JP2018026022A - Residual quantity determination system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a residual quantity determination system capable of reducing the burden of a user.SOLUTION: The residual quantity determination system includes: a voice acquisition device 10 for acquiring voice; a voice recognition unit 110 for recognizing the acquired voice as character information; a criterion data storage unit 120 for storing criterion data in which a predetermined keyword is associated with the residual quantity level for gradually indicating the residual quantity of an article; and a control unit 130 that extracts the predetermined keyword from the character information recognized by the voice recognition unit 110, and collates the extracted predetermined keyword with the criterion data, thereby determining the residual quantity level of the article.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technology of a remaining amount determination system for articles.

  Conventionally, the technology of the remaining amount determination system for articles has been publicly known. For example, as described in Patent Document 1.

  Patent Document 1 describes an inventory information management device that detects and manages the amount of inventory (remaining amount) of food and daily necessities stored in a refrigerator or storage shelf at home. Patent Document 1 describes that the inventory information management device includes a voice recognition unit such as a microphone, and can receive an input of an inventory amount of an article by voice.

  However, in the technique described in Patent Document 1, the user needs to grasp the accurate inventory amount of the article and consciously input the voice, which causes a problem that the burden on the user is large. there were.

JP2013-250698A

  The present invention has been made in view of the above situation, and a problem to be solved is to provide a remaining amount determination system capable of reducing the burden on the user.

  The problem to be solved by the present invention is as described above. Next, means for solving the problem will be described.

  That is, in claim 1, a voice acquisition unit that acquires voice, a voice recognition unit that recognizes the acquired voice as character information, a remaining amount level that indicates a predetermined keyword and the remaining amount of articles in stages A criterion data storage unit for storing criterion data associated with each other, and extracting the predetermined keyword from the character information recognized by the voice recognition unit, and extracting the predetermined keyword and the criterion data And a remaining amount determining unit that determines the remaining amount level of the article.

  In Claim 2, it has a notification part which can notify a user of the necessity of replenishment of goods, and the above-mentioned notification part performs notice according to the remaining amount level judged by the remaining amount judging part It is.

  In Claim 3, the personal identification part which identifies the individual who uttered the acquired said sound was comprised, and the said residual amount determination part was extracted based on the identification result of the said personal identification part. The remaining amount level is determined using a voice uttered by an individual.

  In Claim 4, the personal identification part which identifies the individual who uttered the acquired voice is provided, and the predetermined keyword and the remaining amount level are associated with each other in the determination reference data. The remaining amount determination unit extracts the determination reference data of the individual identified by the personal identification unit, and determines the remaining amount level using the extracted determination reference data.

  In Claim 5, the image acquisition part which acquires the image of articles | goods, The number of articles | goods is determined based on the acquired said image, The said number determined by the said number of articles | goods and the said remaining amount determination part An inventory management unit that stores the remaining level of the article in association with each other.

  According to a sixth aspect of the present invention, the apparatus includes a replenishment history data acquisition unit that acquires a replenishment history of the article, and a prediction unit that predicts a time when the remaining amount of the article is equal to or less than a threshold based on the acquired replenishment history. Is.

  As effects of the present invention, the following effects can be obtained.

  In claim 1, the burden on the user can be reduced.

  According to the second aspect, the user can grasp the standard of the time when the article needs to be replenished.

  In claim 3, the sound for determining the remaining amount level can be limited to the sound of a specific person.

  According to the fourth aspect of the present invention, it is possible to determine the remaining amount level of the article in consideration of the difference in how to interpret the remaining amount of the person, so that the accuracy of determination of the remaining amount level can be improved.

  According to the fifth aspect of the present invention, it is possible to accurately manage the inventory of articles by grasping both the number of articles and the remaining level.

  According to the sixth aspect of the present invention, it is possible to automatically predict when the article needs to be replenished.

The figure which shows the structure of the residual amount determination system which concerns on one Embodiment of this invention. The figure which shows the determination reference | standard data table of the residual amount determination system which concerns on one Embodiment of this invention. The flowchart which shows control of the residual amount determination system which concerns on one Embodiment of this invention. The figure which shows another example of a structure of the residual amount determination system which concerns on one Embodiment of this invention. The figure which shows the structure of the residual amount determination system which concerns on 2nd embodiment of this invention. The flowchart which shows control of the residual amount determination system which concerns on 2nd embodiment of this invention. The flowchart which shows control of the residual amount determination system which concerns on 3rd embodiment of this invention. (A) The figure which shows the determination reference | standard data table for mothers of the residual amount determination system which concerns on 3rd embodiment of this invention. (B) The figure which similarly shows the criteria reference data table for fathers. (C) The figure which similarly shows the criterion reference data table for children. The figure which shows the structure of the residual amount determination system which concerns on 4th embodiment of this invention. The flowchart which shows control of the residual amount determination system which concerns on 4th embodiment of this invention.

  First, the outline | summary of a structure of the residual amount determination system 1 which concerns on one Embodiment of this invention is demonstrated using FIG.

  The remaining amount determination system 1 is a system for determining the remaining amount of articles. The remaining amount determination system 1 is mainly used at home. In addition, in this embodiment and the second embodiment to the fourth embodiment, which will be described later, a home composed of a father, a mother, and a child is assumed. It is assumed that the person is a person who uses the determination result. “Articles” include regular items consumed in daily life, such as foods such as milk and eggs, seasonings, and daily necessaries such as toilet paper and detergents. Further, the remaining amount determination system 1 notifies the user that the item needs to be replenished based on the determination result of the remaining amount of the item. The remaining amount determination system 1 includes a voice acquisition device 10, a user terminal 20, and a server 100.

  The voice acquisition device 10 acquires voice. For example, a microphone is used as the sound acquisition device 10. The voice acquisition device 10 is arranged at a position where a family conversation or monologue voice can be acquired, for example, in the vicinity of a refrigerator or a storage shelf. The number of audio acquisition devices 10 may be one or plural.

  The user terminal 20 is a terminal used by a user of the remaining amount determination system 1. As the user terminal 20, a terminal capable of transmitting and receiving data is used. For example, a personal computer or a high-function mobile phone terminal is used.

  The server 100 performs data storage and analysis. The server 100 includes a voice recognition unit 110, a criterion data storage unit 120, a control unit 130, and a notification unit 140.

  The voice recognition unit 110 recognizes the voice acquired by the voice acquisition device 10 as character information. The voice recognition unit 110 converts the voice acquired by the voice acquisition device 10 into text using a voice recognition function. Thereby, the voice acquisition device 10 creates character information of the voice acquired by the voice acquisition device 10. Hereinafter, the character information of the voice acquired by the voice acquisition device 10 may be referred to as “voice text”.

  The determination reference data storage unit 120 stores determination reference data serving as a reference for determining the remaining amount of articles. The determination reference data includes a predetermined keyword and a remaining amount level, and both are associated with each other. Here, the predetermined keyword refers to a predetermined phrase that is a key for estimating the remaining amount of the article. The predetermined keyword can include various phrases related to the remaining amount of the article. The remaining amount level indicates the remaining amount of the article in stages. The remaining amount level is divided into a plurality of stages (levels) according to the remaining amount of articles (necessity of replenishment).

  FIG. 2 is a diagram illustrating a determination criterion data table that defines determination criterion data. In the determination reference data table, the remaining amount level and a predetermined keyword are associated and stored. The remaining amount level is divided into “sufficient level”, “allowable level”, and “necessary level”. The “sufficient level” indicates that the remaining amount is large and does not need to be replenished yet. The “acceptable level” indicates that the remaining amount is low and needs to be replenished soon. “Necessary level” indicates that the remaining amount is 0 and needs to be replenished immediately. A keyword associated with a sufficient level is not particularly defined. The keywords linked to the acceptable level include words such as “still a little”, “a little more”, and “a little”. The keywords linked to the required level include words such as “no longer”, “lost”, “must buy”.

  The control unit 130 controls the server 100. In particular, the control unit 130 determines the remaining amount (remaining amount level) of the article. The control unit 130 determines the remaining level of the article based on the character information (voice text) created by the voice recognition unit 110 and the determination reference data stored in the determination reference data storage unit 120.

  Specifically, the control unit 130 extracts a keyword related to the remaining amount from the voice text created by the voice recognition unit 110. Then, the control unit 130 refers to the determination criterion data table of the determination criterion data storage unit 120 (checks the extracted keyword with the determination criterion data) and selects a predetermined keyword that matches the extracted keyword. Then, the control unit 130 determines the remaining level based on the remaining level associated with the selected keyword.

  Further, the control unit 130 determines the target article (which article the determined remaining level is for) based on the voice text created by the voice recognition unit 110. Specifically, the control unit 130 extracts words related to the article from the voice text created by the voice recognition unit 110 (particularly, portions before and after the keyword related to the remaining amount), and refers to predetermined data. Determine the article.

  The notification unit 140 notifies the user of the necessity of replenishment of articles. The notification unit 140 performs notification to the user terminal 20 based on control by the control unit 130. The notification unit 140 executes notification according to the remaining amount level determined by the control unit 130. Specifically, the notification unit 140 does not perform notification when the determination result (remaining level) is “sufficient level”. When the determination result is “acceptable level”, the notification unit 140 notifies that it is necessary to replenish (a notification such as “Soon, XX is about to expire, so let's buy it next time.”) I do. In addition, when the determination result is “necessary level”, the notification unit 140 notifies that it is necessary to replenish immediately (notification such as “XX is out. Let's go shopping”) I do.

  Hereinafter, the control of the remaining amount determination system 1 will be described with reference to FIG.

  In step S10, the voice acquisition device 10 acquires voice. In this step, the voice acquisition device 10 acquires a family conversation or a monologue voice. Examples of the voice acquired by the voice acquisition device 10 include voices such as “Soy sauce is gone”, “I have a little more eggs”, “I have no milk”. Here, it is assumed that the voice acquisition device 10 has acquired a voice “No more milk”.

  In step S11, the voice recognition unit 110 performs voice recognition. In this step, the voice recognition unit 110 converts the voice “no more milk” acquired by the voice acquisition device 10 into text, and creates a voice text.

  In step S12, the control unit 130 determines the remaining amount level of the article. In this step, the control unit 130 determines the remaining level of the article using the voice text created by the voice recognition unit 110 and the determination reference data table stored in the determination reference data storage unit 120.

  Specifically, the control unit 130 extracts a keyword related to the remaining amount from the voice text created by the voice recognition unit 110 based on a predetermined keyword defined in the determination criterion data table. Here, the control unit 130 refers to the determination criterion data table, and extracts the word “no more” as a keyword related to the remaining amount from the voice text “no more milk”. Further, the control unit 130 determines that the target article is milk based on the voice text “No more milk”.

  And the control part 130 extracts the residual amount level linked | related with the extracted keyword by collating the extracted keyword and determination criteria data. Specifically, the control unit 130 refers to the determination criterion data table and determines that the remaining amount level is “necessary level” from the remaining amount level associated with the keyword “no more”.

  In step S <b> 13, the control unit 130 notifies the user of the necessity of purchasing (replenishing) the article via the notification unit 140. Specifically, control unit 130 transmits to notification unit 140 a notification signal for executing a notification corresponding to the remaining amount level determined in step S12. Here, since the remaining amount level determined in step S <b> 12 is “necessary level”, the control unit 130 transmits a notification signal to the notification unit 140 for executing a notification that replenishment is required immediately. . In the notification unit 140, a message is stored in advance according to each remaining level. When the predetermined time comes, the notification unit 140 transmits a message “milk has run out. Let's go shopping” to the user terminal 20 based on the notification signal supplied from the control unit 130. . The time at which the message is transmitted can be set to an appropriate time, for example, the time when the user normally leaves the house or the time when the user normally shop.

  Thus, in the remaining amount determination system 1 according to the present embodiment, the remaining amount (remaining level) of the article is automatically determined. Therefore, the user can save the trouble of managing the remaining amount of the article. In addition, since a notification corresponding to the remaining amount level is made to the user, the user needs to purchase (supplement) the item immediately or needs to purchase it at the next shopping, etc. It is possible to grasp the time when the purchase of goods is necessary.

  Further, in the remaining amount determination system 1, since the remaining amount level of the article can be determined from conversations or monologues in daily life, it is not necessary to intentionally input the remaining amount. Therefore, it is possible to reduce time and effort for inputting the remaining amount, thereby reducing the burden on the user.

  Further, in the remaining amount determination system 1 according to the present embodiment, a voice (for example, a conversation between a father and a child, a father, etc.) produced by a family other than the user while the user (mother in the present embodiment) is out, for example. Alternatively, the remaining amount can be determined from a child's monologue. Therefore, even when the user does not recognize that the remaining amount of a certain article is low or zero, it is possible to know that fact.

  Further, in the remaining amount determination system 1 according to the present embodiment, the remaining amount determination can also be performed from a voice uttered by the user himself (mother). Even if the user once confirms that the remaining amount of an article (food) is low (or zero) when the refrigerator is opened, forget it when time passes. It tends to end up. However, in the remaining amount determination system 1, forgetting to buy is prevented if a setting is made so that notification regarding the purchase of goods is made at a predetermined time (for example, the time of leaving home or the time of usual shopping). can do.

As described above, the remaining amount determination system 1 according to the present embodiment includes a voice acquisition device 10 (voice acquisition unit) that acquires voice, a voice recognition unit 110 that recognizes the acquired voice as character information, and a predetermined amount. A determination criterion data storage unit 120 that stores determination criterion data in which a keyword and a remaining amount level indicating the remaining amount of articles are linked to each other, and the character information recognized by the voice recognition unit 110 from the character information And a control unit 130 (remaining amount determining unit) that determines the remaining amount level of the article by comparing the extracted predetermined keyword with the determination criterion data. .
With this configuration, the burden on the user can be reduced.

In addition, the remaining amount determination system 1 according to the present embodiment includes a notification unit 140 that can notify a user of the necessity of replenishment of an article, and the notification unit 140 determines the remaining amount determined by the control unit 130. Notification is made according to the quantity level.
By configuring in this way, the user can grasp an indication of when the item needs to be replenished.

In addition, the audio | voice acquisition apparatus 10 which concerns on this embodiment is one Embodiment of an audio | voice acquisition part.
In addition, the control unit 130 according to the present embodiment is an embodiment of a remaining amount determination unit.

  The embodiment of the present invention has been described above, but the present invention is not limited to the above-described configuration, and various modifications can be made within the scope of the invention described in the claims.

  For example, in the present embodiment, the notification unit 140 notifies the user terminal 20 of a message. However, the notification form is not limited to this, and shopping on which articles that need to be purchased are placed. You may make it notify a list. In addition, when the remaining amount determination system 1 cooperates with, for example, a general mail order application, the notification unit 140 displays a product order screen on which items that need to be purchased are displayed together with a message (or instead of a message) on the use terminal 20. You can also. With such a configuration, the user can purchase the necessary goods using the product order screen displayed on the use terminal 20, so that the user purchases the necessary goods at an appropriate timing without forgetting to buy the goods. be able to.

  In the present embodiment, the notification unit 140 notifies the user terminal 20 at a predetermined time. However, the notification form is not limited to this, and the notification content is predetermined. It may be uploaded to a location so that the user can access it when needed.

  Further, the keywords of the determination criterion data are not limited to those described in the determination criterion data table shown in FIG. 2, and other various words can be included. In addition, keywords may be added and modified based on the speech text history created by the speech recognition unit 110. In addition, the determination criterion data storage unit 120 may be able to add and modify keywords in conjunction with the remaining amount determination system 1 used in other homes. Moreover, the remaining amount determination system 1 according to the present embodiment may include a learning function, and may perform correction when there is a difference between the keyword and the actual remaining amount.

  In the present embodiment, the remaining level of the determination reference data is set to three levels. However, the number of levels of the remaining level is not limited to this, and may be an appropriate number. Also, the criteria for the remaining level classification can be set appropriately.

  Further, in the present embodiment, the remaining amount determination system 1 is used at home, but the form of use is not limited to this and is used in various places (for example, hotels and restaurants). Is possible.

  Further, for example, when an article is unclear because a pronoun such as “that” or “this” is used (spoken), the user may input the article name into the remaining amount determination system 1. Further, for example, the control unit 130 may have a natural language understanding function, and the control unit 130 may determine an article pointed to by the pronoun based on the intention of the conversation. According to such a configuration, it is possible to determine the remaining level of the article pointed to by the pronoun without the user consciously inputting the article name.

  In the present embodiment, the remaining amount is determined from the voice of a family conversation or the like. Of course, the user may consciously input the remaining amount toward the voice acquisition device 10.

  As shown in FIG. 4, the remaining amount determination system 1 may further include a purchase history data acquisition unit 150 as an aid for determination by voice recognition. The purchase history data acquisition unit 150 acquires and accumulates purchase history data (data indicating the purchase date history of goods) input via the user terminal 20 or the like. Then, the control unit 130 calculates the number of days from the purchase date to the next purchase date based on the purchase history data. The control unit 130 averages the calculated number of days, thereby predicting a date (planned purchase date) when the remaining amount of the article is equal to or less than the threshold (for example, 0). Thereby, even when the determination by voice recognition is not made (for example, when the conversation about the remaining amount of the article is not made), it is possible to know the day when the purchase is necessary. Note that the purchase history data may include the amount of purchase of the article (purchase amount), and the purchase date may be predicted in consideration of the purchase amount.

  Further, purchase history data may be acquired and accumulated by utilizing user attributes (number of family members, region, income, etc.). Specifically, matching with other users with similar attributes may be performed, and the purchase history data of the matched users may be used for the prediction of the purchase date. Thereby, it is possible to improve the accuracy of prediction, or it is possible to predict the purchase date even when the initial data is not collected.

  In addition, the RFID tag is used together to count the number of times the article is taken out (use count) from the article management space (storage space where the tag reader is installed), and the purchase date is predicted in consideration of this use count. May be. Specifically, in addition to the purchase date data, the data on the number of times of use in the purchase day may be accumulated, and the planned purchase date may be predicted based on the accumulated data on the purchase date and the number of times of use. Thereby, it is possible to predict the purchase date more accurately.

As described above, the remaining amount determination system 1 according to the present embodiment is based on the purchase history data acquisition unit 150 (replenishment history data acquisition unit) that acquires the purchase history (replenishment history) of an article, and the acquired purchase history. And a control unit 130 (prediction unit) that predicts a time when the remaining amount of the article is equal to or less than a threshold value.
By configuring in this way, it is possible to automatically predict when the purchase (replenishment) of the article is necessary, so that it can be more useful to the user.

  Next, the outline of the configuration of the remaining amount determination system 2 according to the second embodiment of the present invention will be described with reference to FIG.

  The main difference between the remaining amount determination system 2 according to the second embodiment and the remaining amount determination system 1 according to the first embodiment is that a server 200 is provided instead of the server 100. In addition, the main point that the server 200 according to the second embodiment differs from the server 100 according to the first embodiment is that the server 200 according to the first embodiment further includes a personal identification unit 210. Therefore, below, the same code | symbol is attached | subjected about the structure same as the residual amount determination system 1 which concerns on 1st embodiment among the residual amount determination systems 2 which concern on 2nd embodiment, and description is abbreviate | omitted.

  As illustrated in FIG. 5, the remaining amount determination system 2 according to the second embodiment includes a voice acquisition device 10, a user terminal 20, and a server 200. The server 200 includes a personal identification unit 210 in addition to the voice recognition unit 110, the criterion data storage unit 120, the control unit 130, and the notification unit 140.

  The personal identification unit 210 identifies an individual who has uttered the voice acquired by the voice acquisition device 10. The personal identification unit 210 uses the speaker recognition function to identify who the voice acquired by the voice acquisition device 10 is.

  Next, with reference to FIG. 6, control of the remaining amount determination system 2 according to the second embodiment of the present invention will be described.

  In step S20, the voice acquisition device 10 acquires voice (similar to step S10 of the first embodiment). Here, it is assumed that the voice acquisition device 10 has acquired the voice “there is no milk” spoken by the father and the voice “there is still a little milk” spoken by the child.

  In step S21, the voice recognition unit 110 performs voice recognition (similar to step S11 in the first embodiment). In this step, the voice recognition unit 110 converts the voice of “no more milk” and the voice of “milk is still a little” acquired by the voice acquisition device 10 into texts, respectively.

  In step S <b> 22, the personal identification unit 210 identifies an individual who has emitted the voice acquired by the voice acquisition device 10. In this step, the personal identification unit 210 is a voice produced by the father that “no more milk” acquired by the voice acquisition device 10 by the speaker recognition function, and “there is still a little milk”. It is recognized that the voice of is uttered by the child.

  In step S23, the control unit 130 extracts speech text based on the identification result in step S22. In this step, the control unit 130 extracts speech text of speech uttered by one or more specific individuals from the speech text created by the speech recognition unit 110. Here, it is assumed that the control unit 130 is set to extract the voice texts of the father and mother and not to extract the voice texts of the child. The control unit 130 extracts the father's voice text “No more milk”.

  In step S24, the control unit 130 determines the remaining level of the article using the voice text extracted in step S23. In this step, the control unit 130 determines the remaining level of the article using the father's voice text and the determination criterion data table stored in the determination criterion data storage unit 120. As in step S12 of the first embodiment, the control unit 130 refers to the determination criterion data table, and the remaining amount level is “necessary level” from the remaining amount level associated with the keyword “no more”. Judge that there is.

  In step S25, the control unit 130 notifies the user of the necessity of replenishment of articles via the notification unit 140 (similar to step S13 in the first embodiment). The notification unit 140 transmits a message to the user terminal 20 informing that it is necessary to purchase milk immediately at a predetermined time.

  As described above, in the second embodiment, since the remaining amount level is determined using the voice text of the voice uttered by a specific individual, the reliability of the remaining amount level determination can be improved. Specifically, in the second embodiment, only the father's (and mother's) voice is used as the determination material, and the child's voice is excluded from the determination material. It is possible to prevent a wrong determination from being made when the amount is stated. Moreover, it is possible to prevent erroneous determination even when the remaining amount cannot be accurately understood because the child is still young.

As described above, the remaining amount determination system 2 according to the second embodiment includes the personal identification unit 210 that identifies the individual who has obtained the acquired voice, and the control unit 130 identifies the personal identification unit 210. The remaining amount level is determined by using voices uttered by one or more specific individuals extracted based on the result.
With this configuration, it is possible to limit the sound for determining the remaining level to the sound of a specific person. Thereby, the reliability of determination of a remaining amount level can be improved.

  Next, control of the remaining amount determination system 2 according to the third embodiment of the present invention will be described with reference to FIGS. 7 and 8. The configuration of the remaining amount determination system 2 according to the third embodiment is the same as that of the second embodiment. Further, the control of the remaining amount determination system 2 according to the third embodiment is configured by S30 to S35 shown in FIG. 7, but steps S30 to S32 and S35 are respectively steps S20 to S22 and S22 of the second embodiment. Since the content is the same as S25, the description thereof is omitted here.

  In step S33, the control unit 130 extracts the determination criterion data table for the individual identified in step S32.

  As shown in FIG. 8, in the third embodiment, the determination criterion data storage unit 120 has a determination criterion data table for each individual. In each determination reference data table, the association between the remaining amount level and the predetermined keyword is different. For example, in the father criterion data table, the remaining level associated with the keyword “Buy it” is “necessary level” (see FIG. 8B). On the other hand, in the child criterion data table, the remaining level associated with the keyword “Buy it” is “allowable level” (see FIG. 8C).

  In addition, the specified keywords are different in each criterion data table. For example, the keyword “must go shopping” is included in the determination criterion data table for mothers, but is not included in the determination criterion data table for fathers and the determination criterion data table for children. On the other hand, the keyword “I bought it” is included in the determination criterion data table for father and the determination criterion data table for child, but is not included in the determination criterion data table for mother.

  For example, when the voice text is that of the mother, the control unit 130 extracts the determination criterion data table for the mother.

  In step S34, the control unit 130 determines the remaining level of the article using the determination criterion data table extracted in step S33. In this step, the control unit 130 determines the remaining level of the article using the voice text created by the voice recognition unit 110 and the extracted determination criterion data table.

  As described above, in the third embodiment, the remaining amount level is determined using the determination reference data table prepared for each individual and having different associations between the remaining amount level and the keyword. For example, with regard to the word “please buy”, the father says when the remaining amount becomes 0, the child says after the remaining amount is halved, etc., there are various ways of understanding the remaining amount depending on the person. In the third embodiment, since the remaining level of an article can be determined in consideration of such a difference in how it is perceived with respect to the remaining amount of a person, the accuracy of determination of the remaining amount level can be improved.

  In the third embodiment, the specified keywords differ for each determination criterion data table. Therefore, it is possible to specify keywords that take into account the individual phrases and keywords that correspond to roles at home. Therefore, the leakage of keywords related to the remaining amount can be reduced.

As described above, the remaining amount determination system 2 according to the third embodiment includes the personal identification unit 210 that identifies the individual who has obtained the acquired voice, and the determination criterion data includes the predetermined keyword and the remaining keyword. A quantity level is associated with each individual, and the control unit 130 extracts the determination criterion data of the individual identified by the individual identification unit 210 and uses the extracted determination criterion data to store the remaining level. The amount level is determined.
By configuring in this way, it is possible to determine the remaining level of the article in consideration of the difference in how to interpret the remaining amount of the person, so it is possible to improve the accuracy of determination of the remaining level.

  Next, the outline of the configuration of the remaining amount determination system 3 according to the fourth embodiment of the present invention will be described with reference to FIG.

  The main difference between the remaining amount determination system 3 according to the fourth embodiment and the remaining amount determination system 1 according to the first embodiment is that the image capturing device 30 is further provided. Therefore, below, about the structure same as the residual amount determination system 1 which concerns on 1st embodiment among the residual amount determination systems 3 which concern on 4th embodiment, the same code | symbol is attached | subjected and description is abbreviate | omitted.

  The remaining amount determination system 3 according to the fourth embodiment is a system that manages the inventory of articles using both image recognition and voice recognition. The remaining amount determination system 3 includes a voice acquisition device 10, a user terminal 20, an image capturing device 30, and a server 100.

  The image capturing device 30 acquires an image of an article. The image capturing device 30 is disposed at a position where an image of an article can be acquired, for example, in a refrigerator.

  Next, control of the remaining amount determination system 3 according to the fourth embodiment of the present invention will be described with reference to FIG. Note that the control of the remaining amount determination system 3 according to the fourth embodiment is configured by S40 to S44 shown in FIG. 10, but steps S40 to S42 are the same as steps S10 to S12 of the first embodiment, respectively. Since it is the contents, the description is omitted here.

  In step S43, the control unit 130 recognizes the image acquired by the image capturing device 30 as image data. The control unit 130 determines the number of articles and the number of articles shown in the image, the inventory period, and the like by the image recognition function. Then, the control unit 130 stores the determined number of articles (and the inventory period) and the remaining level determined in step S42 in association with each other.

  In step S <b> 44, the control unit 130 notifies the user terminal 20 via the notification unit 140 of notification according to the number of articles and the remaining amount.

  For example, in the case of milk in a paper pack, the remaining amount in the paper pack cannot be determined even if the number can be determined by the conventional inventory management based on image recognition. In the remaining amount determination system 3 according to the fourth embodiment, the remaining amount of articles that cannot be grasped by image recognition can be determined by combining the remaining amount management by image recognition and the remaining amount management by voice recognition. Therefore, more detailed inventory management can be performed.

As described above, the remaining amount determination system 3 according to the fourth embodiment determines the number of articles based on the image capturing device 30 (image acquisition unit) that acquires an image of the article and the acquired image. And a control unit 130 (inventory management unit) that stores the number of articles and the remaining amount level of the article determined by the remaining amount determination unit in association with each other.
With this configuration, it is possible to accurately manage the inventory of articles by grasping both the number of articles and the remaining level.

Note that the image capturing device 30 according to the fourth embodiment is an embodiment of an image acquisition unit.
The control unit 130 according to the fourth embodiment is an embodiment of an inventory management unit.

1, 2, 3 Remaining amount determination system 10 Voice acquisition device 30 Image capturing device 110 Voice recognition unit 120 Determination reference data storage unit 130 Control unit 140 Notification unit 150 Purchase history data acquisition unit 210 Personal identification unit

Claims (6)

An audio acquisition unit for acquiring audio;
A voice recognition unit that recognizes the acquired voice as character information;
A determination criterion data storage unit that stores determination criterion data in which a predetermined keyword and a remaining amount level that indicates the remaining amount of articles in stages are associated with each other;
The remaining amount determination for determining the remaining amount level of the article by extracting the predetermined keyword from the character information recognized by the voice recognition unit and comparing the extracted predetermined keyword with the determination reference data And
Comprising
Remaining amount judgment system. Provide a notification unit that can notify the user of the necessity of replenishment of goods,
The notification unit
Notification according to the remaining amount level determined by the remaining amount determining unit;
The remaining amount determination system according to claim 1. Comprising a personal identification unit for identifying the individual who uttered the acquired voice;
The remaining amount determination unit
The remaining amount level is determined using a voice generated by one or more specific individuals extracted based on the identification result of the personal identification unit.
The remaining amount determination system according to claim 1 or 2. Comprising a personal identification unit for identifying the individual who uttered the acquired voice;
The criterion data is
The predetermined keyword and the remaining amount level are associated with each other,
The remaining amount determination unit
Extracting the determination criterion data of the individual identified by the personal identification unit, and determining the remaining amount level using the extracted determination criterion data;
The remaining amount determination system according to any one of claims 1 to 3. An image acquisition unit for acquiring an image of the article;
An inventory management unit that determines the number of articles based on the acquired image and stores the determined number of articles and the remaining level of the article determined by the remaining amount determination unit in association with each other. When,
Comprising
The remaining amount determination system according to any one of claims 1 to 4. A replenishment history data acquisition unit for acquiring a replenishment history of the article;
Based on the acquired replenishment history, a prediction unit that predicts a time when the remaining amount of the article is equal to or less than a threshold;
Comprising
The remaining amount determination system according to any one of claims 1 to 5.

Images