CN113128927B - Double-camera-based optimization method for unmanned retail terminal hangar damage - Google Patents
Double-camera-based optimization method for unmanned retail terminal hangar damage Download PDFInfo
- Publication number
- CN113128927B CN113128927B CN202110308359.5A CN202110308359A CN113128927B CN 113128927 B CN113128927 B CN 113128927B CN 202110308359 A CN202110308359 A CN 202110308359A CN 113128927 B CN113128927 B CN 113128927B
- Authority
- CN
- China
- Prior art keywords
- commodity
- information
- consumption
- judgment result
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000005457 optimization Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 95
- 230000002159 abnormal effect Effects 0.000 claims abstract description 83
- 238000012795 verification Methods 0.000 claims description 69
- 230000009286 beneficial effect Effects 0.000 description 9
- 230000006978 adaptation Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F9/00—Details other than those peculiar to special kinds or types of apparatus
- G07F9/02—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus
- G07F9/026—Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus for alarm, monitoring and auditing in vending machines or means for indication, e.g. when empty
Abstract
The invention provides an optimization method based on double-camera unmanned retail terminal hangar loss, which comprises the following steps: obtaining customer snapshot information; acquiring a customer consumption order; performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result; acquiring the information of the base loss of the unmanned retail terminal; performing secondary judgment on the consumption order according to the unmanned retail terminal machine library loss information and the monitoring video to obtain a second judgment result; determining an abnormal state judgment result according to the preliminary judgment result and the second judgment result; and storing and reminding information according to the abnormal state judgment result. The invention provides an optimization method based on double-camera unmanned retail terminal machine library damage, which is used for intelligently detecting double cameras to monitor, so that key evidence can be provided when conditions occur, and further the library damage of an unmanned retail shelf is reduced.
Description
Technical Field
The invention relates to the technical field of unmanned retail, in particular to an optimization method for unmanned retail terminal hangar loss based on double cameras.
Background
Unmanned retail is a large class of unmanned services, and mainly refers to article selling and retail consumption behaviors performed under the condition of no shopping guide and cashier on duty based on intelligent technology. The unmanned retail system has the advantages of reducing dependence on people, reducing labor cost and improving management efficiency through self-service or automatic settlement, and further analyzes consumer behavior by collecting and recording consumer consumption data, so that the purchasing experience of more customized and more fitting demands is brought.
At present, abnormal consumption conditions such as more or less taking of the unmanned retail terminal can occur in the use process, but personal facial information of a consumer cannot be monitored, evidence collection is difficult to carry out, and accordingly the warehouse damage of the unmanned retail shelf is caused. Therefore, the invention provides an optimization method based on double-camera unmanned retail terminal hangar damage, which can provide key evidence when conditions occur by intelligently detecting double cameras to monitor, thereby reducing the hangar damage of unmanned retail shelves.
Disclosure of Invention
The invention aims to provide an optimization method for the base loss of an unmanned retail terminal based on double cameras, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: an optimization method based on double-camera unmanned retail terminal hangar damage comprises the following steps:
obtaining customer snapshot information;
acquiring a customer consumption order;
performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result;
acquiring the information of the base loss of the unmanned retail terminal;
performing secondary judgment on the consumption order according to the unmanned retail terminal machine library loss information and the monitoring video to obtain a second judgment result;
determining an abnormal state judgment result according to the preliminary judgment result and the second judgment result;
information storage and reminding are carried out according to the abnormal state judgment result; and when the abnormal state judgment result is that the abnormal consumption condition exists, storing the consumption order, the client snapshot information and the monitoring video, and carrying out abnormal reminding, and when the abnormal state judgment result is that the abnormal consumption condition does not exist, storing the consumption order, the client snapshot information and the monitoring video, but not carrying out abnormal reminding.
Further, the customer snapshot information is obtained through shooting by a front camera of the unmanned retail terminal; the monitoring video is obtained by shooting images near the unmanned retail terminal through a camera at the side of the unmanned retail terminal.
Further, when the customer consumption order is obtained, the obtained information of the customer consumption order includes: order creation time, order completion time, consumer goods and number of consumer goods.
Further, performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result, including:
determining the acquisition time of the customer snapshot information and the order creation time and the order completion time;
matching the acquisition time of the customer snapshot information with the order creation time and the order completion time to obtain a matching result;
when the matching result is successful, the preliminary judgment result is that no abnormal consumption condition exists; and when the matching result is that the matching fails, the preliminary judgment result is that the abnormal consumption condition exists.
Further, performing secondary judgment on the consumption order according to the unmanned retail terminal machine library damage information and the monitoring video to obtain a second judgment result, including:
verifying the consumption order according to the unmanned retail terminal machine library damage information to obtain a verification result;
when the verification result is in accordance, the second judgment result is that no abnormal consumption condition exists; and when the verification result is not consistent, the second judgment result is that the abnormal consumption condition exists, and further verification is carried out by combining the monitoring video, so that the second judgment result is determined.
Further, when the verification result is not consistent, the second judgment result is that abnormal consumption condition exists, and verification is further performed by combining the monitoring video, so as to determine the second judgment result, including:
acquiring the order creation time and the order completion time;
determining video calling time according to the order creation time and the order completion time;
according to the video calling time, calling a target image in the monitoring video;
identifying the target image to obtain commodity information in the target image;
verifying the consumption order according to commodity information in the target image to obtain a verification result;
when the verification results are consistent, the second judgment result is that no abnormal consumption condition exists; and when the verification result is inconsistent, the second judgment result is that an abnormal consumption condition exists.
Further, verifying the consumption order according to the commodity information in the target image to obtain a verification result, including:
sorting commodity information in the target image; information arrangement is carried out on commodity names and commodity quantity in commodity information in the target image, and a monitoring image commodity information table is obtained;
and carrying out verification judgment in the monitoring image commodity information table according to the consumption order to obtain a verification result.
Further, the step of obtaining the customer snapshot information is to take a snapshot of the customer in the process of completing the customer consumption order, and the snapshot frequency is set to snapshot a plurality of photos during the snapshot, so that the customer snapshot information at a plurality of moments is obtained.
Further, performing verification and judgment in the monitored image commodity information table according to the consumption order, including:
determining information of the goods in the consumption order, which is recorded asThe method is specifically expressed as follows:
;
wherein,representing +.>The name of the individual consumer goods,/>Representing +.>The number of items of the individual consumer items;
determining commodity information in the monitoring image commodity information table, and marking the commodity information asThe method is specifically expressed as follows:
;
wherein,representing the +.f in the monitoring image commodity information table>Name of the individual commodity,/>Representing the +.f in the monitoring image commodity information table>The number of items of the individual items;
analyzing based on the commodity name of the consumer commodity and the commodity name of the commodity in the monitoring image commodity information table to obtain a keyword of the commodity name of the consumer commodity and a keyword of the commodity name of the commodity in the monitoring image commodity information table;
matching in the monitoring image commodity information table according to the keywords of the commodity names of the consumer commodities;
;
in the above-mentioned formula(s),representing +.>Matching value of commodity name of individual consumer commodity in the monitoring image commodity information table,/-for>Representing +.>The trade name of the individual consumer goods +.>Keywords (e.g. Japan)>Representing the +.f in the monitoring image commodity information table>The trade name of the individual trade item->Keywords (e.g. Japan)>Representing +.>The trade name of the individual consumer goods +.>The first keyword and the monitoring image commodity information table>The trade name of the individual trade item->Semantic similarity between keywords, +.>Representing +.>The number of keywords in the commodity names of the individual consumer commodities;
when the matching value is hundred percent, calculating a verification value between the commodity number of the commodity in the monitoring image commodity information table and the commodity number of the consumption commodity in the consumption order; otherwise, directly determining the verification result as abnormal consumption; and calculating a verification value between the commodity number of the commodities in the commodity information table of the monitoring image and the commodity number of the consumed commodities in the consumption order, and calculating according to the following formula:
;
in the above-mentioned formula(s),check value indicating the number of products between the products in the monitoring image product information table and the number of products of the consumer products in the consumer order,/-for>Representing +.>The commodity names of the individual consumer commodities match the commodity number of the commodity,
and when the verification value is 0, the verification result is passing, and when the verification value is not 0, the verification result is that abnormal consumption condition exists.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a schematic diagram of steps of an optimization method based on double-camera unmanned retail terminal hangar loss according to the invention;
fig. 2 is a schematic flow chart of a third step in the method for optimizing the model loss of the unmanned retail terminal based on the double cameras;
fig. 3 is a schematic flow chart of the method for optimizing the base loss of the unmanned retail terminal based on the double cameras in the condition that the verification result in the fifth step is not in conformity.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for optimizing a base loss of an unmanned retail terminal based on dual cameras, including:
step one, obtaining customer snapshot information;
step two, obtaining a customer consumption order;
step three, performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result;
step four, acquiring the information of the unmanned retail terminal hangar loss;
step five, carrying out secondary judgment on the consumption order according to the unmanned retail terminal machine library damage information and the monitoring video to obtain a second judgment result;
step six, determining an abnormal state judgment result according to the preliminary judgment result and the second judgment result;
step seven, information storage and reminding are carried out according to the abnormal state judgment result; and when the abnormal state judgment result is that the abnormal consumption condition exists, storing the consumption order, the client snapshot information and the monitoring video, and carrying out abnormal reminding, and when the abnormal state judgment result is that the abnormal consumption condition does not exist, storing the consumption order, the client snapshot information and the monitoring video, but not carrying out abnormal reminding.
The principle of the technical scheme is as follows: in the technical scheme, client snapshot information is obtained; acquiring a customer consumption order; then, performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result; acquiring the information of the base loss of the unmanned retail terminal; secondly, carrying out secondary judgment on the consumption order according to the unmanned retail terminal machine library damage information and the monitoring video to obtain a second judgment result; then, determining an abnormal state judgment result according to the preliminary judgment result and the second judgment result; and finally, information storage and reminding are carried out according to the abnormal state judgment result. If the abnormal state judging result is that the abnormal consumption condition exists, the consumption order, the client snapshot information and the monitoring video are stored, and meanwhile abnormal reminding is carried out, and if the abnormal state judging result is that the abnormal consumption condition does not exist, the consumption order, the client snapshot information and the monitoring video are stored, but abnormal reminding is not carried out.
The beneficial effects of the technical scheme are that: according to the technical scheme, the customer snapshot information and the monitoring video which are respectively acquired through the two cameras are jointly judged with the consumption order to obtain the abnormal state judgment result, so that abnormal consumption conditions of customers during consumption through the unmanned retail terminal are avoided, the occurrence of the phenomenon of the base damage of the unmanned retail terminal is avoided as much as possible, the base damage of the unmanned retail terminal is reduced, further economic losses are avoided, the abnormal judgment result is determined by combining the initial judgment result and the abnormal state judgment result determined by the second judgment result, the abnormal consumption state exists in the abnormal judgment result as long as one of the initial judgment result and the second judgment result is abnormal, in addition, when the abnormal judgment result is used for storing and reminding the customer information, the stored consumption order information, the customer appearance information and the monitoring image information can be proved as evidence, and further economic losses can be reduced as much as possible.
In one embodiment of the invention, the customer snapshot information is obtained by shooting through a front camera of the unmanned retail terminal; the monitoring video is obtained by shooting images near the unmanned retail terminal through a camera at the side of the unmanned retail terminal.
The principle of the technical scheme is as follows: according to the technical scheme, the client snapshot information and the monitoring video are respectively obtained through the two cameras, wherein one camera is positioned on the front side of the unmanned retail terminal, and when the client consumes before the unmanned retail terminal, the client takes a snapshot, so that the client snapshot information is obtained; the other camera is positioned on the side face of the unmanned retail terminal and shoots images nearby the unmanned retail terminal to obtain a monitoring video.
The beneficial effects of the technical scheme are that: according to the technical scheme, the two cameras are used for acquiring the image information respectively, so that the customer snapshot information and the monitoring video are obtained, a judgment reference is provided for obtaining the abnormal judgment result, the positions of the two cameras are set for the acquired information, and the customer snapshot information and the monitoring video which are required to be obtained can be better obtained.
In one embodiment of the present invention, when the customer consumption order is obtained, the information of the customer consumption order obtained includes: order creation time, order completion time, consumer goods and number of consumer goods.
The principle of the technical scheme is as follows: in the above technical solution, the information of the consumer order at least includes an order creation time, an order completion time, a consumer goods and a consumer goods number.
The beneficial effects of the technical scheme are that: according to the technical scheme, the order creation time and the order completion time are contained in the consumption order information, so that when primary judgment and secondary judgment are carried out, in the customer snapshot information and the monitoring video, the customer snapshot information and the monitoring video corresponding to the order creation time and the order completion time are judged, and the speed of primary judgment and secondary judgment is improved.
As shown in fig. 2, in one embodiment of the present invention, performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result, including:
determining the acquisition time of the customer snapshot information and the order creation time and the order completion time;
matching the acquisition time of the customer snapshot information with the order creation time and the order completion time to obtain a matching result;
when the matching result is successful, the preliminary judgment result is that no abnormal consumption condition exists; and when the matching result is that the matching fails, the preliminary judgment result is that the abnormal consumption condition exists.
The principle of the technical scheme is as follows: when the preliminary judgment is carried out according to the customer snapshot information and the customer consumption order, the technical scheme firstly obtains the acquisition time of the customer snapshot information and determines the order creation time and the order completion time; then matching the acquisition time of the client snapshot information with the order creation time and the order completion time, and determining whether the acquisition time of the client snapshot information is matched with the order creation time and the order completion time or not, so as to obtain a matching result; when the matching result is successful, the preliminary judgment result is that no abnormal consumption condition exists; and when the matching result is that the matching fails, the preliminary judgment result is that the abnormal consumption condition exists.
The beneficial effects of the technical scheme are that: according to the technical scheme, in the process of obtaining the preliminary judgment result, the obtaining time of the customer snapshot information is matched with the order creation time and the order completion time, so that the preliminary judgment result is obtained according to the matching result, and the matching is performed according to the time when the matching is performed, so that the time of the customer snapshot information is matched with the time of the consumption order, and the situation that the customer snapshot information is not matched with the consumption order and abnormal consumption is avoided.
In one embodiment of the present invention, performing secondary judgment on the consumption order according to the unmanned retail terminal machine-base loss information and the monitoring video to obtain a second judgment result, including:
verifying the consumption order according to the unmanned retail terminal machine library damage information to obtain a verification result;
when the verification result is in accordance, the second judgment result is that no abnormal consumption condition exists; and when the verification result is not consistent, the second judgment result is that the abnormal consumption condition exists, and further verification is carried out by combining the monitoring video, so that the second judgment result is determined.
The principle of the technical scheme is as follows: in the technical scheme, when the consumption order is secondarily judged according to the unmanned retail terminal machine library loss information and the monitoring video, checking is carried out on the consumption order according to the unmanned retail terminal machine library loss information, whether the unmanned retail terminal machine library loss information accords with the consumption order or not is checked, so that a checking result is obtained, and if the checking result accords with the consumption order, the second judging result is that the abnormal consumption condition does not exist; if the verification result is not in conformity, the second judgment result is that abnormal consumption conditions exist, and further verification is needed by combining the monitoring video, so that the second judgment result is determined.
The beneficial effects of the technical scheme are that: according to the technical scheme, in the process of determining the second judgment result, the second judgment result is obtained by checking the consumption order according to the unmanned retail terminal machine library loss information, so that customer dissatisfaction caused by the fact that the unmanned retail terminal machine library loss information is not consistent with the consumption order or economic loss caused by the unmanned retail terminal machine is avoided, and further verification is carried out when abnormal consumption conditions are suspected, so that the fact that the unmanned retail terminal machine library loss information is not consistent with the consumption order is verified, and the second judgment result is more accurate.
As shown in fig. 3, in an embodiment of the present invention, when the verification result is not consistent, the second judgment result is that the abnormal consumption condition is suspected, and further, verification is performed in combination with the monitoring video, to determine the second judgment result includes:
acquiring the order creation time and the order completion time;
determining video calling time according to the order creation time and the order completion time;
according to the video calling time, calling a target image in the monitoring video;
identifying the target image to obtain commodity information in the target image;
verifying the consumption order according to commodity information in the target image to obtain a verification result;
when the verification results are consistent, the second judgment result is that no abnormal consumption condition exists; and when the verification result is inconsistent, the second judgment result is that an abnormal consumption condition exists.
The principle of the technical scheme is as follows: when the verification result is not consistent, the second judgment result is that abnormal consumption conditions exist, and the verification is further needed by combining the monitoring video at the moment, so that the second judgment result is determined; in the process of further verifying by combining the monitoring video and determining the second judging result, the method sequentially comprises the following steps: acquiring order creation time and order completion time in a consumption order; determining video calling time according to the order creation time and the order completion time, taking the order creation time as the starting time of the video calling time, and taking the order completion time as the deadline of the video calling time; according to the video calling time, calling a target image in the monitoring video, and intercepting the monitoring video corresponding to the video calling time in the monitoring video as the target image; identifying the target image, and identifying the commodity appearing in the target image and the quantity of the commodity appearing in the target image so as to obtain commodity information in the target image; verifying the consumption order in the commodity information in the target image to obtain a verification result; if the commodity information in the target image is consistent with the consumption order, the verification result is consistent, and the second judgment result is that no abnormal consumption condition exists; if the commodity information in the target image is inconsistent with the consumption order, the verification result is inconsistent, and the second judgment result is that an abnormal consumption condition exists.
The beneficial effects of the technical scheme are that: according to the technical scheme, the video calling time is determined, and then the target image is intercepted in the monitoring video, so that redundancy of irrelevant monitoring videos is reduced when a consumption order is verified according to commodity information in the target image, the complexity of verification is further reduced, and the verification efficiency is improved. And the technical scheme classifies the condition that commodity information in the target image is inconsistent with the consumption order as an abnormal consumption condition through the verification result, so that the inconsistent information monitored in the consumption order and the monitoring video is avoided, the economic loss of the unmanned retail terminal side or the economic loss of the client is caused, and further, the economic loss of the unmanned retail terminal side and the economic loss of the client are avoided.
In one embodiment of the present invention, verifying the consumption order according to the commodity information in the target image to obtain a verification result includes:
sorting commodity information in the target image; information arrangement is carried out on commodity names and commodity quantity in commodity information in the target image, and a monitoring image commodity information table is obtained;
and carrying out verification judgment in the monitoring image commodity information table according to the consumption order to obtain a verification result.
The principle of the technical scheme is as follows: in the technical scheme, when verifying the consumption order according to the commodity information in the target image, firstly, sorting the commodity information in the target image; information arrangement is carried out on commodity names and commodity quantity in commodity information in the target image, and a monitoring image commodity information table is obtained; and then, carrying out verification judgment in the monitoring image commodity information table according to the consumption order to obtain a verification result.
The beneficial effects of the technical scheme are that: according to the technical scheme, in the process of obtaining the verification result, the commodity information in the consumption order and the target image is verified, so that the fact that the commodity paid in the consumption order by some users is different from the actual commodity monitored in the monitoring image in the process of consumption is avoided, and further abnormal consumption conditions such as more or less buying and paying are avoided, and economic losses are avoided.
In one embodiment of the invention, the obtaining of the customer snapshot information is to take a snapshot of the customer in the process of completing the customer consumption order, and the snapshot frequency is set to take a plurality of photos during the snapshot, so that the customer snapshot information at a plurality of moments is obtained.
The principle of the technical scheme is as follows: according to the technical scheme, when the customer snapshot information is acquired, the snapshot frequency is set for the timing device, so that the customer snapshot information at a plurality of moments is acquired by carrying out snapshot according to the snapshot frequency during the completion of a transaction order.
The beneficial effects of the technical scheme are that: according to the technical scheme, customer snapshot information at a plurality of moments is obtained through snapshot during the completion of a transaction order according to the snapshot frequency, so that abundant judgment references can be provided when preliminary judgment is carried out, and the accuracy of the preliminary judgment is improved.
In one embodiment of the present invention, the verification and judgment in the monitored image commodity information table according to the consumption order includes:
determining information of the goods in the consumption order, which is recorded asThe method is specifically expressed as follows:
;
wherein,representing +.>The name of the individual consumer goods,/>Representing +.>The number of items of the individual consumer items;
determining commodity information in the monitoring image commodity information table, and marking the commodity information asThe method is specifically expressed as follows:
;
wherein,representing the +.f in the monitoring image commodity information table>Name of the individual commodity,/>Representing the +.f in the monitoring image commodity information table>The number of items of the individual items;
analyzing based on the commodity name of the consumer commodity and the commodity name of the commodity in the monitoring image commodity information table to obtain a keyword of the commodity name of the consumer commodity and a keyword of the commodity name of the commodity in the monitoring image commodity information table;
matching in the monitoring image commodity information table according to the keywords of the commodity names of the consumer commodities;
;
in the above-mentioned formula(s),representing +.>Matching value of commodity name of individual consumer commodity in the monitoring image commodity information table,/-for>Representing +.>The trade name of the individual consumer goods +.>Keywords (e.g. Japan)>Representing the +.f in the monitoring image commodity information table>The trade name of the individual trade item->Keywords (e.g. Japan)>Representing +.>The trade name of the individual consumer goods +.>The first keyword and the monitoring image commodity information table>The trade name of the individual trade item->Semantic similarity between keywords, +.>Representing +.>The number of keywords in the commodity names of the individual consumer commodities;
when the matching value is hundred percent, calculating a verification value between the commodity number of the commodity in the monitoring image commodity information table and the commodity number of the consumption commodity in the consumption order; otherwise, directly determining the verification result as abnormal consumption;
the principle of the technical scheme is as follows: when verification and judgment are carried out in the monitoring image commodity information table according to the consumption order, the information of the commodity in the consumption order and the commodity information in the monitoring image commodity information table are firstly determined respectively, then analysis is carried out based on the commodity names of the consumption commodity and the commodity names of the commodity in the monitoring image commodity information table, keywords of the commodity names of the consumption commodity and keywords of the commodity names of the commodity in the monitoring image commodity information table are obtained, then matching is carried out in the monitoring image commodity information table according to the keywords of the commodity names of the consumption commodity, and when the matching value is hundred percent, a verification value between the commodity number of the commodity in the monitoring image commodity information table and the commodity number of the consumption commodity in the consumption order is calculated; otherwise, directly determining the verification result as abnormal consumption.
The beneficial effects of the technical scheme are that: according to the technical scheme, matching is carried out in the monitoring image commodity information table according to the keywords of the commodity names of the consumer commodities, so that a matching result is more accurate, and the keywords of the same commodity names are the same, so that the semantic similarity among the same keywords can be as high as one hundred percent, and a powerful judgment threshold is provided for matching judgment. And when the matching value is hundred percent, further calculating a verification value between the commodity number of the commodity in the monitoring image commodity information table and the commodity number of the consumption commodity in the consumption order; otherwise, directly determining the verification result as abnormal consumption, and rapidly and preliminarily determining the abnormal consumption condition.
It will be appreciated by those skilled in the art that the first and second aspects of the present invention refer only to different phases of application.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (4)
1. The utility model provides an optimization method based on unmanned retail terminal hangar of two cameras is damaged which characterized in that includes:
obtaining customer snapshot information;
acquiring a customer consumption order; the information of the customer consumption order obtained comprises: order creation time, order completion time, consumer goods and number of consumer goods;
performing preliminary judgment according to the customer snapshot information and the customer consumption order to obtain a preliminary judgment result;
acquiring the information of the base loss of the unmanned retail terminal;
performing secondary judgment on the consumption order according to the unmanned retail terminal machine library damage information and the monitoring video to obtain a second judgment result, wherein the secondary judgment result comprises the following steps: verifying the consumption order according to the unmanned retail terminal machine library damage information to obtain a verification result; when the verification result is in accordance, the second judgment result is that no abnormal consumption condition exists; when the verification result is not consistent, the second judgment result is that abnormal consumption is suspected to existThe condition is further verified by combining the monitoring video, and a second judging result is determined; if the verification result is not consistent, the second judgment result is that abnormal consumption conditions exist, and verification is further carried out by combining the monitoring video, so that the second judgment result is determined, and the method comprises the following steps: acquiring the order creation time and the order completion time; determining video calling time according to the order creation time and the order completion time; according to the video calling time, calling a target image in the monitoring video; identifying the target image to obtain commodity information in the target image; verifying the consumption order according to the commodity information in the target image to obtain a verification result, wherein the verification result comprises the following steps: sorting commodity information in the target image; information arrangement is carried out on commodity names and commodity quantity in commodity information in the target image, and a monitoring image commodity information table is obtained; performing verification judgment in the monitoring image commodity information table according to the consumption order to obtain a verification result; when the verification results are consistent, the second judgment result is that no abnormal consumption condition exists; when the verification result is inconsistent, a second judgment result is that an abnormal consumption condition exists; wherein, according to the consumption order, verification judgment is carried out in the monitoring image commodity information table, which comprises the following steps: determining information of the goods in the consumption order, which is recorded asThe method is specifically expressed as follows:
;
wherein,representing +.>The name of the individual consumer goods,/>Representing +.>The number of items of the individual consumer items;
determining commodity information in the monitoring image commodity information table, and marking the commodity information asThe method is specifically expressed as follows:
;
wherein,representing the +.f in the monitoring image commodity information table>Name of the individual commodity,/>Representing the +.f in the monitoring image commodity information table>The number of items of the individual items;
analyzing based on the commodity name of the consumer commodity and the commodity name of the commodity in the monitoring image commodity information table to obtain a keyword of the commodity name of the consumer commodity and a keyword of the commodity name of the commodity in the monitoring image commodity information table;
matching in the monitoring image commodity information table according to the keywords of the commodity names of the consumer commodities;
;
in the above-mentioned formula(s),representing +.>Matching value of commodity name of individual consumer commodity in the monitoring image commodity information table,/-for>Representing +.>The trade name of the individual consumer goods +.>Keywords (e.g. Japan)>Representing the +.f in the monitoring image commodity information table>The trade name of the individual trade item->Keywords (e.g. Japan)>Representing +.>The trade name of the individual consumer goods +.>The first keyword and the monitoring image commodity information table>The trade name of the individual trade item->Semantic similarity between keywords, +.>Representing +.>The number of keywords in the commodity names of the individual consumer commodities;
when the matching value is hundred percent, calculating a verification value between the commodity number of the commodity in the monitoring image commodity information table and the commodity number of the consumption commodity in the consumption order; otherwise, directly determining the verification result as abnormal consumption;
determining an abnormal state judgment result according to the preliminary judgment result and the second judgment result;
information storage and reminding are carried out according to the abnormal state judgment result; and when the abnormal state judgment result is that the abnormal consumption condition exists, storing the consumption order, the client snapshot information and the monitoring video, and carrying out abnormal reminding, and when the abnormal state judgment result is that the abnormal consumption condition does not exist, storing the consumption order, the client snapshot information and the monitoring video, but not carrying out abnormal reminding.
2. The optimization method based on double-camera unmanned retail terminal machine library loss according to claim 1, wherein the customer snapshot information is obtained through shooting by a front-side camera of the unmanned retail terminal machine; the monitoring video is obtained by shooting images near the unmanned retail terminal through a camera at the side of the unmanned retail terminal.
3. The optimization method based on double-camera unmanned retail terminal hangar loss according to claim 1, wherein the preliminary judgment is performed according to the customer snapshot information and the customer consumption order, and the preliminary judgment result is obtained, comprising:
determining the acquisition time of the customer snapshot information and the order creation time and the order completion time;
matching the acquisition time of the customer snapshot information with the order creation time and the order completion time to obtain a matching result;
when the matching result is successful, the preliminary judgment result is that no abnormal consumption condition exists; and when the matching result is that the matching fails, the preliminary judgment result is that the abnormal consumption condition exists.
4. The optimization method based on the double-camera unmanned retail terminal machine library loss according to claim 1, wherein the step of obtaining the customer snapshot information is to take a snapshot of the customer in the process of completing the customer consumption order, and the snapshot frequency is set to take a plurality of photos during the snapshot, so that the customer snapshot information at a plurality of moments is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110308359.5A CN113128927B (en) | 2021-03-23 | 2021-03-23 | Double-camera-based optimization method for unmanned retail terminal hangar damage |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110308359.5A CN113128927B (en) | 2021-03-23 | 2021-03-23 | Double-camera-based optimization method for unmanned retail terminal hangar damage |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113128927A CN113128927A (en) | 2021-07-16 |
CN113128927B true CN113128927B (en) | 2023-12-22 |
Family
ID=76773818
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110308359.5A Active CN113128927B (en) | 2021-03-23 | 2021-03-23 | Double-camera-based optimization method for unmanned retail terminal hangar damage |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113128927B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
CN206179134U (en) * | 2016-09-21 | 2017-05-17 | 深圳市泛海三江科技发展有限公司 | Discuss outstandingly intelligent ability anti -theft system |
CN110097689A (en) * | 2018-01-26 | 2019-08-06 | 江苏美萃恪斯数字技术有限公司 | Seller's management system, payment management method for unmanned retail cabinet |
CN110189205A (en) * | 2019-06-03 | 2019-08-30 | 深圳普思英察科技有限公司 | Optimization method and system based on the unmanned retail shelf library damage of dual camera |
CN110443949A (en) * | 2019-08-14 | 2019-11-12 | 北京卓因达科技有限公司 | Automatic vending machine shipment method and device based on image recognition |
CN110489457A (en) * | 2019-07-19 | 2019-11-22 | 宜通世纪物联网研究院(广州)有限公司 | Merchandise news analysis method, system and storage medium based on image recognition |
WO2019228063A1 (en) * | 2018-05-30 | 2019-12-05 | 京东方科技集团股份有限公司 | Product inspection terminal, method and system, computer apparatus and readable medium |
CN110570599A (en) * | 2019-09-11 | 2019-12-13 | 四川科伦智慧药房科技有限公司 | automatic medicine vending machine with remote inquiry function |
WO2020045294A1 (en) * | 2018-08-27 | 2020-03-05 | 隆均 半田 | Merchandise payment settlement system |
CN111915794A (en) * | 2019-05-09 | 2020-11-10 | 顺丰科技有限公司 | Unmanned vending machine and vending method thereof |
CN115186165A (en) * | 2022-07-07 | 2022-10-14 | 杭州么贝软件科技有限公司 | Mobile electronic commerce image searching and shopping method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9218580B2 (en) * | 2010-12-30 | 2015-12-22 | Honeywell International Inc. | Detecting retail shrinkage using behavioral analytics |
JP7010030B2 (en) * | 2018-01-31 | 2022-01-26 | 日本電気株式会社 | In-store monitoring equipment, in-store monitoring methods, and in-store monitoring programs |
-
2021
- 2021-03-23 CN CN202110308359.5A patent/CN113128927B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
CN206179134U (en) * | 2016-09-21 | 2017-05-17 | 深圳市泛海三江科技发展有限公司 | Discuss outstandingly intelligent ability anti -theft system |
CN110097689A (en) * | 2018-01-26 | 2019-08-06 | 江苏美萃恪斯数字技术有限公司 | Seller's management system, payment management method for unmanned retail cabinet |
WO2019228063A1 (en) * | 2018-05-30 | 2019-12-05 | 京东方科技集团股份有限公司 | Product inspection terminal, method and system, computer apparatus and readable medium |
WO2020045294A1 (en) * | 2018-08-27 | 2020-03-05 | 隆均 半田 | Merchandise payment settlement system |
CN111915794A (en) * | 2019-05-09 | 2020-11-10 | 顺丰科技有限公司 | Unmanned vending machine and vending method thereof |
CN110189205A (en) * | 2019-06-03 | 2019-08-30 | 深圳普思英察科技有限公司 | Optimization method and system based on the unmanned retail shelf library damage of dual camera |
CN110489457A (en) * | 2019-07-19 | 2019-11-22 | 宜通世纪物联网研究院(广州)有限公司 | Merchandise news analysis method, system and storage medium based on image recognition |
CN110443949A (en) * | 2019-08-14 | 2019-11-12 | 北京卓因达科技有限公司 | Automatic vending machine shipment method and device based on image recognition |
CN110570599A (en) * | 2019-09-11 | 2019-12-13 | 四川科伦智慧药房科技有限公司 | automatic medicine vending machine with remote inquiry function |
CN115186165A (en) * | 2022-07-07 | 2022-10-14 | 杭州么贝软件科技有限公司 | Mobile electronic commerce image searching and shopping method |
Also Published As
Publication number | Publication date |
---|---|
CN113128927A (en) | 2021-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11861584B2 (en) | Self-service settlement method, apparatus and storage medium | |
US20210056498A1 (en) | Method and device for identifying product purchased by user and intelligent shelf system | |
WO2020010827A1 (en) | Open type vending machine-based shopping settlement method and device | |
US8429016B2 (en) | Generating an alert based on absence of a given person in a transaction | |
CN112466035B (en) | Commodity identification method, device and system based on vision and gravity sensing | |
CN108960038B (en) | Shopping trolley based on image recognition technology and recognition method thereof | |
CN110348293B (en) | Commodity identification method and system | |
CN109658194A (en) | A kind of lead referral method and system based on video frequency tracking | |
TWM443899U (en) | An intelligent point-of-sales system with active identification of customer group | |
CN108648338A (en) | The shopping saving system method, apparatus and vending machine of automatic vending machine | |
CN115063084A (en) | Inventory checking method and system for cigarette retail merchants | |
CN111260685B (en) | Video processing method and device and electronic equipment | |
CN113128927B (en) | Double-camera-based optimization method for unmanned retail terminal hangar damage | |
US20130290107A1 (en) | Behavior based bundling | |
CN110853230A (en) | Self-service vending machine exception handling method, system and equipment | |
CN115294325A (en) | Dynamic commodity identification system, method, medium, equipment and terminal for sales counter | |
CN115880626A (en) | Method and system for detecting shortage of goods and replenishing goods | |
CN110443946A (en) | Vending machine, the recognition methods of type of goods and device | |
CN112989973A (en) | Abnormal behavior detection reminding method and system | |
CN111523979A (en) | Intelligent selling method | |
CN112734446A (en) | Commodity verification method and device based on vision and gravity detection | |
CN111401232B (en) | Customer type judgment method, system, equipment and medium | |
CN114821729B (en) | Commodity shopping guide method and device, cloud server and storage medium | |
US20240104587A1 (en) | Familiarity degree estimation apparatus, familiarity degree estimation method, and recording medium | |
CN117011984B (en) | AI-based self-service cashing loss prevention method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |