WO2020107928A1 - 商品检测方法和装置 - Google Patents

商品检测方法和装置 Download PDF

Info

Publication number
WO2020107928A1
WO2020107928A1 PCT/CN2019/099052 CN2019099052W WO2020107928A1 WO 2020107928 A1 WO2020107928 A1 WO 2020107928A1 CN 2019099052 W CN2019099052 W CN 2019099052W WO 2020107928 A1 WO2020107928 A1 WO 2020107928A1
Authority
WO
WIPO (PCT)
Prior art keywords
weight data
time
moment
weight
commodity
Prior art date
Application number
PCT/CN2019/099052
Other languages
English (en)
French (fr)
Inventor
林金表
Original Assignee
北京京东尚科信息技术有限公司
北京京东世纪贸易有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京京东尚科信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京京东尚科信息技术有限公司
Priority to JP2021530218A priority Critical patent/JP7524182B2/ja
Priority to US17/288,293 priority patent/US20210383635A1/en
Priority to EP19890002.9A priority patent/EP3855378A4/en
Publication of WO2020107928A1 publication Critical patent/WO2020107928A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
    • G07G1/00—Cash registers
    • G07G1/0036—Checkout procedures
    • G07G1/0045—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader
    • G07G1/0054—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader with control of supplementary check-parameters, e.g. weight or number of articles
    • G07G1/0072—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader with control of supplementary check-parameters, e.g. weight or number of articles with means for detecting the weight of the article of which the code is read, for the verification of the registration
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01G—WEIGHING
    • G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
    • 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/20—Point-of-sale [POS] network systems
    • G06Q20/203—Inventory monitoring
    • 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/20—Point-of-sale [POS] network systems
    • G06Q20/208—Input by product or record sensing, e.g. weighing or scanner processing
    • 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/407—Cancellation of a transaction
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
    • G07F11/007—Coin-freed apparatus for dispensing, or the like, discrete articles wherein the storage and dispensing mechanism are configurable in relation to the physical or geometrical properties of the articles to be stored or dispensed
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
    • G07F11/72—Auxiliary equipment, e.g. for lighting cigars, opening bottles
    • 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

Definitions

  • the present disclosure relates to the field of data processing, and in particular to a commodity detection method and device.
  • vending machines widely used in the market have made breakthroughs in payment methods, they have unavoidable defects. For example, after a customer purchases a product, the vending machine still needs to transfer the product to the vending machine through the mechanical mechanism. The mechanical structure is prone to failure and adversely affects the entire vending machine system. In addition, the customer uses the existing vending machine. Before purchasing a product, you can only see the sample of the product or the product picture through the observation window. You cannot choose the product intuitively. Once you get the product, you cannot change the selection, which makes the customer's shopping experience poor.
  • Unmanned vending containers use RFID (Radio Frequency Identification) tags, gravity calculation, and image recognition.
  • RFID Radio Frequency Identification
  • Technical means reckon that the customer purchases the goods, and the customer settles intelligently after closing the door.
  • a product detection method which includes: determining the product that the user has taken and the weight data of each product; acquiring the weight data in the weight rise time interval when the user takes the product to the time when the gravity scale is stable, wherein , Gravity scale is used to detect the weight of the product; according to the difference between the maximum weight data and the minimum weight data in the weight data in the weight rise time period, the maximum replacement weight data is determined; according to the maximum replacement weight data and the weight data of each product , Predict whether each commodity will be put back.
  • the weight data of a commodity is greater than the maximum replacement weight data, it is estimated that the commodity has not been replaced; if the weight data of a commodity is less than or equal to the maximum replacement weight data, the commodity is estimated Was put back.
  • the weight data of a certain product is less than or equal to the maximum replacement weight data, and the difference between the weight data detected by the gravity scale after the user takes the product and the weight data detected after the gravity scale is stabilized, the weight of the product If the data is not equal, it is estimated that the product is put back, and the user takes other products.
  • the maximum weight data is greater than the weight data at the previous moment and greater than the weight data at the later moment, and the minimum weight data is less than the weight data at the previous moment and less than the weight data at the latter moment.
  • the difference between the maximum weight data and the minimum weight data in each weight rise time interval is obtained, and the maximum difference value is used as the maximum return weight data.
  • the weight data at the first moment and the weight data at the second moment detected by the gravity scale are obtained, wherein the second moment is later than the first moment, and the second moment is adjacent to the first moment, the first
  • the initial value of the time is the starting time, and the weight data at the starting time is the minimum weight data; determine whether the weight data at the second time is greater than the weight data at the first time; if the weight data at the second time is greater than the weight data at the first time, then The weight data at the first moment and the weight data at the second moment are the weight data in the weight rise time interval; determine whether the second moment is the end moment, and if so, use the weight data at the second moment as the maximum weight data, otherwise, The second time is regarded as the first time, and the time next to the second time is regarded as the second time.
  • the weight data at the second time is less than the weight data at the first time, it is determined whether the number of times the weight data has fallen is greater than or equal to the noise frequency threshold between the starting time and the second time, and if so, the second time As the starting time, otherwise, the second time is regarded as the first time, and the next time of the second time is regarded as the second time.
  • the weight data at the second time is equal to the weight data at the first time, and the weight data at the previous time at the first time is greater than the weight data at the first time, it is determined between the starting time and the second time Whether the weight data drop times are greater than the noise frequency threshold, if so, the second time is used as the starting time, otherwise, the second time is used as the first time, and the next time as the second time is used as the second time.
  • a commodity detection device which includes: a taken commodity data determination unit configured to determine the commodity that the user has taken and weight data of each commodity; a weight data acquisition unit configured to Obtain the weight data in the weight rise time range when the user takes the goods to the gravity scale stable, where the gravity scale is used to detect the weight of the goods; the maximum replacement data determination unit is configured to determine the weight data in the weight rise time range The difference between the maximum weight data and the minimum weight data in to determine the maximum replacement weight data; the product replacement estimation unit is configured to estimate whether each product is returned based on the maximum replacement weight data and the weight data of each product .
  • the product replacement estimation unit is configured to estimate that if the weight data of a product is greater than the maximum replacement weight data, the product is not returned, if the weight data of a product is less than or equal to the maximum replacement If the weight data is returned, it is estimated that the product will be put back.
  • the commodity return estimation unit is further configured if the weight data of a commodity is less than or equal to the maximum return weight data, and the weight data detected by the gravity scale after the user takes the commodity and the weight data detected after the gravity scale is stable The difference between the weight data and the weight data of the product is not equal, it is estimated that the product is put back, and the user has taken other products.
  • the maximum weight data is greater than the weight data at the previous moment and greater than the weight data at the later moment, and the minimum weight data is less than the weight data at the previous moment and less than the weight data at the latter moment.
  • the maximum replacement data determination unit is configured to obtain the difference between the maximum weight data and the minimum weight data for each weight rise time interval if there are multiple weight rise time intervals, and use the maximum difference as the maximum Return weight data.
  • the weight data acquisition unit is configured to acquire the weight data detected at the first moment and the weight data at the second moment detected by the gravity scale, wherein the second moment is later than the first moment, the second moment and the first moment Are adjacent times, the initial value of the first time is the starting time, and the weight data at the starting time is the minimum weight data; it is determined whether the weight data at the second time is greater than the weight data at the first time; if the weight data at the second time is greater than the first For the weight data at one moment, the weight data at the first moment and the weight data at the second moment are the weight data in the weight rise time interval; determine whether the second moment is the end moment, and if so, use the weight data at the second moment as The maximum weight data, otherwise, the second time is regarded as the first time, and the next time of the second time is regarded as the second time.
  • the weight data acquiring unit is configured to determine whether the number of weight data drops is greater than or equal to the noise frequency threshold between the starting time and the second time if the weight data at the second time is less than the weight data at the first time, If yes, the second time is taken as the starting time, otherwise, the second time is taken as the first time, and the next time of the second time is taken as the second time.
  • the weight data acquiring unit is configured to determine the starting point if the weight data at the second time is equal to the weight data at the first time, and the weight data at the previous time at the first time is greater than the weight data at the first time Whether the number of weight data drops is greater than the noise frequency threshold between time and second time, if yes, the second time is used as the starting time, otherwise, the second time is used as the first time, and the next time of the second time is used as the second time.
  • a commodity detection apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the commodity detection method as described above based on instructions stored in the memory.
  • a computer-readable storage medium on which computer program instructions are stored, which when executed by a processor implements the aforementioned commodity detection method.
  • FIG. 1 is a graph of gravity changes after a user puts back a certain product and takes other products in some embodiments.
  • FIG. 2 is a graph of gravity changes after a user puts back a certain product and takes other products in other embodiments.
  • FIG. 3 is a schematic flowchart of some embodiments of a commodity detection method of the present disclosure.
  • FIG. 4 is a schematic flowchart of some embodiments of determining the maximum replacement weight data in the commodity detection method of the present disclosure.
  • FIG. 5 is a schematic flowchart of a specific embodiment of determining the maximum replacement weight data in the commodity detection method of the present disclosure.
  • FIG. 6 is a schematic structural diagram of some embodiments of a commodity detection device of the present disclosure.
  • FIG. 7 is a schematic structural diagram of other embodiments of a commodity detection device of the present disclosure.
  • FIG. 8 is a schematic structural diagram of still other embodiments of a commodity detection device of the present disclosure.
  • the new product may be retrieved immediately. For example, the user has taken the goods A and B, and the weight of the goods B is much larger than the weight of the goods A. If the user puts back the goods A, he takes the goods C heavier than A before the gravity scale stabilizes. The gravity change curve at this time is shown in FIG. 1. The weight difference between the initial and stable gravity scales is equal to the weight difference between the product C and the product A. According to the existing scheme, it is impossible to determine whether the user has returned the product A. After the user picks up the new product, it may put back the product that was taken before. For example, the user has taken the product A and the product B, and the weight of the product B is much larger than the weight of the product A.
  • the present disclosure uses the weight data in the weight rise time interval to determine the maximum weight of the product that the user may put back, can predict whether the product that has been taken is put back, and can assist the unmanned sales container to calculate the user's purchase list.
  • the solution of the present application will be introduced below by taking specific embodiments as examples.
  • FIG. 3 is a schematic flowchart of some embodiments of a commodity detection method of the present disclosure.
  • the products that the user has taken and the weight data of each product are determined.
  • the commodities that the user has taken in the storage device and the weight data of each product are determined.
  • the storage device is, for example, a device capable of storing commodities and goods such as a container or a shelf.
  • there are products A, B, C, D, and E in the unmanned vending container the weight data of each product is known, and the user has taken the product A and the product B in the container.
  • step 320 the weight data in the weight rise time interval when the user takes the goods to the gravity scale is stable, wherein the gravity scale is used to detect the weight of the remaining goods in the container.
  • the gravity scale is used to detect the weight of the remaining goods in the container.
  • the weight rise time interval is the to-t1 interval
  • the weight rise time interval is the t6-t7 interval
  • the weight data in the weight rise time interval corresponds to the to-t1 interval
  • Weight data or weight data corresponding to the interval t6-t7.
  • the corresponding relationship between time and weight may be a graph or specific data in a data table.
  • the maximum replacement weight data is determined according to the difference between the maximum weight data and the minimum weight data in the weight data within the weight rise time interval. As shown in Figure 1, the maximum weight data is G2, the minimum weight data is G1, and the maximum replacement weight data is G2-G1. As shown in Figure 2, the maximum weight data is G5, the minimum weight data is G4, and the maximum replacement weight data is G5-G4.
  • the maximum weight data is greater than the weight data at the previous moment and greater than the weight data at the later moment, and the minimum weight data is less than the weight data at the previous moment and less than the weight data at the latter moment.
  • the difference between the maximum weight data and the minimum weight data in each weight rise time interval is obtained, and the maximum difference value is used as the maximum return weight data. For example, if the user has taken and put back the product multiple times, there may be multiple weight rise time intervals, then the difference between the maximum weight data and the minimum weight data of each weight rise time interval should be obtained, and the maximum difference value should be obtained. As the maximum return weight data.
  • step 340 based on the maximum replacement weight data and the weight data of each commodity, it is estimated whether each commodity is replaced. For example, analyze the taken products one by one. For the product A taken by the user, if the weight of the product A is greater than the maximum replacement weight, it is considered that the user has not returned the product A, as shown in FIG. 1, if the weight of the product A If the value is greater than G2-G1, it means that the user has not put back the product A. If the weight of the product A is less than or equal to the maximum replacement weight, it is considered that the user may have replaced the product A.
  • relying solely on the weight data may not be able to accurately guess the product purchased by the user. Therefore, after estimating whether each product is placed back, it is possible to refer to other data to determine whether the product is actually placed back. For example, comprehensive judgment can be made with reference to visual data.
  • the maximum replacement weight data is determined, and then the maximum replacement weight is compared
  • the data and the weight data of each product estimate whether each product is returned, which improves the accuracy of whether the estimated product is returned, and thus improves the accuracy of calculating the user's purchased product.
  • the user can construct the weight data change waveform by taking the weight data in the process of taking the goods, as shown in FIGS. 1 and 2, and then find the replacement pulse according to the weight change waveform, where,
  • the replacement pulse is a piece of waveform that rises monotonously during the weight change, and the weight difference corresponding to the waveform is the maximum replacement weight.
  • a predetermined number of noises that do not conform to the monotonous rise rule are allowed, for example, one or two noises that do not conform to the monotonous rise rule are allowed.
  • FIG. 4 is a schematic flowchart of some embodiments of determining the maximum replacement weight data in the commodity detection method of the present disclosure.
  • step 410 the weight data at the first moment and the weight data at the second moment detected by the gravity scale are obtained, wherein the second moment is later than the first moment, and the second moment is adjacent to the first moment, the first moment
  • the initial value of is the starting time
  • the weight data at the starting time is the minimum weight data.
  • the difference between the second time and the first time can be set according to specific actual conditions, and the difference between the second time and the first time reflects the detection accuracy of the gravity scale.
  • step 420 it is determined whether the weight data at the second time is greater than the weight data at the first time. If so, step 430 is executed; otherwise, step 440 is executed.
  • step 430 the weight data at the first time and the weight data at the second time are the weight data in the weight rise time interval.
  • step 431 it is determined whether the second time is the end time, if yes, step 432 is executed, otherwise, step 433 is executed.
  • step 432 the weight data at the second moment is used as the maximum weight data, and step 460 is subsequently performed.
  • step 433 the second time is regarded as the first time, and the next time of the second time is regarded as the second time, and then step 420 is continued.
  • step 440 it is determined whether the weight data at the second time is smaller than the weight data at the first time. If yes, step 441 is executed; otherwise, step 450 is executed.
  • step 441 it is determined whether the number of times the weight data has fallen is greater than or equal to the threshold of the number of noises between the starting time and the second time. If so, step 442 is executed; otherwise, step 443 is executed.
  • step 442 the second time is taken as the starting time, and step 420 is executed again.
  • step 443 the second time is taken as the first time, the next time of the second time is taken as the second time, and step 420 is executed again.
  • step 450 if the weight data before the first time is greater than the weight data at the first time, then it is determined whether the number of times the weight data has fallen is greater than the noise frequency threshold between the starting time and the second time. If so, step 451 is executed. Otherwise, go to step 452.
  • the threshold of the number of noise times is, for example, once or twice.
  • step 451 the second time is taken as the starting time, and step 420 is executed again.
  • step 452 the second time is regarded as the first time, the next time as the second time is regarded as the second time, and step 420 is executed again.
  • step 460 the difference between the maximum weight data and the minimum weight data in the weight data in the weight rise time interval is taken as the maximum replacement weight data.
  • the weight data in the weight rise time interval can be determined Determine the maximum return weight data to facilitate subsequent comparison of the maximum return weight data with the weight data of each commodity to estimate whether each commodity will be returned to the container.
  • FIG. 5 is a schematic flowchart of a specific embodiment of determining the maximum replacement weight data in the commodity detection method of the present disclosure.
  • step 510 the weight data w 0 , w 1 , ..., w n at each moment in the weight change waveform are obtained.
  • the starting point of the pulse is the starting point of the weight rise time interval.
  • step 530 it is determined whether w i is greater than w i-1 . If it is, it means that the waveform is in the rising band. Step 540 is executed; otherwise, step 550 is executed.
  • step 580 the number of descents is corrected.
  • step 550 it is determined whether w i is less than w i-1 . If yes, it means that the waveform is in the falling band, and step 560 is executed; otherwise, step 570 is executed.
  • w i -w i-1 it needs to be processed according to the direction of ws change.
  • step 590 it is judged whether i is less than or equal to n, if yes, step 530 is executed, otherwise, step 5100 is executed.
  • a continuous waveform of monotonous rise is found based on the weight data at each moment in the weight change waveform, where the waveform allows for some noise that does not conform to the law of monotonous rise, and then the maximum weight value is output for subsequent follow-up based on The maximum return weight value estimates whether the goods are returned to the container.
  • the weight of the product A is 50g
  • the weight of the product B is 100g
  • the weight of the product C is 150g
  • the maximum replacement weight data is less than 100g, and the second, third, and fourth possibilities may be excluded. If the calculated maximum return weight data is less than 150g, the third and fourth possibilities can be excluded.
  • the commodity detection device includes a taken commodity data determination unit 610, a weight data acquisition unit 620, a maximum replacement data determination unit 630, and a commodity replacement prediction unit 640.
  • the taken commodity data determination unit 610 is configured to determine the commodity that the user has taken and the weight data of each commodity. For example, the goods that the user has taken in the storage device and the weight data of each product are determined.
  • the storage device is, for example, a device that can store goods and goods, such as a container or a shelf. In some embodiments, there are products A, B, C, D, and E in the unmanned vending container, the weight data of each product is known, and the user has taken the product A and the product B in the container.
  • the weight data acquiring unit 620 is configured to acquire weight data in the weight rise time interval when the user takes the goods until the gravity scale is stable, wherein the gravity scale is used to detect the weight of the goods in the container. As shown in the data detected by the gravity scale shown in FIG. 1, after the users take the products A and B, they take the product C heavier than the product A before the gravity scale stabilizes, or as shown in the data detected by the gravity scale in FIG. 2, the user After taking the lighter product D, the product A was put back before the gravity scale stabilized.
  • the weight rise time interval is the to-t1 interval
  • the weight rise time interval is the t6-t7 interval
  • the weight data in the weight rise time interval corresponds to the to-t1 interval.
  • Weight data, or weight data corresponding to the interval t6-t7 may be a graph or specific data in a data table.
  • the weight data at the first moment and the weight data at the second moment detected by the gravity scale are obtained, wherein the second moment is later than the first moment, and the second moment is adjacent to the first moment, the first
  • the initial value of the time is the starting time, and the weight data at the starting time is the minimum weight data; determine whether the weight data at the second time is greater than the weight data at the first time; if the weight data at the second time is greater than the weight data at the first time, then The weight data at the first moment and the weight data at the second moment are the weight data in the weight rise time interval; determine whether the second moment is the end moment, and if so, use the weight data at the second moment as the maximum weight data, otherwise, The second time is regarded as the first time, and the time next to the second time is regarded as the second time.
  • the weight data at the second time is smaller than the weight data at the first time, it is determined whether the number of times the weight data has fallen is greater than or equal to the threshold of the number of noises from the starting time to the second time. Let the second moment be the first moment, and the next moment of the second moment as the second moment.
  • the weight data at the second time is equal to the weight data at the first time, and the weight data at the previous time at the first time is greater than the weight data at the first time, it is determined whether the number of times the weight data has fallen between the starting time and the second time If it is greater than the threshold of the number of noises, if it is, the second time is taken as the starting time, otherwise, the second time is taken as the first time, and the next time of the second time is taken as the second time.
  • the maximum replacement data determination unit 630 is configured to determine the maximum replacement weight data according to the difference between the maximum weight data and the minimum weight data in the weight data in the weight rise time interval. As shown in Figure 1, the maximum weight data is G2, the minimum weight data is G1, and the maximum replacement weight data is G2-G1. As shown in Figure 2, the maximum weight data is G5, the minimum weight data is G4, and the maximum replacement weight data is G5-G4.
  • the maximum weight data is greater than the weight data at the previous moment and greater than the weight data at the later moment, and the minimum weight data is less than the weight data at the previous moment and less than the weight data at the latter moment.
  • the difference between the maximum weight data and the minimum weight data in each weight rise time interval is obtained, and the maximum difference value is used as the maximum return weight data.
  • the commodity replacement estimation unit 640 is configured to estimate whether each commodity is to be replaced based on the maximum replacement weight data and the weight data of each commodity.
  • the taken products one by one. For the product A taken by the user, if the weight of the product A is greater than the maximum replacement weight, it is considered that the user has not returned the product A, as shown in FIG. 1, if the weight of the product A If the value is greater than G2-G1, it means that the user did not put back the product A, otherwise, it is considered that the user may put back the product A.
  • the difference between the weight data detected by the gravity scale after the user takes the product and the weight data detected after the gravity scale is stable is not equal to the weight data of the product A. For example, if the value of G1-G3 is not equal to the weight data of the product A , Then consider the possibility of the user taking back other products while returning the product A.
  • relying solely on the weight data may not be able to accurately guess the goods purchased by the user. Therefore, after estimating whether each product is placed back, you can refer to other data to determine whether the goods are actually placed back. For example, comprehensive judgment can be made with reference to visual data.
  • the maximum replacement weight data is determined, and then the maximum replacement weight is compared.
  • the data and the weight data of each product predict whether each product is returned, which improves the accuracy of detecting whether the product is returned, and can assist in calculating the products purchased by the user.
  • the device includes a memory 710 and a processor 720, where the memory 710 may be a magnetic disk, flash memory, or any other non-volatile storage medium.
  • the memory is configured to store instructions in the embodiments corresponding to FIGS. 3-5.
  • the processor 720 is coupled to the memory 710, and may be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller.
  • the processor 720 is configured to execute instructions stored in the memory.
  • the device 800 includes a memory 810 and a processor 820.
  • the processor 820 is coupled to the memory 810 through the BUS bus 830.
  • the device 800 can also be connected to the external storage device 850 through the storage interface 840 to call external data, and can also be connected to the network or another computer system (not marked) through the network interface 860, which will not be described in detail here.
  • storing the data instruction through the memory and then processing the above instruction through the processor can improve the accuracy of detecting whether the commodity is put back.
  • a computer-readable storage medium has stored thereon computer program instructions, which when executed by a processor, implements the steps of the method in the embodiments corresponding to FIGS. 3-5.
  • the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware.
  • the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code .
  • each flow and/or block in the flowchart and/or block diagram and a combination of the flow and/or block in the flowchart and/or block diagram may be implemented by computer program instructions.
  • These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processing machine, or other programmable data processing device to produce a machine that enables the generation of instructions executed by the processor of the computer or other programmable data processing device
  • These computer program instructions may also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, the instructions
  • the device implements the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps are performed on the computer or other programmable device to produce computer-implemented processing, which is executed on the computer or other programmable device
  • the instructions provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.

Landscapes

  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

公开了一种商品检测方法和装置，该方法包括：确定用户已拿取的商品和各商品的重量数据（310）；获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据（320），其中，重力秤用于检测商品的重量；根据重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据（330）；根据最大放回重量数据与各商品的重量数据，预估各商品是否被放回（340）。该方法和装置可提高预估商品是否被放回的准确性，进而提高推算出用户购买商品的准确性。

Description

商品检测方法和装置
相关申请的交叉引用
本申请是以CN申请号为201811420721.2，申请日为2018年11月27日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及数据处理领域，尤其涉及一种商品检测方法和装置。
背景技术
目前，市面上广泛使用的自动售货机，虽然在支付手段上有所突破，但有着不可避免的缺陷。例如，自动售货机在顾客购买商品后，仍需借助机械机构将商品传送出售货机，机械结构容易发生故障，对整个自动售货机的系统造成不良影响；另外，顾客利用现有的自动售货机，在选购商品之前，只能通过观察窗口看到商品的样品或者商品图片，无法直观地选择商品，一旦拿到商品后无法再更改选择，使得顾客的购物体验较差。
现在，市面上出现了若干新型无人售货柜，能够让顾客打开柜门后如同在超市一样自助选取商品，无人售货柜通过RFID(Radio Frequency Identification，射频识别)标签、重力推算、图像识别等技术手段推算顾客购买商品，顾客关门后智能结算。毫无疑问，这种用户体验更佳、占地面积更小、更具科技感的购物方式，将会是未来零售行业的一个主流发展方向。
发明内容
根据本公开一方面，提出一种商品检测方法，包括：确定用户已拿取的商品和各商品的重量数据；获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，重力秤用于检测商品的重量；根据重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据；根据最大放回重量数据与各商品的重量数据，预估各商品是否被放回。
在一些实施例中，若某个商品的重量数据大于最大放回重量数据，则预估该商品没有被放回；若某个商品的重量数据小于等于最大放回重量数据，则预估该商品被放 回。
在一些实施例中，若某个商品的重量数据小于等于最大放回重量数据，且用户拿取商品后重力秤检测的重量数据与重力秤稳定后检测的重量数据之差，与该商品的重量数据不相等，则预估该商品被放回，并且用户又拿取了其他商品。
在一些实施例中，最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据，最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
在一些实施例中，若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
在一些实施例中，获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，第二时刻晚于第一时刻，第二时刻与第一时刻为相邻时刻，第一时刻的初始值为起点时刻，起点时刻的重量数据为最小重量数据；判断第二时刻的重量数据是否大于第一时刻的重量数据；若第二时刻的重量数据大于第一时刻的重量数据，则第一时刻的重量数据和第二时刻的重量数据为重量上升时间区间内的重量数据；判断第二时刻是否为结束时刻，若是，则将第二时刻的重量数据作为最大重量数据，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
在一些实施例中，若第二时刻的重量数据小于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
在一些实施例中，若第二时刻的重量数据等于第一时刻的重量数据，且第一时刻的前一时刻的重量数据大于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
根据本公开的另一方面，还提出一种商品检测装置，包括：已拿商品数据确定单元，被配置为确定用户已拿取的商品和各商品的重量数据；重量数据获取单元，被配置为获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，重力秤用于检测商品的重量；最大放回数据确定单元，被配置为根据重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据；商品放回预估单元，被配置为根据最大放回重量数据与各商品的重量数据，预估各商品是否被放回。
在一些实施例中，商品放回预估单元被配置为若某个商品的重量数据大于最大放回重量数据，则预估该商品没有被放回，若某个商品的重量数据小于等于最大放回重量数据，则预估该商品被放回。
在一些实施例中，商品放回预估单元还被配置为若某个商品的重量数据小于等于最大放回重量数据，且用户拿取商品后重力秤检测的重量数据与重力秤稳定后检测的重量数据之差，与该商品的重量数据不相等，则预估该商品被放回，并且用户又拿取了其他商品。
在一些实施例中，最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据，最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
在一些实施例中，最大放回数据确定单元被配置为若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
在一些实施例中，重量数据获取单元被配置为获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，第二时刻晚于第一时刻，第二时刻与第一时刻为相邻时刻，第一时刻的初始值为起点时刻，起点时刻的重量数据为最小重量数据；判断第二时刻的重量数据是否大于第一时刻的重量数据；若第二时刻的重量数据大于第一时刻的重量数据，则第一时刻的重量数据和第二时刻的重量数据为重量上升时间区间内的重量数据；判断第二时刻是否为结束时刻，若是，则将第二时刻的重量数据作为最大重量数据，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
在一些实施例中，重量数据获取单元被配置为若第二时刻的重量数据小于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
在一些实施例中，重量数据获取单元被配置为若第二时刻的重量数据等于第一时刻的重量数据，且第一时刻的前一时刻的重量数据大于第一时刻的重量数据，则判断起点时刻到第二时刻之间重量数据下降次数是否大于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
根据本公开的另一方面，还提出一种商品检测装置，包括：存储器；以及耦接至 存储器的处理器，处理器被配置为基于存储在存储器的指令执行如上述的商品检测方法。
根据本公开的另一方面，还提出一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现上述的商品检测方法。
通过以下参照附图对本公开的示例性实施例的详细描述，本公开的其它特征及其优点将会变得清楚。
附图说明
构成说明书的一部分的附图描述了本公开的实施例，并且连同说明书一起用于解释本公开的原理。
参照附图，根据下面的详细描述，可以更加清楚地理解本公开，其中：
图1为一些实施例中用户放回某商品又拿取其他商品后的重力变化曲线图。
图2为另一些实施例中用户放回某商品又拿取其他商品后的重力变化曲线图。
图3为本公开商品检测方法的一些实施例的流程示意图。
图4为本公开商品检测方法中，确定最大放回重量数据的一些实施例的流程示意图。
图5为本公开商品检测方法中，确定最大放回重量数据的一个具体实施例的流程示意图。
图6为本公开商品检测装置的一些实施例的结构示意图。
图7为本公开商品检测装置的另一些实施例的结构示意图。
图8为本公开商品检测装置的再一些实施例的结构示意图。
具体实施方式
现在将参照附图来详细描述本公开的各种示例性实施例。应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。
同时，应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为授权说明书的一部分。
在这里示出和讨论的所有示例中，任何具体值应被解释为仅仅是示例性的，而不是作为限制。因此，示例性实施例的其它示例可以具有不同的值。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
为使本公开的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本公开进一步详细说明。
申请人发现，用户在拿取/放回商品的过程中，会对重力秤施加压力，由于重力秤的稳定也需要一定时间，因此，在用户拿取/放回商品过程中，重力秤的读数会不断发生变化。现有使用重力信息的无人售货柜，仅仅考虑重力秤稳定后的重力值，并利用重力秤初始和稳定后的重力差来确定用户拿取或者放回的商品重量。比如，无人售货柜已经计算出当前用户拿取了商品A和B，此时重力秤的读数又发生新的变化，重力秤稳定后，货柜增加的重量等于商品A的重量，则认为用户放回了商品A。然而，相关方案仅利用重力秤初始重力信息和稳定后的重力信息，对拿取/放回过程中的重力信息缺乏有效利用。
在一些实施例中，用户放回商品后，可能又马上拿取了新的商品。例如，用户已经拿取了商品A和商品B，商品B的重量远远大于商品A的重量，如果用户放回了商品A，在重力秤稳定前又拿取了重量较A重的商品C，此时的重力变化曲线如图1所示，重力秤初始和稳定后的重量差等于商品C和商品A的重量差，按照现有方案，将无法判断用户是否放回了商品A。用户拿取了新的商品后，可能又放回之前拿取的商品。例如，用户已经拿取了商品A和商品B，商品B的重量远远大于商品A的重量，如果用户在又拿取了重量较轻的商品D后，在重力秤稳定前又放回了商品A，此时的重力变化曲线如图2所示。重力秤初始和稳定后的重量差等于商品A和商品D的重量差，将无法判断用户是否放回了商品A。
本公开利用重量上升时间区间内的重量数据，判断用户可能放回的商品的最大重量，可以预估已拿取的商品是否被放回，进而可以辅助无人售货柜推算出用户的购买清单。下面将以具体实施例为例对本申请的方案进行介绍。
图3为本公开商品检测方法的一些实施例的流程示意图。
在步骤310，确定用户已拿取的商品和各商品的重量数据。例如，确定用户在储 物装置中已拿取的商品和各商品的重量数据，储物装置例如为货柜或货架等能够存放商品、货物的装置。在一些实施例中，无人售货柜中有商品A、B、C、D、E，各商品的重量数据已知，用户在货柜中已拿取商品A和商品B。
在步骤320，获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，重力秤用于检测货柜中剩余商品的重量。如图1重力秤检测的数据所示，用户拿取商品A和B后，在重力秤稳定前又拿取了比商品A重的商品C，或者如图2重力秤检测的数据所示，用户拿取了较轻的商品D后，在重力秤稳定前又放回了商品A。从图1中可以看出，重量上升时间区间为to-t1区间，从图2中可以看出，重量上升时间区间为t6-t7区间，重量上升时间区间内的重量数据即to-t1区间对应的重量数据，或者t6-t7区间对应的重量数据。本领域的技术人员应当理解，时间和重量之间的对应关系可以是曲线图，也可以为数据表中的具体数据。
在步骤330，根据重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据。如图1所示，最大重量数据为G2，最小重量数据为G1，最大放回重量数据为G2-G1。如图2所示，最大重量数据为G5，最小重量数据为G4，最大放回重量数据为G5-G4。
在一些实施例中，最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据，最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
在一些实施例中，若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。例如，若用户存在多次拿取、放回商品的情况，则可能出现多个重量上升时间区间，则应当获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
在步骤340，根据最大放回重量数据与各商品的重量数据，预估各商品是否被放回。例如，对已拿取的商品逐个分析，对于用户拿取的商品A，如果商品A的重量大于最大放回重量，则认为用户没有放回商品A，如图1所示，若商品A的重量大于G2-G1的值，则说明用户没有放回商品A。如果商品A的重量小于等于最大放回重量，则认为用户可能放回了商品A。若重力秤初始检测的重量数据，与重力秤稳定后检测的重量数据之差，与商品A的重量数据不相等，例如，若G1-G3的值与商品A的重量数据不相等，则考虑用户放回商品A的同时，有拿取其他商品的可能性。
在一些实施例中，完全依靠重量数据可能不能完全准确猜对用户购买的商品，因 此，预估各商品是否被放回后，可以参考其他数据综合判断商品是否被真正放回。例如，可以参考视觉数据等进行综合判断。
在上述实施例中，根据用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据，然后比较最大放回重量数据与各商品的重量数据，预估各商品是否被放回，提高了预估商品是否被放回的准确性，进而提高了推算出用户购买商品的准确性。
在本公开的一个具体实施例中，可以将用户拿取商品过程中的重量数据构建重量数据变化波形，即如图1和图2所示，然后根据重量变化波形，找到放回脉冲，其中，放回脉冲即重量变化过程中单调上升的一段波形，该波形对应的重量差值即最大放回重量。
在一些实施例中，由于重力秤的检测有可能有偏差，因此，允许有预定个不符合单调上升规律的噪点，例如，允许一个或两个不符合单调上升规律的噪点。
图4为本公开商品检测方法中，确定最大放回重量数据的一些实施例的流程示意图。
在步骤410，获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，第二时刻晚于第一时刻，且第二时刻与第一时刻为相邻时刻，第一时刻的初始值为起点时刻，起点时刻的重量数据为最小重量数据。其中，第二时刻与第一时刻之间的差值可以根据具体实际情况进行设置，第二时刻与第一时刻之间的差值反映重力秤的检测精度。
在步骤420，判断第二时刻的重量数据是否大于第一时刻的重量数据，若是，则执行步骤430，否则，执行步骤440。
在步骤430，第一时刻的重量数据和第二时刻的重量数据为重量上升时间区间内的重量数据。
在步骤431，判断第二时刻是否为结束时刻，若是，则执行步骤432，否则，执行步骤433。
在步骤432，将第二时刻的重量数据作为最大重量数据，后续执行步骤460。
在步骤433，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻，后续继续执行步骤420。
在步骤440，判断第二时刻的重量数据是否小于第一时刻的重量数据，若是，则执行步骤441，否则，执行步骤450。
在步骤441，判断起点时刻到第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则执行步骤442，否则，执行步骤443。
在步骤442，将第二时刻作为起点时刻，并重新执行步骤420。
在步骤443，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻，并重新执行步骤420。
在步骤450，第一时刻的前一时刻的重量数据大于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于噪声次数阈值，若是，则执行步骤451，否则，执行步骤452。其中，噪声次数阈值例如为1次或者2次。
在步骤451，将第二时刻作为起点时刻，并重新执行步骤420。
在步骤452，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻，并重新执行步骤420。
在步骤460，将重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，作为最大放回重量数据。
在该实施例中，通过相邻时刻的重量数据大小的比较，以及判断起点时刻到第二时刻之间重量数据下降次数是否大于噪声次数阈值，能够确定重量上升时间区间内的重量数据，进而可以确定最大放回重量数据，便于后续通过比较最大放回重量数据与各商品的重量数据，预估各商品是否被放回到货柜中。
图5为本公开商品检测方法中，确定最大放回重量数据的一个具体实施例的流程示意图。
在步骤510，获取重量变化波形中各时刻的重量数据w 0,w 1,...,w n。
在步骤520，记录脉冲起点is＝0,初始最大放回重量out＝0,初始下降次数dt＝0，最大下降次数mdt＝2,变化方向ws＝0，计数器i＝1。其中，脉冲起点即重量上升时间区间的起始点，变化方向ws＝0，表示波形方向没有变化，ws＝1表示波形方向为正，ws＝-1表示波形方向为负。
在步骤530，判断w i是否大于w i-1，若是，则说明波形处于上升波段，执行步骤540，否则，执行步骤550。
在步骤540，修正下降次数，如果dt>0，dt＝dt-1，更新最大放回重量out＝max(out,w i-w is)，记录波形变化方向ws＝1。后续执行步骤580。
在步骤550，判断w i是否小于w i-1，若是，则说明波形处于下降波段，执行步骤560，否则，执行步骤570。
在步骤560，记录下降次数dt＝dt+1，如果dt>＝mdt，重新初始化脉冲起点is＝i，dt＝0，记录波形变化方向ws＝-1。后续执行步骤580。
在步骤570，ws＝-1，认为此时波形仍处于下降波段，则执行步骤571。在w i-w i-1时，需要根据ws变化方向进行处理。
在步骤571，记录下降次数，dt＝dt+1，如果dt>＝mdt，重新初始化脉冲起点is＝i，dt＝0，记录波形变化方向ws＝-1。后续执行步骤580。
在步骤580，更新计数器i＝i+1。
在步骤590，判断i是否小于等于n，若是，则执行步骤530，否则，执行步骤5100。
在步骤5100，输出out作为最大放回重量。
在上述实施例中，基于重量变化波形中各时刻的重量数据找到单调上升的一段连续波形，其中，该波形允许有部分不符合单调上升规律的噪点，进而输出最大放回重量值，以便后续基于最大放回重量值预估商品是否被放回到货柜中。
在一个具体实施例中，假设商品A重量为50g，商品B重量为100g，商品C重量为150g，那么如果重力秤的重量增加了50g，可以认为有4种可能：1、用户放回了商品A；2、用户放回了商品B并且拿取了商品A；3、用户放回了商品C并且拿取了商品B；4、用户放回了商品C并且拿取了2个商品A。根据本公开计算出最大放回重量数据小于100g，则可以排除第2、3、4种可能。如果计算出最大放回重量数据小于150g，则可以排除第3、4种可能。
图6为本公开商品检测装置的一些实施例的结构示意图。该商品检测装置包括已拿商品数据确定单元610、重量数据获取单元620、最大放回数据确定单元630、商品放回预估单元640。
已拿商品数据确定单元610被配置为确定用户已拿取的商品和各商品的重量数据。例如，确定用户在储物装置中已拿取的商品和各商品的重量数据，储物装置例如为货柜或货架等能够存放商品、货物的装置。在一些实施例中，无人售货柜中有商品A、B、C、D、E，各商品的重量数据已知，用户在货柜中已拿取商品A和商品B。
重量数据获取单元620被配置为获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，重力秤用于检测货柜中商品的重量。如图1重力秤检测的数据所示，用户拿取商品A和B后，在重力秤稳定前又拿取了比商品A重的商品C，或者如图2重力秤检测的数据所示，用户拿取了较轻的商品D后，在重力秤稳定前又放回了商品A。从图1中可以看出，重量上升时间区间为to-t1区间，从图2中可以看 出，重量上升时间区间为t6-t7区间，重量上升时间区间内的重量数据即to-t1区间对应的重量数据，或者t6-t7区间对应的重量数据。本领域的技术人员应当理解，时间和重量之间的对应关系可以是曲线图，也可以为数据表中的具体数据。
在一些实施例中，获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，第二时刻晚于第一时刻，第二时刻与第一时刻为相邻时刻，第一时刻的初始值为起点时刻，起点时刻的重量数据为最小重量数据；判断第二时刻的重量数据是否大于第一时刻的重量数据；若第二时刻的重量数据大于第一时刻的重量数据，则第一时刻的重量数据和第二时刻的重量数据为重量上升时间区间内的重量数据；判断第二时刻是否为结束时刻，若是，则将第二时刻的重量数据作为最大重量数据，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
若第二时刻的重量数据小于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
若第二时刻的重量数据等于第一时刻的重量数据，且第一时刻的前一时刻的重量数据大于第一时刻的重量数据，则判断起点时刻到第二时刻之间，重量数据下降次数是否大于噪声次数阈值，若是，则将第二时刻作为起点时刻，否则，将第二时刻作为第一时刻，将第二时刻的下一时刻作为第二时刻。
最大放回数据确定单元630被配置为根据重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据。如图1所示，最大重量数据为G2，最小重量数据为G1，最大放回重量数据为G2-G1。如图2所示，最大重量数据为G5，最小重量数据为G4，最大放回重量数据为G5-G4。
在一些实施例中，最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据，最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
在一些实施例中，若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
商品放回预估单元640被配置为根据最大放回重量数据与各商品的重量数据，预估各商品是否被放回。
例如，对已拿取的商品逐个分析，对于用户拿取的商品A，如果商品A的重量大于最大放回重量，则认为用户没有放回商品A，如图1所示，若商品A的重量大于G2-G1的值，则说明用户没有放回商品A，否则，认为用户可能放回了商品A。此时 用户拿取商品后重力秤检测的重量数据与重力秤稳定后检测的重量数据之差，与商品A的重量数据不相等，例如，若G1-G3的值与商品A的重量数据不相等，则考虑用户放回商品A的同时拿取其他商品的可能性。
在一些实施例中，完全依靠重量数据可能不能完全准确猜对用户购买的商品，因此，预估各商品是否被放回后，可以参考其他数据综合判断商品是否被真正放回。例如，可以参考视觉数据等进行综合判断。
在该实施例中，根据用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据，然后比较最大放回重量数据与各商品的重量数据，预估各商品是否被放回，提高了检测商品是否被放回的准确性，进而能够辅助推算出用户购买的商品。
图7为本公开商品检测装置的另一些实施例的结构示意图。该装置包括存储器710和处理器720，其中：存储器710可以是磁盘、闪存或其它任何非易失性存储介质。存储器被配置为存储图3-5所对应实施例中的指令。处理器720耦接至存储器710，可以作为一个或多个集成电路来实施，例如微处理器或微控制器。该处理器720被配置为执行存储器中存储的指令。
在一些实施例中，还可以如图8所示，该装置800包括存储器810和处理器820。处理器820通过BUS总线830耦合至存储器810。该装置800还可以通过存储接口840连接至外部存储装置850以便调用外部数据，还可以通过网络接口860连接至网络或者另外一台计算机系统(未标出)，此处不再进行详细介绍。
在该实施例中，通过存储器存储数据指令，再通过处理器处理上述指令，能够提高检测商品是否被放回的准确性。
在另一些实施例中，一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现图3-5所对应实施例中的方法的步骤。本领域内的技术人员应明白，本公开的实施例可提供为方法、装置、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(系统)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的 每一流程和/或方框以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
至此，已经详细描述了本公开。为了避免遮蔽本公开的构思，没有描述本领域所公知的一些细节。本领域技术人员根据上面的描述，完全可以明白如何实施这里公开的技术方案。
虽然已经通过示例对本公开的一些特定实施例进行了详细说明，但是本领域的技术人员应该理解，以上示例仅是为了进行说明，而不是为了限制本公开的范围。本领域的技术人员应该理解，可在不脱离本公开的范围和精神的情况下，对以上实施例进行修改。本公开的范围由所附权利要求来限定。

Claims (18)

  1. 一种商品检测方法，包括：
    确定用户已拿取的商品和各商品的重量数据；
    获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，所述重力秤用于检测商品的重量；
    根据所述重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据；
    根据所述最大放回重量数据与各商品的重量数据，预估各商品是否被放回。
  2. 根据权利要求1所述的商品检测方法，其中，
    若某个商品的重量数据大于所述最大放回重量数据，则预估该商品没有被放回；
    若某个商品的重量数据小于等于所述最大放回重量数据，则预估该商品被放回。
  3. 根据权利要求2所述的商品检测方法，其中，
    若某个商品的重量数据小于等于所述最大放回重量数据，且用户拿取商品后所述重力秤检测的重量数据与所述重力秤稳定后检测的重量数据之差，与该商品的重量数据不相等，则预估该商品被放回，并且用户又拿取了其他商品。
  4. 根据权利要求1所述的商品检测方法，其中，
    所述最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据；
    所述最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
  5. 根据权利要求1所述的商品检测方法，其中，
    若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
  6. 根据权利要求1-5任一所述的商品检测方法，其中，
    获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，所述第二时刻晚于所述第一时刻，所述第二时刻与所述第一时刻为相邻时刻，所述第一时刻的 初始值为起点时刻，所述起点时刻的重量数据为所述最小重量数据；
    判断所述第二时刻的重量数据是否大于所述第一时刻的重量数据；
    若所述第二时刻的重量数据大于所述第一时刻的重量数据，则所述第一时刻的重量数据和所述第二时刻的重量数据为所述重量上升时间区间内的重量数据；
    判断所述第二时刻是否为结束时刻，若是，则将所述第二时刻的重量数据作为最大重量数据，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  7. 根据权利要求6所述的商品检测方法，其中，
    若所述第二时刻的重量数据小于所述第一时刻的重量数据，则判断所述起点时刻到所述第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则将所述第二时刻作为所述起点时刻，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  8. 根据权利要求7所述的商品检测方法，其中，
    若所述第二时刻的重量数据等于所述第一时刻的重量数据，且所述第一时刻的前一时刻的重量数据大于所述第一时刻的重量数据，则判断起点时刻到所述第二时刻之间，重量数据下降次数是否大于噪声次数阈值，若是，则将所述第二时刻作为所述起点时刻，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  9. 一种商品检测装置，包括：
    已拿商品数据确定单元，被配置为确定用户已拿取的商品和各商品的重量数据；
    重量数据获取单元，被配置为获取用户拿取商品到重力秤稳定时，重量上升时间区间内的重量数据，其中，所述重力秤用于检测商品的重量；
    最大放回数据确定单元，被配置为根据所述重量上升时间区间内的重量数据中的最大重量数据与最小重量数据之差，确定最大放回重量数据；
    商品放回预估单元，被配置为根据所述最大放回重量数据与各商品的重量数据，预估各商品是否被放回。
  10. 根据权利要求9所述的商品检测装置，其中，
    所述商品放回预估单元被配置为若某个商品的重量数据大于所述最大放回重量数据，则预估该商品没有被放回，若某个商品的重量数据小于等于所述最大放回重量数据，则预估该商品被放回。
  11. 根据权利要求10所述的商品检测装置，其中，
    所述商品放回预估单元还被配置为若某个商品的重量数据小于等于所述最大放回重量数据，且用户拿取商品后所述重力秤检测的重量数据与所述重力秤稳定后检测的重量数据之差，与该商品的重量数据不相等，则预估该商品被放回，并且用户又拿取了其他商品。
  12. 根据权利要求9所述的商品检测装置，其中，
    所述最大重量数据大于前一时刻的重量数据且大于后一时刻的重量数据；
    所述最小重量数据小于前一时刻的重量数据且小于后一时刻的重量数据。
  13. 根据权利要求9所述的商品检测装置，其中，
    所述最大放回数据确定单元被配置为若存在多个重量上升时间区间，则获取每个重量上升时间区间最大重量数据与最小重量数据之差，并将最大差值作为最大放回重量数据。
  14. 根据权利要求9-13任一所述的商品检测装置，其中，
    所述重量数据获取单元被配置为获取重力秤检测的第一时刻的重量数据和第二时刻的重量数据，其中，所述第二时刻晚于所述第一时刻，所述第二时刻与所述第一时刻为相邻时刻，所述第一时刻的初始值为起点时刻，所述起点时刻的重量数据为所述最小重量数据；判断所述第二时刻的重量数据是否大于所述第一时刻的重量数据；若所述第二时刻的重量数据大于所述第一时刻的重量数据，则所述第一时刻的重量数据和所述第二时刻的重量数据为所述重量上升时间区间内的重量数据；判断所述第二时刻是否为结束时刻，若是，则将所述第二时刻的重量数据作为最大重量数据，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  15. 根据权利要求14所述的商品检测装置，其中，
    所述重量数据获取单元被配置为若所述第二时刻的重量数据小于所述第一时刻的重量数据，则判断所述起点时刻到所述第二时刻之间，重量数据下降次数是否大于等于噪声次数阈值，若是，则将所述第二时刻作为所述起点时刻，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  16. 根据权利要求15所述的商品检测方法，其中，
    所述重量数据获取单元被配置为若所述第二时刻的重量数据等于所述第一时刻的重量数据，且所述第一时刻的前一时刻的重量数据大于所述第一时刻的重量数据，则判断起点时刻到所述第二时刻之间，重量数据下降次数是否大于噪声次数阈值，若是，则将所述第二时刻作为所述起点时刻，否则，将所述第二时刻作为第一时刻，将所述第二时刻的下一时刻作为第二时刻。
  17. 一种商品检测装置，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器的指令执行如权利要求1至8任一项所述的商品检测方法。
  18. 一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现权利要求1至8任一项所述的商品检测方法。
PCT/CN2019/099052 2018-11-27 2019-08-02 商品检测方法和装置 WO2020107928A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2021530218A JP7524182B2 (ja) 2018-11-27 2019-08-02 商品検出方法および商品検出装置
US17/288,293 US20210383635A1 (en) 2018-11-27 2019-08-02 Commodity detection method and device
EP19890002.9A EP3855378A4 (en) 2018-11-27 2019-08-02 GOODS DETECTION METHOD AND DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811420721.2A CN110379070B (zh) 2018-11-27 2018-11-27 商品检测方法和装置
CN201811420721.2 2018-11-27

Publications (1)

Publication Number Publication Date
WO2020107928A1 true WO2020107928A1 (zh) 2020-06-04

Family

ID=68243115

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/099052 WO2020107928A1 (zh) 2018-11-27 2019-08-02 商品检测方法和装置

Country Status (5)

Country Link
US (1) US20210383635A1 (zh)
EP (1) EP3855378A4 (zh)
JP (1) JP7524182B2 (zh)
CN (1) CN110379070B (zh)
WO (1) WO2020107928A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111310618A (zh) * 2020-02-03 2020-06-19 北京百度网讯科技有限公司 物品识别方法、装置、电子设备及可读存储介质
CN111739091A (zh) * 2020-03-24 2020-10-02 北京京东乾石科技有限公司 一种物品放回检测方法、装置、设备及介质
CN113554802B (zh) * 2021-04-21 2023-06-02 浙江星星冷链集成股份有限公司 一种称重装置及无人售货系统
CN113554804B (zh) * 2021-04-21 2023-06-02 浙江星星冷链集成股份有限公司 一种稳定重量获取装置及无人售货系统
CN114092186B (zh) * 2021-11-18 2022-04-22 新石器慧通（北京）科技有限公司 用于检测售卖柜中的不合格商品的方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1736945A1 (en) * 2005-06-09 2006-12-27 Ncr International Inc. A weight validating self-checkout system employing a portable data register
JP6165455B2 (ja) * 2013-02-08 2017-07-19 株式会社フロウ 商品管理システム
CN107341655A (zh) * 2017-07-12 2017-11-10 杨智勇 零售店智能支付方法
CN107451776A (zh) * 2017-07-27 2017-12-08 惠州市伊涅科技有限公司 无人超市补货方法
CN108389315A (zh) * 2018-03-02 2018-08-10 北京京东尚科信息技术有限公司 物品识别方法和装置以及计算机可读存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8165929B2 (en) * 2008-08-04 2012-04-24 Chudy Group, LLC Adaptive pharmaceutical product management methods and system
WO2011001516A1 (ja) * 2009-06-30 2011-01-06 株式会社 東芝 チェックアウト装置、および作業状況計測装置
WO2016181352A1 (en) * 2015-05-14 2016-11-17 Inventorytech Limited Event detection system and method for real-time inventory management system
US10915910B2 (en) * 2015-12-09 2021-02-09 International Business Machines Corporation Passive analysis of shopping behavior in a physical shopping area using shopping carts and shopping trays
US11157922B2 (en) 2016-05-26 2021-10-26 Purchase Point Llc Smart display system
CN110738287B (zh) * 2016-08-31 2021-08-24 北京牧家科技有限公司 一种重力感应货柜系统
US10520353B1 (en) * 2016-12-22 2019-12-31 Amazon Technologies, Inc. System to process load cell data
CN106934692B (zh) * 2017-03-03 2020-12-22 陈维龙 物品信息处理系统、方法及装置
JP6760184B2 (ja) 2017-03-31 2020-09-23 トヨタ紡織株式会社 マニホールド
JP6342039B1 (ja) 2017-06-06 2018-06-13 株式会社 ディー・エヌ・エー 商品を管理するためのシステム、方法、及びプログラム
CN108335408B (zh) * 2018-03-02 2020-11-03 北京京东尚科信息技术有限公司 用于自动售货机的物品识别方法、装置、系统及存储介质
CN108564713A (zh) * 2018-03-23 2018-09-21 刘婧 一种基于综合测量方式的无人值守零售的商品识别和防作弊系统及其方法
US11436557B1 (en) * 2018-03-28 2022-09-06 Amazon Technologies, Inc. Interaction determination using data from weight sensors
CN108765704B (zh) * 2018-05-23 2020-07-24 济南每日优鲜便利购网络科技有限公司 自动售货系统补货控制方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1736945A1 (en) * 2005-06-09 2006-12-27 Ncr International Inc. A weight validating self-checkout system employing a portable data register
JP6165455B2 (ja) * 2013-02-08 2017-07-19 株式会社フロウ 商品管理システム
CN107341655A (zh) * 2017-07-12 2017-11-10 杨智勇 零售店智能支付方法
CN107451776A (zh) * 2017-07-27 2017-12-08 惠州市伊涅科技有限公司 无人超市补货方法
CN108389315A (zh) * 2018-03-02 2018-08-10 北京京东尚科信息技术有限公司 物品识别方法和装置以及计算机可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3855378A4 *

Also Published As

Publication number Publication date
CN110379070A (zh) 2019-10-25
EP3855378A4 (en) 2022-06-22
JP7524182B2 (ja) 2024-07-29
JP2022509846A (ja) 2022-01-24
US20210383635A1 (en) 2021-12-09
CN110379070B (zh) 2023-05-02
EP3855378A1 (en) 2021-07-28

Similar Documents

Publication Publication Date Title
WO2020107928A1 (zh) 商品检测方法和装置
US11983727B2 (en) System and method for data-driven insight into stocking out-of-stock shelves
CN108875664B (zh) 选购商品的识别方法、装置以及售货机
JP7248689B2 (ja) 自動販売方法および装置、ならびにコンピュータ可読記憶媒体
WO2019165894A1 (zh) 物品识别方法、装置、系统及存储介质
US11443291B2 (en) Tracking product items in an automated-checkout store
US11373160B2 (en) Monitoring shopping activities using weight data in a store
WO2019182948A1 (en) System and method for the determination of produce shelf life
WO2021042698A1 (zh) 基于视觉和重力感应的商品识别方法、装置和系统
US20150235239A1 (en) Predicting demand of a newly introduced short lifecycle product within an assortment
US20150112762A1 (en) Optimization of product assortments
CN111222870B (zh) 结算方法、装置和系统
WO2017037881A1 (ja) オンライン予測システムおよび方法
CN111126990B (zh) 物品自动识别方法、结算方法、装置、终端及存储介质
CN111723777A (zh) 商品取放过程判别方法、装置、智能货柜和可读存储介质
CN113743643A (zh) 一种确定商品数据预测准确率的方法、装置、设备和介质
JP2009251779A (ja) 販売数予測システム、販売数予測方法および販売数予測プログラム
JP6078014B2 (ja) 購買意欲学習装置、購買予測装置、方法、及びプログラム
CN111507792A (zh) 一种自助购物方法、计算机可读存储介质及系统
CN112561596A (zh) 商品推荐方法和装置
US11392879B2 (en) Operation estimating method and operation estimating system
JPWO2020107928A5 (zh)
US20200126026A1 (en) Generating customized alerts with computer vision and machine learning
CN109117828A (zh) 一种商品重放检测方法及其装置、电子设备
US20210397167A1 (en) Process improvement support device, process improvement support method, and recording medium storing process improvement support program

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19890002

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019890002

Country of ref document: EP

Effective date: 20210419

ENP Entry into the national phase

Ref document number: 2021530218

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE