 and the voice recognition engine 16 may be stored in one of the voice recognition server 3 and the upper server 4, but in the present embodiment, they are stored in the external server. The external server is a server different from the voice recognition server 3 and the upper server 4.

The input unit 51, the display unit 52, and the narrowing unit 53 are stored in the terminal device 5. As the terminal device 5, for example, a smartphone, a tablet terminal, or the like is used. The application is installed in the terminal device 5.

The voice recognition server 3 and the upper server 4 are, for example, cloud servers. The voice recognition server 3 and the higher-level server 4 may use artificial intelligence (AI).

The control unit of the label issuing device 2, the voice recognition server 3, the upper server 4, the external server, and the terminal device 5 is realized by a computer. The control unit includes a control arithmetic unit and a storage device. A processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) can be used as the control arithmetic unit. The control arithmetic unit reads a program stored in the storage device and performs a predetermined arithmetic processing according to the program. Further, the control arithmetic unit can write the arithmetic result to the storage device and read the information stored in the storage device according to the program.

(2) Detailed configuration (2-1) Search data generation unit The search data generation unit 11 is based on the product name data 41 and the accessory information data 42 to 44 corresponding to the product name, and the product name and the accessory information. Generates text information including the name of. As search data. In the search data, the product name and the attached information associated with the product name are registered as keywords.

Specifically, the search data generation unit 11 acquires the product name data 41 stored in the upper server 4 and the attached information data 42 to 44. The product name data is, for example, as shown in FIG. 2, a list of product names represented by at least one character of kanji, hiragana, and katakana. The attached information is information corresponding to the trade name, and includes, for example, at least one of the place of origin, size, calories, unit price, raw materials, additives, and allergies. In FIG. 1, search data is generated as ancillary information based on the production area name, size, and calorie data 42 to 44. The data 42 of the production area name as the attached information is a list of production area names expressed in Chinese characters, for example, as shown in FIG.

The product name data 41 and the attached information data 42 to 44 acquired by the search data generation unit 11 are transmitted to the furi-kana conversion engine 13 by the furi-kana conversion engine communication unit 12. The pretending pseudonym conversion engine 13 generates text information including the respective names of the product name and the attached information. Here, the pretending pseudonym conversion engine 13 converts all the titles of the characters of the transmitted product name data 41 and the attached information data 42 to 44 into hiragana. The search data generation unit 11 receives text information including the respective names of the product name and the attached information from the furi-kana conversion engine 13 by the furi-kana conversion engine communication unit 12.

The search data generation unit 11 that has acquired the text information generates the search data. The search data is data in which the product name in text format and the attached information are combined. Specifically, the combined data is data in which one hiragana of the product name and one hiragana of at least one attached information are combined. For example, the search data may be data in which one of the product names and one of the production area names are combined, or may be data in which one of the product names, one of the production area names, and one of the sizes are combined. Here, the search data is a list in which one hiragana of the product name and one hiragana of the attached information are combined. More specifically, the search data of FIG. 4 is the product name No. 2 shown in FIG. No. 1 and the production area name shown in FIG. 1-No. Each of the data is combined with 5.

(2-2) Furi Kana Conversion Engine Communication Unit As described above, the Furi Kana conversion engine communication unit 12 transmits the product name data 41 and the attached information data 42 to 44 to the Furi Kana conversion engine 13, and the Furi Kana conversion engine 13 Receive text information including the product name and the name of the attached information from. The pretending pseudonym conversion engine communication unit 12 of the present embodiment includes a transmission unit 12a and a reception unit 12b. The transmission unit 12a transmits the product name data 41 and the attached information data 42 to 44 acquired by the search data generation unit 11 to the pretending pseudonym conversion engine 13. The receiving unit 12b transmits the text information including the title of the product name and the attached information converted by the pretending pseudonym conversion engine 13 to the search data generation unit 11.

The Furi-Kana conversion engine communication unit 12 is a communication interface that enables mutual communication between the external server in which the Furi-Kana conversion engine 13 is stored and the voice recognition server 3. The pretending pseudonym conversion engine communication unit 12 transmits and receives to and from the pretending pseudonym conversion engine 13 via a public line such as the Internet or an intranet.

(2-3) Input unit The input unit 51 is for acquiring the utterance of the user's product. The input unit 51 of the present embodiment includes an input button 51a (see FIGS. 7 to 10) and a sound collecting member (not shown). The input button is a button displayed on the screen of the terminal device 5, a button attached to the terminal device 5, or the like, and is pressed (tapped) when the user utters a voice. The sound collecting member acquires vocalization. The sound collecting member is, for example, a microphone.

(2-4) Voice acquisition unit The voice acquisition unit 14 acquires the utterance of the user's product as a voice signal. The voice acquisition unit 14 of the present embodiment receives the utterance input to the input unit 51 as a voice signal.

The utterance of the user's product is related to the product name and attached information, and may include a part of speech other than a noun. When particles, verbs, etc. other than the product name and attached information are included in the utterance, the voice acquisition unit 14 acquires a voice signal extracted only from the product name and attached information, excluding particles and verbs unnecessary for the search. To do.

(2-5) Voice recognition engine communication unit The voice recognition engine communication unit 15 transmits a voice signal to the voice recognition engine to receive text information of the voice signal from the voice recognition engine. The voice recognition engine communication unit 15 of the present embodiment includes a transmission unit 15a and a reception unit 15b. The transmission unit 15a transmits the voice signal acquired by the voice acquisition unit 14 to the voice recognition engine 16. The voice recognition engine 16 converts the voice signal into text information. Here, the voice recognition engine 16 converts the voice signal into hiragana. The receiving unit 15b transmits the text information converted by the voice recognition engine 16 to the product information output unit 17.

The voice recognition engine communication unit 15 is a communication interface that enables mutual communication between the external server in which the voice recognition engine 16 is stored and the voice recognition server 3. The voice recognition engine communication unit 15 transmits and receives to and from the voice recognition engine 16 via a public line such as the Internet or an intranet.

(2-6) Product Information Output Unit The product information output unit 17 outputs product information corresponding to the user's voice based on the text information of the voice obtained from the voice signal and the search data. Here, the product information output unit 17 outputs information on one or a plurality of products corresponding to the utterance of the user.

Specifically, the product information output unit 17 acquires the text information of the utterance obtained from the voice signal from the voice acquisition unit 14 via the voice recognition engine communication unit 15. In addition, the product information output unit 17 acquires search data from the search data generation unit 11. Then, the product information output unit 17 searches the search data for product information corresponding to the product name and the attached information included in the utterance text information. More specifically, the product information output unit 17 extracts product information that matches the utterance text information from the search data. In this way, the product information output unit 17 outputs one or more search results.

When there is a plurality of product information corresponding to the user's utterance, the product information output unit 17 may output the information of the plurality of products in order.

(2-7) Display unit The display unit 52 displays product information corresponding to the user's utterance. Here, the display unit 52 receives the product information as the search result output from the product information output unit 17. The display unit 52 displays the received product information so that it can be visually recognized. When the product information output unit 17 outputs information on a plurality of products, the display unit 52 displays information on the plurality of products. The user can confirm the product information displayed on the display unit 52.

In this embodiment, the input unit 51 and the display unit 52 are provided in the terminal device 5. Therefore, the terminal device 5 receives the utterance of the user's product and displays the product information corresponding to the user's utterance. The label issuing device 2 issues a label based on the acquired product information.

The display unit 52 of the present embodiment displays an input button 51a and a narrowing-down button 53a (see FIGS. 7 to 10) described later.

(2-8) Narrowing down unit When the product information output unit 17 outputs information on a plurality of products corresponding to the user's utterance, the narrowing down unit 53 narrows down the product information from the information on the plurality of products. Do. The narrowing-down unit 53 includes a narrowing-down button 53a (see FIGS. 7 to 10) for further searching by utterances related to products, and a selection unit 53b (FIG. 10) for selecting one from information on a plurality of products displayed on the display unit. See) and includes.

The narrowing section 53 further includes a sound collecting member. Here, the sound collecting member is common to the sound collecting member of the input unit 51.

(3) Product Information Search Method Next, a product information search method will be described with reference to FIGS. 1 to 10.

(3-1) Search Data Generation Method The search data generation unit 11 includes the product name and the name of the accessory information from the product name data 41 and the accessory information data 42 to 44 corresponding to the product name. Generate text information as search data.

Specifically, as shown in FIG. 5, the search data generation unit 11 acquires the product name data 41 as shown in FIG. 2 and the incidental information data 42 to 44 as shown in FIG. 3 (step). S1).

Next, text information including the respective titles of the product name data 41 and the attached information data 42 to 44 is generated (step S2). Here, the search data generation unit 11 transmits the product name data 41 and the attached information data 42 to 44 to the Furi Kana conversion engine 13 by the Furi Kana conversion engine communication unit 12, and the Furi Kana conversion engine 13 sends the product name and the product name and the attached information data 42 to 44. Receive text information including the name of the attached information.

Next, text information including the product name and the name of the attached information is generated as search data (step S3). Here, the search data generation unit 11 that has acquired the text information of the product name and the attached information combines the product name and the attached information in the text format to generate the search data as shown in FIG.

(3-2) Search Method As shown in FIG. 6, the user first installs the application on the terminal device 5 (step S11). The application receives the utterance of the user's product and displays the product information corresponding to the user's utterance. 7 to 10 show a screen (display unit 52) of the terminal device 5 in which the application is installed.

Next, the user makes a voice regarding the product (step S12). In step S12, the utterance is input to the input unit 51.

Specifically, the user presses the input button 51a displayed on the terminal device 5 shown in FIG. 7. When the input button 51a is pressed, the color of the input button 51a changes and the sound collecting member is turned on. When the color of the input button 51a changes, the user utters about the product. When the user utters "Onagawa-san's saury", as shown in FIG. 8, the search word "Akitou from Onagawa" is displayed on the screen of the terminal device 5. The input unit 51 determines from the tone of the user's utterance that the utterance has ended.

Next, the voice acquisition unit 14 acquires the utterance of the user's product as a voice signal (step S13). In step S13, the input unit 51 transmits the utterance as a voice signal to the voice acquisition unit 14. Here, the voice acquisition unit 14 transmits the voice signal to the voice recognition engine 16 by the voice recognition engine communication unit 15, and receives the text information of the voice signal from the voice recognition engine 16.

When step S13 is executed, as shown in FIG. 9, "Product search ..." is displayed on the screen of the terminal device 5.

Next, the product information output unit 17 outputs product information corresponding to the user's utterance based on the utterance text information obtained from the voice signal and the search data (step S14). In step S14, the search data generated by the search data generation unit 11 in steps S1 to S3 is used.

Specifically, the product information output unit 17 has "Onagawa-san" and "pacific saury" excluding the particle "no" from "Onagawa-san's pacific saury" as the text information of the utterance. Search for information in the list of search data. In the search data of FIG. 4, No. which matches the text information of the utterance. 2 is extracted. Therefore, the product information output unit 17 causes the No. Information on 2 products is output.

The product information output by the product information output unit 17 is displayed on the display unit 52 of the terminal device 5. Specifically, as shown in FIG. 10, on the screen of the terminal device 5, "Pacific saury from Onagawa" is displayed as a search result.

Next, it is determined whether or not narrowing down is necessary from the output product information (step S15). In FIG. 10, since the output product information is one, it is determined that it is not necessary to narrow down the product information. As a result, the user can obtain information on the product corresponding to the utterance (step S16).

On the other hand, when there are a plurality of output product information, the plurality of output product information is displayed in the search result column of FIG. 10, and it is determined that it is necessary to narrow down the product information in step S15. In this case, the user narrows down the information of a plurality of products. The user may select from the information of a plurality of products, or may further search by utterance about the product (step S17).

In detail, when the information corresponding to the utterance can be easily selected from the information of a plurality of products displayed on the display unit 52, it is displayed in the search result column (selection unit 53b of the narrowing unit 53) of FIG. Press one from the information of a plurality of products. As a result, since further narrowing down is not necessary, the user can obtain information on the product corresponding to the utterance.

Since there is a lot of information on a plurality of products displayed on the display unit 52, if it cannot be easily selected, it can be further searched by vocalization. In this case, the narrowing button 53a on the screen of the terminal device 5 of FIG. 10 is pressed (step S17). When the narrowing down button 53a is pressed, the color of the narrowing down button 53a changes and the sound collecting member is turned on. When the color of the narrow-down button 53a changes, the user makes a voice regarding the product (step S12). After this step (step S17), the above-mentioned steps (steps S12 to S17) are repeated.

Specifically, when the user makes a voice regarding the product (step S12), the step of acquiring the above-mentioned audio signal (step S13) is performed. Next, the step of outputting the above-mentioned product information (step S14) is carried out, and in this step S14, the information of the extracted products is further extracted. Next, it is determined from the search results whether or not narrowing down (step S15) is necessary.

By carrying out the above steps (steps S1 to S3, S11 to S17), product information of food can be extracted.

(4) Features (4-1)
The product information search system 1 of the present embodiment is a search system that extracts product information of food products. The product information search system 1 includes a search data generation unit 11, a voice acquisition unit 14, and a product information output unit 17. The search data generation unit 11 generates text information including the product name and the name of the accessory information as search data from the product name data 4 and the accessory information data 42 to 44 corresponding to the product name. The voice acquisition unit 14 acquires the utterance of the user's product as a voice signal. The product information output unit 17 outputs product information corresponding to the user's utterance based on the utterance text information obtained from the audio signal and the search data.

In the product information search system 1 of the present embodiment, the search data generation unit 11 generates text information including the product name and the name of the attached information as search data. The product information output unit 17 can output product information corresponding to the user's utterance based on the generated search data and the utterance text information obtained from the voice signal acquired by the voice acquisition unit. Therefore, the user can search for product information by uttering the product name and attached information without specifying the product extraction method. Therefore, it is possible to improve the efficiency of searching for product information.

Further, since the user can utter both the product name and the attached information at the same time, the hit rate at the time of searching can be improved.

Further, the product information output unit 17 does not search the data of the product name as shown in FIG. 2 and the data of the attached information as shown in FIG. 3, but searches the search data. Therefore, even if the product name data is changed or the attached information is changed, the search data generation unit 11 can create the search data based on the product name data and the attached information data. You can search without adding new triggers. Therefore, the product information search system 1 of the present embodiment is highly convenient because it is easy to respond to changes in the product name and attached information.

(4-2)
The product information output unit 17 of the present embodiment obtains utterance text information obtained from an audio signal. Specifically, the voice recognition engine communication unit 15 transmits a voice signal to the voice recognition engine 16 and receives text information of the voice signal from the voice recognition engine 16.

By using the voice recognition engine 16, it is possible to easily obtain the text information of the utterance obtained from the voice signal.

(4-3)
The search data generation unit 11 of the present embodiment uses text information including the product name and the name of the accessory information as search data from the product name data 41 and the accessory information data 42 to 44 corresponding to the product name. Generate. Specifically, the Furi-Kana conversion engine communication unit 12 transmits the product name data and the attached information data to the Furi-Kana conversion engine 13, and receives the text information including the product name and the name of the attached information from the Furi-Kana conversion engine 13. To do.

By using the pretending pseudonym conversion engine 13, text information including the title of the product name and the attached information can be easily obtained from the product name data 41 and the attached information data 42 to 44.

(5) Modification Example The following is a modification of the above embodiment. In addition, a part or all of the contents of each modification may be combined with the contents of the said embodiment and the contents of other modifications to the extent that they do not contradict each other.

(5-1) Modification A
In the above embodiment, the product name data 41 is a list of product names represented by at least one character of kanji, hiragana, and katakana, and the attached information data 42 is a list of production areas represented by kanji. I mentioned and explained in. In the product name data 41 and the attached information data 42, the product name and the attached information can be represented by arbitrary characters such as kanji, hiragana, katakana, alphabets, and numbers.

Further, in the above embodiment, as the text information including the respective titles of the product name and the attached information, the respective titles of the product name data and the attached information data are all represented by hiragana. In this modification, the search data generation unit 11 generates text information in which all the names of the product name data and the attached information data are represented by alphabets as search data.

(5-2) Modification B
In the above embodiment, the voice acquisition unit 14 receives the utterance of the user's product input to the terminal device 5 as a voice signal, the voice acquisition unit 14 transmits the voice signal to the voice recognition engine 16, and the voice recognition engine 16 transmits the voice signal. The product information output unit 17 receives the converted voice text information. In this modification, as shown in FIG. 11, the utterance of the user's product input to the terminal device 5 is transmitted to the voice recognition engine 16 as a voice signal, and the text information of the utterance converted by the voice recognition engine 16 is voiced. The acquisition unit 14 is receiving. Then, the voice acquisition unit 14 transmits the uttered text information to the product information output unit 17.

Further, in this modification, the voice recognition engine communication unit 15 transmits a voice signal from the input unit 51 or the narrowing unit 53 to the voice recognition engine 16, and the voice recognition engine 16 transmits the text information of the voice signal to the voice acquisition unit 14. Receives.

(5-3) Modification C
In the above embodiment, the search data generation unit 11 receives the product name data 41 and the attached information data 42 to 44 stored in the upper server 4, and the search data generation unit 11 sends the product to the pretending pseudonym conversion engine 13. The name data 41 and the attached information data 42 to 44 are transmitted, and the search data generation unit 11 receives the text information converted by the pretending pseudonym conversion engine 13. In this modification, as shown in FIG. 12, the pretending pseudonym conversion engine 13 receives the product name data 41 and the attached information data 42 to 44 stored in the upper server 4, and the text is converted by the pretending pseudonym conversion engine 13. The information is transmitted to the search data generation unit 11.

Further, in this modification, the Furi-Kana conversion engine communication unit 12 transmits the product name data and the attached information data stored in the upper server 4 to the Furi-Kana conversion engine 13, and the Furi-Kana conversion engine 13 sends the product name and attachments. The search data generation unit 11 receives the text information including the name of the information.

(5-4) Modification D
In the above embodiment, an example in which the application is installed in the terminal device 5 and the terminal device 5 is provided with an input unit 51 for inputting a user's utterance has been described. In this modification, the label issuing device 2 is provided with an input unit 51 in which an application is installed and a user's utterance is input.

Further, in the above embodiment, an example in which the terminal device is provided with the display unit 52 and the narrowing unit 53 has been described. In this modification, the label issuing device 2 is provided with a display unit 52 and a narrowing unit 53. Therefore, in this modification, the terminal device 5 is omitted.

(5-5) Modification E
In the above embodiment, the product information retrieval system 1 does not include the pretending pseudonym conversion engine 13 and the voice recognition engine 16. In this modification, the product information retrieval system further includes a pretending pseudonym conversion engine 13 and a voice recognition engine 16.

1: Product information search system 2: Label issuing device 3: Voice recognition server 4: Upper server 5: Terminal device 11: Search data generation unit 12: Kana conversion engine communication unit 13: Kana conversion engine 14: Voice acquisition unit 15: Voice recognition engine Communication unit 16: Voice recognition engine 17: Product information output unit 51: Input unit 52: Display unit 53: Narrowing unit

JP-A-2018-130860

Claims (7)

A search system that extracts product information of food products.
A search data generation unit that generates text information including the product name and the name of the accessory information as search data from the product name data and the data of the accessory information corresponding to the product name.
A voice acquisition unit that acquires the utterance of the user's product as a voice signal,
A product information output unit that outputs product information corresponding to the user's utterance based on the utterance text information obtained from the voice signal and the search data.
To prepare
Product information search system. A voice recognition engine communication unit that transmits the voice signal to the voice recognition engine and receives text information of the voice signal from the voice recognition engine is further provided.
The product information search system according to claim 1. It further includes a pretending pseudonym conversion engine communication unit that transmits the data of the product name and the data of the attached information to the pretending pseudonym conversion engine and receives text information including the name of the product name and the ancillary information from the pretending pseudonym conversion engine. ,
The product information search system according to claim 1 or 2. The annex includes at least one of origin, size, calories, unit price, raw materials, additives, and allergies.
The product information search system according to any one of claims 1 to 3. The product information output unit outputs information on a plurality of products corresponding to the user's utterance.
The product information search system according to any one of claims 1 to 4. Further provided with a narrowing section for narrowing down from the information of the plurality of products.
The product information search system according to claim 5. The search data generation unit, the voice acquisition unit, and the product information output unit are stored in the voice recognition server.
The product information search system according to any one of claims 1 to 6.

Images