CN111783513A - Cargo replenishing method, device and system - Google Patents

Cargo replenishing method, device and system Download PDF

Info

Publication number
CN111783513A
CN111783513A CN201911125556.2A CN201911125556A CN111783513A CN 111783513 A CN111783513 A CN 111783513A CN 201911125556 A CN201911125556 A CN 201911125556A CN 111783513 A CN111783513 A CN 111783513A
Authority
CN
China
Prior art keywords
goods
cargo
neural network
data
sales
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.)
Pending
Application number
CN201911125556.2A
Other languages
Chinese (zh)
Inventor
叶盛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information Technology Co Ltd
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 Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Priority to CN201911125556.2A priority Critical patent/CN111783513A/en
Publication of CN111783513A publication Critical patent/CN111783513A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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]
    • G06Q30/0623—Item investigation
    • G06Q30/0625—Directed, with specific intent or strategy
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects

Abstract

The disclosure provides a cargo supplementing method, a cargo supplementing device and a cargo supplementing system, and relates to the technical field of data processing. The cargo replenishing method comprises the following steps: acquiring a video image of a goods sales area; acquiring user behavior data and cargo attribute information according to the video image; determining goods and quantity to be supplemented based on a neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data; the replenishment of goods is performed according to the goods and the amount to be replenished. By the method, the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented can be predicted according to the video images and the sales data of the sales area, so that the quantity of the supplemented goods is matched with the quantity of expected sales, the supply and demand are reduced, and the waste caused by supply and demand is reduced.

Description

Cargo replenishing method, device and system
Technical Field
The disclosure relates to the technical field of data processing, in particular to a cargo supplementing method, device and system.
Background
Compared with the traditional supermarket with people for service, the unmanned supermarket can better reduce the labor cost, and a shop owner does not need to hire a large number of shop assistants to manage the supermarket any more, and meanwhile, more free and private purchasing options are provided for consumers.
The unmanned supermarket mostly adopts fixed time, people are sent regularly to manage commodities, special price or off-shelf treatment is carried out on the commodities close to the shelf life, and goods are supplemented in time when the commodities are sold out.
Disclosure of Invention
One object of the present disclosure is to improve the pertinence of restocking and the degree of matching of the number of restocking with the user's demand.
According to an aspect of some embodiments of the present disclosure, there is provided a cargo replenishment method including: acquiring a video image of a goods sales area; acquiring user behavior data and cargo attribute information according to the video image; determining goods and quantity to be supplemented based on a neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data; the replenishment of goods is performed according to the goods and the amount to be replenished.
In some embodiments, obtaining user behavior data from the video image comprises: intercepting each frame of image according to the video stream data and the time sequence; and carrying out displacement matching on the adjacent frame images to obtain user behavior data.
In some embodiments, obtaining cargo attribute information from the video image comprises: capturing the behavior of a user holding the goods according to the video image; acquiring an image of the goods held by the user according to the image frame including the goods holding behavior of the user; and determining the goods held by the user by matching the images of the goods held by the user with the stored goods image information, and acquiring the goods attribute information.
In some embodiments, the user behavior data comprises: the stay time in the current video capture area and the goods included in the current video capture area, the stay time of the user in each goods sales area and the corresponding goods, the time length for the user to pick up the goods and the picked up goods, the time length for the user to hold the goods and the held goods, and the time for the user to put back the goods and the put-back goods.
In some embodiments, the video image is an image within a predetermined time period; the goods sales data includes sales quantities of various goods within a predetermined time period.
In some embodiments, determining the goods and quantity to be replenished based on the neural network algorithm based on the user behavior data, the goods attribute information, and the goods sales data comprises: inputting user behavior data and cargo attribute information acquired according to video images in a preset time period into a Back Propagation (BP) neural network; inputting goods sales data extracted from sales data within the same preset time period into a BP neural network, wherein the BP neural network is generated based on user behavior data, goods attribute information and goods sales data training; determining the goods needing to be supplemented and the quantity of each goods needing to be supplemented based on the BP neural network.
In some embodiments, training the generation of the BP neural network based on the user behavior data, the cargo attribute information, and the cargo sales data comprises: inputting user behavior data, cargo attribute information and cargo sales data in a preset time period into a BP neural network; acquiring goods which are output by the BP neural network and need to be supplemented and the quantity of each goods which need to be supplemented; determining the prediction accuracy according to the data output by the BP neural network and the goods sales data in the next preset time period; and under the condition that the prediction accuracy is lower than the accuracy threshold, correcting the BP neural network, and continuing training the BP neural network until the prediction accuracy is not lower than the accuracy threshold.
In some embodiments, the predetermined time period matches a replenishment period.
By the method, the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented can be predicted according to the video images and the sales data of the sales area, so that the quantity of the supplemented goods is matched with the quantity of expected sales, the supply and demand are reduced, and the waste caused by supply and demand is reduced.
According to an aspect of other embodiments of the present disclosure, there is provided a cargo replenishing device including: an image acquisition unit configured to acquire a video image of a goods sales area; the image analysis unit is configured to acquire user behavior data and cargo attribute information according to the video image; the prediction unit is configured to determine goods needing to be supplemented and the quantity of the goods needing to be supplemented based on a neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data; and the replenishing unit is configured to prompt replenishment personnel to perform cargo replenishment according to the cargos to be replenished and the quantity.
According to an aspect of still further embodiments of the present disclosure, there is provided a cargo replenishing device including: a memory; and a processor coupled to the memory, the processor configured to perform any of the cargo replenishment methods above based on the instructions stored in the memory.
The device can predict the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented according to the video images and the sales data of the sales area, so that the quantity of the goods needing to be supplemented is matched with the quantity of expected sales, the supply shortage is reduced, and the waste caused by the supply exceeding the demand is also reduced.
In an aspect of still further embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, which instructions, when executed by a processor, implement the steps of any of the cargo replenishment methods described above.
By executing the instructions on the computer-readable storage medium, the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented can be predicted according to the video images and the sales data of the sales area, so that the quantity of the goods needing to be supplemented is matched with the quantity of expected sales, the supply shortage is reduced, and the waste caused by supply exceeding the demand is also reduced.
Additionally, according to an aspect of some embodiments of the present disclosure, there is provided a cargo replenishment system, comprising: an image capturing device configured to capture images of respective goods sales areas; and a cargo replenishing device as any one of the above.
The goods replenishment system can collect images of goods sales areas, predict the types of goods needing replenishment and the quantity of each kind of goods needing replenishment according to the video images and the sales data of the sales areas, so that the quantity of the replenished goods is matched with the quantity of expected sales, and the waste caused by supply and demand is reduced while the supply is short of the demand.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:
fig. 1 is a flow chart of some embodiments of a cargo replenishment method of the present disclosure.
Fig. 2 is a flow diagram of some embodiments of neural network training in the cargo replenishment method of the present disclosure.
Fig. 3 is a schematic view of some embodiments of the cargo replenishing device of the present disclosure.
Fig. 4 is a schematic view of further embodiments of the cargo replenishing device of the present disclosure.
Fig. 5 is a schematic view of further embodiments of the cargo replenishing device of the present disclosure.
Fig. 6 is a schematic view of some embodiments of cargo replenishment systems of the present disclosure.
Detailed Description
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
In the related art, a worker supplies a fixed amount of commodities at the time of replenishment, or replenishes commodities according to the consumption amount of each commodity. However, the inventor found that the former method may cause waste of manpower and goods in the case of a high replenishment frequency and quantity, and may cause shortage of goods in the case of a low replenishment frequency and quantity; the latter method does not fit well to the sales of the goods in the next cycle, resulting in a situation where supply is insufficient and supply is greater than demand.
A flow chart of some embodiments of the cargo replenishment method of the present disclosure is shown in fig. 1.
In step 101, a video image of a goods sales area is acquired. In some embodiments, the video images may be captured by one or more cameras deployed in a supermarket, a mall, and in particular an unmanned supermarket. In some embodiments, image data acquired by a camera video may be transcoded by a chip to be converted into a digital data stream, and the data is transmitted to a video analysis processing platform through an ethernet interface line for subsequent operations.
In step 102, user behavior data and cargo attribute information are obtained from the video image. In some embodiments, each frame of image may be truncated chronologically from the video stream data; and then, carrying out displacement matching on the adjacent frame images, removing background information to obtain a user image, and further acquiring user behavior data. In some embodiments, the duration of various behaviors of the user may be counted.
In step 103, the goods and the quantity to be supplemented are determined based on the neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data. In some embodiments, the neural network used is trained and generated based on user behavior data, cargo attribute information and cargo sales data over a period of time, and can predict the demand of various cargoes. In some embodiments, the neural network may be a BP neural network. In the process of inputting the user behavior data, the cargo attribute information and the cargo sales data into the neural network, the user behavior data and the cargo attribute information are input as reference conditions, and the cargo sales data are input as results.
In step 104, replenishment of goods is performed according to the goods and quantity to be replenished. In some embodiments, the kind of the goods output by the neural network and the corresponding quantity of each kind of goods are the various goods to be supplemented and the corresponding quantity thereof.
By the method, the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented can be predicted according to the video images and the sales data of the sales area, so that the quantity of the supplemented goods is matched with the quantity of expected sales, the supply and demand are reduced, and the waste caused by supply and demand is reduced.
In some embodiments, user actions may include staying in front of a shelf, staying in front of a certain item, picking up goods, putting down goods, and so forth. In some embodiments, the duration of various activities of the user may be obtained, as well as the goods to which the activities correspond. For example, the stay time of the user in the current video capture area and the goods included in the current video capture area, the stay time of the user in each goods sales area and the corresponding goods, the time length for the user to pick up the goods and the picked up goods, the time length for the user to hold the goods and the held goods, the time for the user to put back the goods and the put-back goods, and the like are obtained.
By the method, which positions and goods are concerned by the user can be collected, and the concerned points of the user are considered in the prediction of the neural network, so that the accuracy of the prediction is improved. By extracting information on the goods which the user has picked up and dropped down, it is possible to extract a case where the user pays attention to but abandons the purchase for various unclear reasons, and further, the prediction accuracy is further improved by taking the case into consideration in the prediction of the neural network. In addition, by extracting the occurrence time of various events, the user behaviors with different time lengths can be considered in the prediction of the neural network, and the accuracy of the prediction is further improved.
In some embodiments, the goods held by the user can be determined by acquiring the images of the goods held by the user and further using the pre-stored commodity image data for matching, so as to acquire the goods attribute information. In some embodiments, what kind or which kind of goods are placed on each shelf, and the positions of various kinds, models, brands of goods on the shelf may be pre-stored, and the goods that the user is interested in are determined by the position where the user stays. In some embodiments, the property information of the good may include a category of the good, a price, in addition to a brand model of the good, and the like.
By the method, goods targeted by user behaviors can be determined based on image analysis or pre-stored data, and a more accurate data basis is provided for prediction of the neural network. In addition, the method can take the influence of the category and the price of the goods on the purchase desire of the user into consideration, and the method can be used for predicting the neural network to further improve the accuracy.
In some embodiments, the video images are images of a predetermined time period, such as a day, and the goods sales data is sales quantities of various goods within the corresponding predetermined time period (such as the day). In some embodiments, the predetermined time period matches the replenishment period, thereby increasing the accuracy of the directions for replenishment.
In some embodiments, the video image and the goods sales data may be data of a single store and the same store in consideration of regional differences and store differences, so that the prediction result satisfies the personalized features of the current store.
In some embodiments, information collected from each store can be gathered to a big data analysis platform, and the conditions of each store are integrated to predict, so that the input quantity and the product production quantity are conveniently guided, on one hand, the prediction accuracy is improved by increasing the sample quantity, on the other hand, the quantity is controlled in the aspects of input and production, the utilization rate of limited resources is further improved, and the resource waste is reduced.
In some embodiments, to improve the accuracy of the neural network prediction, training of the neural network model may be performed first. A flow diagram of some embodiments of neural network training in the cargo replenishment method of the present disclosure is shown in fig. 2.
In step 201, user behavior data, cargo attribute information, and cargo sales data for a predetermined time period are input to a BP neural network. In some embodiments, the user behavior data, the cargo attribute information, and the cargo sales data in the history may be input into a BP neural network, which is trained as the collected data is generated without the history.
In step 202, the goods to be replenished and the quantity of each goods to be replenished output by the neural network are obtained.
In step 203, a prediction accuracy is determined based on the data output by the neural network and the sales data of the goods in the next predetermined time period. For example, a guide to yesterday's restocking is generated from the user behavior data, the good attribute information, and the good sales data of the previous day. After yesterday completes restocking, the prediction accuracy is determined from yesterday generated sales data for the good. In some embodiments, the variance of the actual sales volume of each good and the number of corresponding goods output by the neural network may be calculated, the sum of the variances is obtained, and the prediction accuracy is inversely related to the sum of the variances. For example, the sum of the variances is reciprocal, with greater reciprocal of the sum of the variances being more accurate.
In step 204, it is determined whether the prediction accuracy is below an accuracy threshold. If the prediction accuracy is lower than the accuracy threshold, go to step 205; otherwise, step 206 is performed.
In step 205, the neural network is modified, and the training of the neural network is continued, and step 201 is performed. In some embodiments, the accuracy of the neural network may be improved by an error correction operation. In some embodiments, the prediction accuracy may be gradually improved in the training by inputting the user behavior data, the cargo attribute information, and the cargo sales data for the next one or more predetermined time periods into the BP neural network until the prediction accuracy is not below the accuracy threshold.
In step 206, the current BP neural network is used as a prediction model for cargo supplement. In some embodiments, the accuracy of the neural network is further improved as the use may further optimize neural network parameters.
By the method, the forecasting model with accuracy meeting the requirement can be obtained in a neural network training mode, and then the neural network is applied to forecasting the replenishment under the condition of reaching the accuracy threshold, so that the accuracy of matching the replenished goods quantity with the expected sales quantity is improved.
A schematic view of some embodiments of the cargo replenishing device of the present disclosure is shown in fig. 3.
The image acquisition unit 301 can acquire a video image of a goods sales area. In some embodiments, the video images may be captured by one or more cameras deployed in a supermarket, a mall, and in particular an unmanned supermarket. In some embodiments, image data acquired by a camera video may be transcoded by a chip to be converted into a digital data stream, and the data is transmitted to a video analysis processing platform through an ethernet interface line for subsequent operations.
The image analysis unit 302 can acquire user behavior data and cargo attribute information from the video image. In some embodiments, each frame of image may be truncated chronologically from the video stream data; and then, carrying out displacement matching on the adjacent frame images, removing background information to obtain a user image, and further acquiring user behavior data. In some embodiments, the duration of various behaviors of the user may be counted.
The prediction unit 303 can determine the goods and the quantity to be supplemented based on the neural network algorithm according to the user behavior data, the goods attribute information, and the goods sales data. In some embodiments, the neural network used may be a BP neural network, which is trained and generated based on user behavior data, cargo attribute information, and cargo sales data over a period of time, and can predict the demand of various cargoes. In some embodiments, in the inputting of the user behavior data, the goods attribute information, and the goods sales data into the neural network, the user behavior data and the goods attribute information are input as the reference condition, and the goods sales data is input as the result.
The replenishment unit 304 can instruct the worker to perform replenishment of the goods according to the goods and the amount to be replenished. In some embodiments, the kind of the goods output by the neural network and the corresponding quantity of each kind of goods are the various goods to be supplemented and the corresponding quantity thereof. In some embodiments, the replenishment quantity required by the commodity can be provided to the commodity management system, and relevant personnel perform replenishment operation after checking.
The device can predict the types of goods needing to be supplemented and the quantity of each kind of goods needing to be supplemented according to the video images and the sales data of the sales area, so that the quantity of the goods needing to be supplemented is matched with the quantity of expected sales, the supply shortage is reduced, and the waste caused by the supply exceeding the demand is also reduced.
A schematic structural view of one embodiment of the disclosed cargo replenishment device is shown in fig. 4. The cargo replenishing device includes a memory 401 and a processor 402. Wherein: the memory 401 may be a magnetic disk, flash memory, or any other non-volatile storage medium. The memory is for storing the instructions in the corresponding embodiments of the cargo replenishment method hereinabove. The processor 402 is coupled to the memory 401 and may be implemented as one or more integrated circuits, such as a microprocessor or microcontroller. The processor 402 is configured to execute instructions stored in the memory to match the quantity of the replenishment product to the quantity of the desired sale, thereby reducing waste due to over demand while reducing supply shortages.
In one embodiment, as also shown in fig. 5, the cargo replenishment device 500 includes a memory 501 and a processor 502. The processor 502 is coupled to the memory 501 by a BUS 503. The device 500 may also be connected to an external storage device 505 via a storage interface 504 for accessing external data, and may also be connected to a network or another computer system (not shown) via a network interface 506. And will not be described in detail herein.
In this embodiment, the data instructions are stored in the memory and processed by the processor, so that the number of the supplementary goods can be matched with the number of the expected sales, and the waste caused by supply and demand exceeding is reduced while the supply and demand are reduced.
In another embodiment, a computer readable storage medium has stored thereon computer program instructions which, when executed by a processor, implement the steps of the method in the corresponding embodiment of the cargo replenishment method. As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
A schematic diagram of some embodiments of the cargo replenishment system of the present disclosure is shown in fig. 6.
The cargo replenishment system includes the image acquisition device 61, and any one of the cargo replenishment devices mentioned above. In some embodiments, the image capture device 61 may be one or more cameras deployed in a supermarket, a shopping mall, and in particular an unmanned supermarket.
The goods replenishment system can collect images of goods sales areas, predict the types of goods needing replenishment and the quantity of each kind of goods needing replenishment according to the video images and the sales data of the sales areas, so that the quantity of the replenished goods is matched with the quantity of expected sales, and the waste caused by supply and demand is reduced while the supply is short of the demand.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Thus far, the present disclosure has been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
Finally, it should be noted that: the above examples are intended only to illustrate the technical solutions of the present disclosure and not to limit them; although the present disclosure has been described in detail with reference to preferred embodiments, those of ordinary skill in the art will understand that: modifications to the specific embodiments of the disclosure or equivalent substitutions for parts of the technical features may still be made; all such modifications are intended to be included within the scope of the claims of this disclosure without departing from the spirit thereof.

Claims (12)

1. A cargo replenishment method comprising:
acquiring a video image of a goods sales area;
acquiring user behavior data and cargo attribute information according to the video image;
determining goods and quantity to be supplemented based on a neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data;
the replenishment of goods is performed according to the goods and the amount to be replenished.
2. The method of claim 1, wherein the obtaining user behavior data from the video image comprises:
intercepting each frame of image according to the video stream data and the time sequence;
and carrying out displacement matching on the adjacent frame images to obtain user behavior data.
3. The method of claim 2, wherein said obtaining cargo attribute information from said video image comprises:
capturing user behaviors of goods according to the video images;
acquiring an image of the goods held by the user according to the image frame including the goods holding behavior of the user;
and determining the goods held by the user by matching the images of the goods held by the user with the stored goods image information, and acquiring the goods attribute information.
4. The method of claim 1, wherein,
the user behavior data includes: the stay time in the current video capture area and the goods included in the current video capture area, the stay time of the user in each goods sales area and the corresponding goods, the time length for the user to pick up the goods and the picked up goods, the time length for the user to hold the goods and the held goods, and the time for the user to put back the goods and the put-back goods.
5. The method of claim 1, wherein,
the video image is an image in a preset time period;
the goods sales data includes sales quantities of various goods within a predetermined time period.
6. The method of claim 1, wherein,
the determining the goods and the quantity to be supplemented based on the neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data comprises the following steps:
inputting user behavior data and cargo attribute information acquired according to the video image in a preset time period into a back propagation BP neural network;
inputting the goods sales data extracted from sales data within the same preset time period into the BP neural network, wherein the BP neural network is generated based on user behavior data, goods attribute information and goods sales data training;
determining the goods needing to be supplemented and the quantity of each goods needing to be supplemented based on the BP neural network.
7. The method of any one of claims 1 to 6, wherein training to generate the BP neural network based on user behavior data, good attribute information, and good sales data comprises:
inputting user behavior data, cargo attribute information and cargo sales data in a preset time period into the BP neural network;
acquiring the goods which are output by the BP neural network and need to be supplemented and the quantity of each goods which need to be supplemented;
determining the prediction accuracy according to the data output by the BP neural network and the goods sales data in the next preset time period;
and under the condition that the prediction accuracy is lower than the accuracy threshold, correcting the BP neural network, and continuing training the BP neural network until the prediction accuracy is not lower than the accuracy threshold.
8. The method of claim 5, wherein the predetermined period of time matches a replenishment period.
9. A cargo replenishing device comprising:
an image acquisition unit configured to acquire a video image of a goods sales area;
the image analysis unit is configured to acquire user behavior data and cargo attribute information according to the video image;
the prediction unit is configured to determine goods needing to be supplemented and the quantity of the goods needing to be supplemented based on a neural network algorithm according to the user behavior data, the goods attribute information and the goods sales data;
and the replenishing unit is configured to prompt replenishment personnel to perform cargo replenishment according to the cargos to be replenished and the quantity.
10. A cargo replenishing device comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of any of claims 1-8 based on instructions stored in the memory.
11. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 8.
12. A cargo replenishment system comprising:
an image capturing device configured to capture images of respective goods sales areas; and
the cargo replenishing device according to claim 9 or 10.
CN201911125556.2A 2019-11-18 2019-11-18 Cargo replenishing method, device and system Pending CN111783513A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911125556.2A CN111783513A (en) 2019-11-18 2019-11-18 Cargo replenishing method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911125556.2A CN111783513A (en) 2019-11-18 2019-11-18 Cargo replenishing method, device and system

Publications (1)

Publication Number Publication Date
CN111783513A true CN111783513A (en) 2020-10-16

Family

ID=72755758

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911125556.2A Pending CN111783513A (en) 2019-11-18 2019-11-18 Cargo replenishing method, device and system

Country Status (1)

Country Link
CN (1) CN111783513A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113673929A (en) * 2021-08-23 2021-11-19 上海商汤智能科技有限公司 Task reminding method and device, electronic equipment and storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180146024A1 (en) * 2016-08-19 2018-05-24 Beijing Sensetime Technology Development Co., Ltd. Data processing method, apparatus and electronic device
CN108171531A (en) * 2017-12-08 2018-06-15 广州云印信息科技有限公司 A kind of vending machine intelligent management system and method based on data mining
CN108229894A (en) * 2018-02-11 2018-06-29 京东方科技集团股份有限公司 Cargo configuration method, device, terminal and system based on vending machine
CN108551658A (en) * 2017-12-18 2018-09-18 上海云拿智能科技有限公司 Object positioning system and localization method
CN108898109A (en) * 2018-06-29 2018-11-27 北京旷视科技有限公司 The determination methods, devices and systems of article attention rate
CN109308630A (en) * 2018-08-09 2019-02-05 虫极科技（北京）有限公司 A kind of Intelligent cargo cabinet and its commodity display method
CN109426982A (en) * 2017-08-31 2019-03-05 青岛海尔特种电冰柜有限公司 One kind, which is sold goods, exhibits and sells device passenger flow statistical method
CN109726759A (en) * 2018-12-28 2019-05-07 北京旷视科技有限公司 Self-service method, apparatus, system, electronic equipment and computer-readable medium
CN109993516A (en) * 2018-01-02 2019-07-09 阿里巴巴集团控股有限公司 Information processing method, the apparatus and system of commodity
CN110264236A (en) * 2019-05-07 2019-09-20 美佳亚太投资有限公司 Vending machine sales data analysis method, device and storage medium
CN110276495A (en) * 2019-06-26 2019-09-24 东莞市盟大塑化科技有限公司 Commercial articles ordering method, apparatus, computer and storage medium based on artificial intelligence

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180146024A1 (en) * 2016-08-19 2018-05-24 Beijing Sensetime Technology Development Co., Ltd. Data processing method, apparatus and electronic device
CN109426982A (en) * 2017-08-31 2019-03-05 青岛海尔特种电冰柜有限公司 One kind, which is sold goods, exhibits and sells device passenger flow statistical method
CN108171531A (en) * 2017-12-08 2018-06-15 广州云印信息科技有限公司 A kind of vending machine intelligent management system and method based on data mining
CN108551658A (en) * 2017-12-18 2018-09-18 上海云拿智能科技有限公司 Object positioning system and localization method
CN109993516A (en) * 2018-01-02 2019-07-09 阿里巴巴集团控股有限公司 Information processing method, the apparatus and system of commodity
CN108229894A (en) * 2018-02-11 2018-06-29 京东方科技集团股份有限公司 Cargo configuration method, device, terminal and system based on vending machine
CN108898109A (en) * 2018-06-29 2018-11-27 北京旷视科技有限公司 The determination methods, devices and systems of article attention rate
CN109308630A (en) * 2018-08-09 2019-02-05 虫极科技（北京）有限公司 A kind of Intelligent cargo cabinet and its commodity display method
CN109726759A (en) * 2018-12-28 2019-05-07 北京旷视科技有限公司 Self-service method, apparatus, system, electronic equipment and computer-readable medium
CN110264236A (en) * 2019-05-07 2019-09-20 美佳亚太投资有限公司 Vending machine sales data analysis method, device and storage medium
CN110276495A (en) * 2019-06-26 2019-09-24 东莞市盟大塑化科技有限公司 Commercial articles ordering method, apparatus, computer and storage medium based on artificial intelligence

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113673929A (en) * 2021-08-23 2021-11-19 上海商汤智能科技有限公司 Task reminding method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
WO2019165894A1 (en) Article identification method, device and system, and storage medium
CN108922026B (en) Replenishment management method and device for vending machine and user terminal
CN109117824B (en) Commodity management method and device, electronic equipment and storage medium
CN109726843B (en) Method, device and terminal for predicting distribution data
US20140180848A1 (en) Estimating Point Of Sale Wait Times
CN103593232B (en) The method for scheduling task and device of a kind of data warehouse
CN109840503B (en) Method and device for determining category information
CN106780909A (en) The control method and device of gate equipment
CN110379070B (en) Commodity detection method and commodity detection device
US20180336603A1 (en) Restaurant review systems
CN111523620B (en) Dynamic adjustment method and commodity verification method for commodity identification model
CN110610169B (en) Picture marking method and device, storage medium and electronic device
CN111242524A (en) Method, system, equipment and storage medium for determining replenishment quantity of single article
CN113111801A (en) Goods checking method, equipment and storage medium for automatic vending machine
US20160283895A1 (en) Plan determination method, computer-readable recording medium storing plan determination program, and plan determination apparatus
CN111783513A (en) Cargo replenishing method, device and system
JP2015103221A (en) Visitor attribute distribution information estimation device and program
CN116957471A (en) Intelligent retail service method, system, electronic equipment and storage medium
CN108090785B (en) Method and device for determining user behavior decline tendency and electronic equipment
US11393015B1 (en) Interface for item acquisition
JP6645957B2 (en) Motion estimation method and motion estimation system
CN106537442A (en) Collection amount regulation assist apparatus, collection amount regulation assist method, and computer-readable recording medium
CN109214548A (en) A kind of prediction technique and device of order time
CN112130571B (en) Linen conveying method and device for hotel rooms and electronic equipment
CN113689125A (en) Information pushing method and device

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