CN111652606B - Intelligent retail terminal system - Google Patents
Intelligent retail terminal system Download PDFInfo
- Publication number
- CN111652606B CN111652606B CN202010297341.5A CN202010297341A CN111652606B CN 111652606 B CN111652606 B CN 111652606B CN 202010297341 A CN202010297341 A CN 202010297341A CN 111652606 B CN111652606 B CN 111652606B
- Authority
- CN
- China
- Prior art keywords
- unit
- user
- information
- shopping
- commodity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000013500 data storage Methods 0.000 claims abstract description 21
- 230000003993 interaction Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/18—Payment architectures involving self-service terminals [SST], vending machines, kiosks or multimedia terminals
-
- 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
- G06Q20/16—Payments settled via telecommunication systems
-
- 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
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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]
- G06Q30/0631—Item recommendations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses an intelligent retail terminal system, which comprises a retail terminal, a server, an Internet of things platform and a user side; the retail terminal comprises a network unit, a central control unit, a payment identification module and an intelligent terminal interaction module; the server comprises a data processing unit, a data storage unit and an intelligent terminal shopping guide module; the internet of things platform comprises a Lot network unit, a Lot message unit and a Lot rule unit; the intelligent terminal interaction module carries out voice conversation with a user, after a voice command of the user is sent out, the voice command is converted into a word command, and the word command and the user information are sent to the intelligent terminal shopping guide module; the intelligent terminal shopping guide module acquires shopping information of the user according to the user information, predicts a future shopping list of the user through comparison and intelligent analysis of the shopping information, matches coupons, and recommends the shopping information to the user according to a text instruction. The invention can enhance the stability of the unmanned vending machine, improve the interactivity of the unmanned vending machine and reduce the operation cost.
Description
Technical Field
The invention relates to the technical field of unmanned vending machines, in particular to an intelligent retail terminal system.
Background
With the development of technology and the change of consumption modes, the unmanned vending machine is increasingly widely applied. Early vending machines were slot machines, and with the increasing use of mobile internet technology, unmanned vending machines have emerged that pay for goods and/or control the vending machine via mobile terminals. Generally, as shown in fig. 1, the current unmanned vending machine system comprises a vending machine and a cloud server, wherein the vending machine comprises a container, a communication module and a control module, and the vending machine can communicate with the cloud server through the communication module so as to complete a transaction, wherein the communication module can adopt 4G, GPRS, WIFI or wired network technology.
However, the above unmanned vending machine has the following disadvantages that firstly, when the network connection between the vending machine and the cloud server fails, normal vending service cannot be performed, even if the mobile terminal equipment of the consumer can access the internet; secondly, the equipment operates alone, the resource integration capability is not available, and a machine manager cannot grasp the condition of the machine in real time; third, the interaction between the vending machine and the user is limited.
Disclosure of Invention
In view of the above, the present invention provides an intelligent retail terminal system for solving the above-mentioned problems in the prior art.
The invention solves the problems by the following technical means:
an intelligent retail terminal system comprises a retail terminal, a server, an Internet of things platform and a user side;
the retail terminal comprises a network unit, a central control unit, a payment identification module and an intelligent terminal interaction module;
the server comprises a data processing unit, a data storage unit and an intelligent terminal shopping guide module;
the internet of things platform comprises a Lot network unit, a Lot message unit and a Lot rule unit;
the network unit is used for providing network connection; the method comprises the steps of establishing socket long connection with a Lot network unit, and sending machine information acquired by a central control unit to a Lot message unit; after the network unit is successfully connected with the Lot network unit, the commodity data of the terminal is requested to the server data processing unit and displayed to the user through the central control unit;
the central control unit is used for receiving the instruction sent by the operator and processed by the data processing unit and forwarded by the Lot network unit, analyzing the instruction to operate the machine, and sending feedback information to the Lot network unit;
the payment identification module is used for identifying user information through payment of the commodity purchased by the user;
the intelligent terminal interaction module is used for carrying out voice dialogue with a user, after a voice command of the user is sent out, converting the voice command into a word command, and sending the word command and user information to the intelligent terminal shopping guide module;
the intelligent terminal shopping guide module is used for acquiring shopping information of a user according to the user information, predicting a future shopping list of the user through comparison and intelligent analysis of the shopping information, matching coupons, and recommending the shopping information to the user according to a text instruction;
the user side is used for displaying recommended shopping information;
the data processing unit is used for processing the api request and inquiring data from the data storage unit; receiving an instruction sent by an operator, storing instruction information into a data storage unit after processing, and sending the processed instruction to a Lot network unit; receiving a machine state change message sent by the Lot message unit, performing machine state processing, and simultaneously storing the machine state change message into the data storage unit;
the data storage unit is used for storing service data;
the Lot network unit is used for providing stable Lot connection service to connect the retail terminal and the server; receiving an instruction sent by an operator after being processed by the data processing unit, and forwarding the instruction to the central control unit through the network unit; receiving feedback information of the central control unit, and judging whether to forward to the data processing unit according to a rule preset by the Lot rule unit;
the Lot message unit is used for sending a message to the retail terminal and the data processing unit; receiving machine information sent by a network unit, after verification is passed, sending heartbeat information to the network unit at fixed time to be responsible for maintaining socket connection, and after connection is successful, sending state information to a data processing unit of a server for machine state processing every time the machine state is changed;
the Lot rule unit is used for setting message forwarding rules.
Further, the retail terminal comprises a bluetooth communication unit, the user terminal comprises a bluetooth unit, the bluetooth communication unit of the retail terminal is used for providing the function of the bluetooth unit connected with the user terminal, and limited network connection service is provided under the condition of network unit failure;
the payment recognition module includes:
the camera is used for acquiring an image of a user and sending the image information to the WeChat face-brushing payment unit;
and the WeChat face-brushing payment unit is used for receiving the image information, carrying out face-brushing payment of the commodity purchased by the user through the image information, and identifying the user information.
Further, the intelligent terminal interaction module includes:
a voice device unit for providing input and output of sound;
the voice recognition unit is used for performing real-time voice recognition by using intelligent voice interaction;
the problem recording unit is used for recording dialogue information of a user, performing semantic analysis, providing a hot word model for the self-learning platform to perform machine learning, and improving the accuracy of voice recognition;
the self-learning platform unit is used for performing machine learning by using a deep learning algorithm, so that the recognition rate is improved;
and the electronic commerce unit is used for converting the voice into text information and sending the text information and the user information to the intelligent terminal shopping guide module.
Further, the voice recognition unit uses an LMS adaptive filtering noise reduction algorithm to perform signal noise reduction, where the LMS adaptive filtering noise reduction algorithm is specifically:
1) Given W (0), and 1 < mu < 1/lambda max ；
2) Calculating an output value: y (k) =w (k) T x(k)；
3) Calculating an estimation error: e (k) =d (k) -y (k);
4) And (5) updating the weight: w (k+1) =w (k) +μe (k) x (k);
wherein w is the array of adaptive recorder weighting coefficients updated once with each update of the estimation error e (k);
y (k) is the actual output signal, d (k) is the ideal output signal, x (k) is the input signal, k is the input signal length, μ is the convergence factor, and λ is the lagrangian multiplier.
Further, the voice recognition unit uses a wiener filtering method to perform signal noise reduction, and the wiener filtering method specifically comprises the following steps:
first, for a degraded image process, one of the following forms is written:
wherein ,
for the wiener filtered image, E is the expected value operator, f is the undegraded image, min is the minimum mean square error, and the expression in the frequency domain is expressed as:
wherein ,
h (u, v) represents a degradation function;
|H(u，v)| 2 ＝H*(u，v)H(u，v)；
H * (u, v) represents the complex conjugate of H (u, v);
S η (u，v)＝|N(u，v)| 2 a power spectrum representing noise;
S f (u，v)＝|F(u，v)| 2 a power spectrum representing an undegraded image;
n (u, v) is the noise function, G (u, v) is the sampling result of the image, u, v is the point of the acquisition matrix.
Further, the self-learning platform unit uses a deep learning algorithm to improve the recognition rate, specifically:
if the function f (x, y) has a first order continuous bias, for any point p (x 0 ，y 0 ) There is one such vector: f (x) 0 ，y 0 ) x i+f(x 0 ，y 0 ) y j, then this vector is called the gradient of f (x, y) at p, denoted grad f (x) 0 ，y 0 ) The method comprises the steps of carrying out a first treatment on the surface of the So that
The unit vector of the point L is e= (cos alpha, cos beta), the direction derivative is the slope of the function in all directions, the gradient is the direction with the largest slope, and the value of the gradient is the value with the largest direction derivative, so if the unit vector can descend fastest along the opposite direction of the gradient, the unit vector can reach the lowest as soon as possible, the system is stable, and the deep learning efficiency is improved.
Further, the intelligent terminal shopping guide module includes:
the information acquisition module is used for acquiring shopping records and consumption lists of a user on a shopping platform of a mall each time according to user information;
the information analysis module is used for analyzing shopping habits of users and counting commodity consumption periods of the users, and the time of purchasing the same type of commodity from the next time; according to the collected user information, making a consumption image of the user; acquiring shopping preferential information of a mall or an entity store, and automatically judging the matching degree of the preferential information and a shopping list of a user;
the commodity recommending module is used for generating commodity list recommending to the user according to the past commodity using time length and commodity consumption period of the user and when the commodity consumption period reaches the corresponding time point; recommending commodities purchased by users with similar images to the users according to the consumption images of the users; and generating a recommended shopping list and recommending the preferential information to the user when the preferential information matches the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user.
Further, the information analysis module includes:
the shopping period analysis unit is used for analyzing shopping habits of users and counting commodity consumption periods of the users, wherein the purchased commodity is longer than the time for purchasing similar commodities next time;
the user portrait analysis unit is used for making a consumption portrait of the user according to the collected user information;
and the preferential information analysis unit is used for acquiring shopping preferential information of the mall or the physical store and automatically judging the matching degree of the preferential information and the shopping list of the user.
Further, the commodity recommendation module includes:
the periodic commodity recommending unit is used for generating commodity list recommendation required by the user to the user when the commodity consumption period reaches a corresponding time point according to the past commodity use time length of the user and the commodity consumption period;
a similar commodity recommending unit for recommending commodities purchased by the user with similar portrait to the user according to the consumer portrait of the user;
and the preferential commodity recommending unit is used for generating a recommended shopping list and preferential information recommendation for the user when the preferential matching is carried out on the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user.
Further, the recommendation method of the commodity recommendation module specifically comprises the following steps:
collaborative filtering recommendation is carried out on the basis of content recommendation, preference of a user on commodities is calculated firstly to form a U-V matrix, then similarity of U-U and V-V is calculated according to user attributes, similarity of U and V is calculated according to preference of the user on the commodities, and a method for calculating the similarity is used for calculating Manhattan distance and Pearson correlation coefficients respectively;
manhattan distance represents the sum of the absolute wheelbases of two n-dimensional vectors a (x 11, x11, … x1 n) and b (x 21, x21, … x2 n) on a standard coordinate system:
k is the latitude of which, and the minimum value is the highest similarity after obtaining the values of all vectors;
the Pearson correlation coefficient measures the linear correlation between two variables X, Y, pearson: -1;
-1: complete negative correlation; 1: complete positive correlation; 0: uncorrelated, its calculation formula is:
where E is a mathematical expectation and N represents the number of values of the variable.
Compared with the prior art, the invention has the beneficial effects that at least:
the invention can enhance the stability of the unmanned vending machine, improve the interactivity of the unmanned vending machine, reduce the operation cost, greatly facilitate the shopping demand of the user and improve the shopping experience of the user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a prior art vending machine system;
FIG. 2 is a schematic diagram of the architecture of the intelligent retail terminal system of the present invention;
FIG. 3 is a timing diagram of a payment identification module of the present invention;
FIG. 4 is a schematic structural diagram of an intelligent terminal interaction module according to the present invention;
FIG. 5 is a flow chart of the intelligent terminal shopping guide module of the present invention;
fig. 6 is a flowchart of the intelligent terminal shopping guide module shopping guide method of the invention.
Detailed Description
In order to make the above objects, features and advantages of the present invention more comprehensible, the following detailed description of the technical solution of the present invention refers to the accompanying drawings and specific embodiments. It should be noted that the described embodiments are only some embodiments of the present invention, and not all embodiments, and that all other embodiments obtained by persons skilled in the art without making creative efforts based on the embodiments in the present invention are within the protection scope of the present invention.
Example 1
As shown in fig. 2, the invention provides an intelligent retail terminal system, which comprises a retail terminal, a server, an internet of things platform and a user side;
the retail terminal comprises a network unit, a central control unit, a payment identification module and an intelligent terminal interaction module;
the server comprises a data processing unit, a data storage unit and an intelligent terminal shopping guide module;
the internet of things platform comprises a Lot network unit, a Lot message unit and a Lot rule unit;
the network unit is used for providing network connection; the method comprises the steps of establishing socket long connection with a Lot network unit, and sending machine information acquired by a central control unit to a Lot message unit; after the network unit is successfully connected with the Lot network unit, the commodity data of the terminal is requested to the server data processing unit and displayed to the user through the central control unit;
the central control unit is used for receiving the instruction sent by the operator and processed by the data processing unit and forwarded by the Lot network unit, analyzing the instruction to operate the machine, and sending feedback information to the Lot network unit;
the payment identification module is used for identifying user information through payment of the commodity purchased by the user;
the intelligent terminal interaction module is used for carrying out voice dialogue with a user, after a voice command of the user is sent out, converting the voice command into a word command, and sending the word command and user information to the intelligent terminal shopping guide module;
the intelligent terminal shopping guide module is used for acquiring shopping information of a user according to the user information, predicting a future shopping list of the user through comparison and intelligent analysis of the shopping information, matching coupons, and recommending the shopping information to the user according to a text instruction;
the user side is used for displaying recommended shopping information;
the data processing unit is used for processing the api request and inquiring data from the data storage unit; receiving an instruction sent by an operator, storing instruction information into a data storage unit after processing, and sending the processed instruction to a Lot network unit; receiving a machine state change message sent by the Lot message unit, performing machine state processing, and simultaneously storing the machine state change message into the data storage unit;
the data storage unit is used for storing service data;
the Lot network unit is used for providing stable Lot connection service to connect the retail terminal and the server; receiving an instruction sent by an operator after being processed by the data processing unit, and forwarding the instruction to the central control unit through the network unit; receiving feedback information of the central control unit, and judging whether to forward to the data processing unit according to a rule preset by the Lot rule unit;
the Lot message unit is used for sending a message to the retail terminal and the data processing unit; receiving machine information sent by a network unit, after verification is passed, sending heartbeat information to the network unit at fixed time to be responsible for maintaining socket connection, and after connection is successful, sending state information to a data processing unit of a server for machine state processing every time the machine state is changed;
the Lot rule unit is used for setting message forwarding rules.
In this embodiment, the retail terminal includes a bluetooth communication unit, the client includes a bluetooth unit, and the bluetooth communication unit of the retail terminal is configured to provide a function of connecting to the bluetooth unit of the client, and provide limited network connection service in case of a network unit failure.
As shown in fig. 3, the payment recognition module includes a camera and a WeChat face-brushing payment unit;
the camera is used for acquiring an image of a user and sending image information to the WeChat face-brushing payment unit;
the WeChat face-brushing payment unit is used for receiving the image information, carrying out face-brushing payment of the commodity purchased by the user through the image information, and identifying the user information.
The retail terminal comprises a network unit, a Bluetooth communication unit, a central control unit and an intelligent terminal interaction module, wherein the network unit is responsible for providing network connection, the Bluetooth communication unit is responsible for providing a function of connecting with Bluetooth of a user, and limited network connection service is provided under the condition of network unit failure. The intelligent terminal interaction module acquires user information through the face recognition unit of the camera hardware matched with WeChat payment, the intelligent terminal shopping guide module is connected to conduct data analysis and then provide better shopping experience for users, the intelligent terminal interaction module can conduct voice dialogue with the users through voice equipment, after a user voice command is sent, the terminal responds to the command, and corresponding results are displayed for the users and are broadcasted through voice.
The server comprises a data processing unit, a data storage unit and an intelligent terminal shopping guide module, wherein the data processing unit is responsible for processing an api request and inquiring data from the data storage unit, the data storage unit is responsible for storing service data, the intelligent terminal shopping guide module acquires shopping information of a user according to user information, predicts a future shopping list of the user through comparison and intelligent analysis of the shopping information, and matches coupons to recommend the shopping information to the user.
The client module comprises an applet unit and an app unit.
The internet of things platform comprises a Lot network unit, a Lot message unit and a Lot rule unit, wherein the Lot network unit is responsible for providing stable Lot connection service and connecting with a retail terminal; the Lot message unit is responsible for sending the message to the retail terminal and the data processing unit, and the Lot rule unit is responsible for setting message forwarding rules.
The network unit is responsible for establishing socket long connection with the Lot network unit, sending machine information acquired from the central control unit, after verification, the Lot message unit can send heartbeat messages to the network unit at regular time to be responsible for maintaining socket connection, and after connection is successful, the Lot message unit can send state messages to the data processing unit of the server for machine state processing and simultaneously store the state messages in the data storage unit each time the machine state changes. And after the network unit is successfully connected with the Lot network unit, requesting data from the server data processing unit, and displaying the data to a user through the central control unit.
The operator sends out instructions to the data processing unit, the data processing unit stores instruction information into the data storage unit after processing, the Lot network unit sends out instructions to the Lot network unit, the Lot network unit forwards the instructions to the central control unit through the network unit, the central control unit analyzes the instructions to operate the machine, feedback information is sent to the Lot network unit, and after the Lot network unit receives the instructions, whether the instructions are to be forwarded to the data processing unit is judged according to rules preset by the Lot rule unit.
The vending terminal and the user interaction are improved, and the networking operation scheme is as follows: the user can search the nearby selling terminals to select interesting commodity ordering and purchasing, then select to get the commodity or directly select to get the commodity to the gate when the user is proper, and the user can also select to get the commodity to the front of the terminal machine, and operate the terminal by touching the 32 inch display screen to complete the shopping process, so that the commodity can be immediately fetched or the commodity can be selected to get the commodity to the gate. The retail terminal uses the intelligent terminal interaction unit and the intelligent retail shopping guide unit to promote the interactivity of the user and the vending terminal.
The invention improves the stability scheme of the unmanned vending terminal, which is characterized in that a communication module is used for connecting an Internet of things platform of the Arian, so that the on-line stability of the terminal is improved, and a manager can be immediately informed to check in time and monitor in real time whenever the state of the terminal changes; when the goods in the terminal are purchased by a user, the cloud server can send the goods taking code to the terminal for storage, when the user takes goods, network faults occur, goods can still be taken through the goods taking code, when the terminal has network faults, and the goods cannot be taken, the user can be connected with the Bluetooth module of the terminal through a WeChat applet or the Bluetooth function of the app, the user side reads the security configuration of the terminal and communicates with the cloud server, after the goods pass inspection, the cloud server returns the goods taking code information, the goods are written into the terminal by the user side, and after the operation is completed, the user can take goods at the terminal through the goods taking code.
Example 2
As shown in fig. 4, in this embodiment, on the basis of embodiment 1, the intelligent terminal interaction module includes a voice device unit, a voice recognition unit, a problem recording unit, a self-learning platform unit, and an e-commerce unit;
the voice equipment unit is used for providing input and output of sound;
the voice recognition unit is used for performing real-time voice recognition by using intelligent voice interaction;
the problem recording unit is used for recording dialogue information of a user, performing semantic analysis, providing a hot word model for a self-learning platform to perform machine learning, and improving the accuracy of voice recognition;
the self-learning platform unit is used for performing machine learning by using a deep learning algorithm, so that the recognition rate is improved;
the electronic commerce unit is used for converting the voice into text information and sending the text information and the user information to the intelligent terminal shopping guide module.
Firstly, a person speaking is converted into characters through speech recognition (ASR), then the intention of a user is known through Natural Language Understanding (NLU), the intention of the user is further clarified through questioning by using multi-round Dialogue Management (DM), the intention of the user is determined to be converted into character information, the characters are processed through a forward iteration finest granularity segmentation algorithm to obtain query information, then electronic commerce data is queried, and finally the characters are spoken through speech synthesis (TTS).
In particular, the voice recognition unit uses a noise reduction algorithm for signal noise reduction, wherein two noise reduction algorithms, LMS adaptive filtering and wiener filtering, are provided.
LMS adaptive filter
1) Given W (0), and 1 < mu < 1/lambda max ；
2) Calculating an output value: y (k) =w (k) T x(k)；
3) Calculating an estimation error: e (k) =d (k) -y (k);
4) And (5) updating the weight: w (k+1) =w (k) +μe (k) x (k);
wherein w is the array of adaptive recorder weighting coefficients updated once with each update of the estimated error e (k)
y (k) is the actual output signal, d (k) is the ideal output signal, x (k) is the input signal, k is the input signal length, μ is the convergence factor (learning rate), and λ is the lagrangian multiplier.
Wilner filtering method
First, for a degraded image process, one of the following forms is written:
wherein ,
for the wiener filtered image, E is the expected value operator, f is the undegraded image, min is the minimum mean square error, and the expression in the frequency domain is expressed as:
wherein ,
h (u, v) represents a degradation function;
|H(u，v)| 2 ＝H*(u，v)H(u，v)；
H * (u, v) represents the complex conjugate of H (u, v);
S η (u，v)＝|N(u，v)| 2 a power spectrum representing noise;
S f (u，v)＝|F(u，v)| 2 a power spectrum representing an undegraded image;
n (u, v) is the noise function, G (u, v)) is the sampling result of the image, u, v being the point of the acquisition matrix.
Specifically, the self-learning platform unit uses a deep learning algorithm to improve the recognition rate, specifically:
if the function f (x, y) has a first order continuous bias, for any point p (x 0 ，y 0 ) There is one such vector: f (x) 0 ，y 0 ) x i+f(x 0 ，y 0 ) y j, then this vector is called the gradient of f (x, y) at p, denoted grad f (x) 0 ，y 0 ) The method comprises the steps of carrying out a first treatment on the surface of the So that
Where the unit vector at point L is e= (cos α, cos β), the directional derivative is the slope of the function in each direction, and the gradient is the direction where the slope is greatest, and the value of the gradient is the value where the directional derivative is greatest. Therefore, if the gradient can descend fastest along the opposite direction of the gradient, the gradient reaches the minimum as soon as possible, so that the system is stable, and the efficiency of deep learning is improved.
Example 3
As shown in fig. 5 and 6, in this embodiment, based on embodiment 1, the intelligent terminal shopping guide module includes an information acquisition module, an information analysis module, and a commodity recommendation module;
the information acquisition module is used for acquiring shopping records and consumption lists of a user on a shopping platform of a mall each time according to user information;
the information analysis module is used for analyzing shopping habits of users and counting commodity consumption periods of the users, and the time of purchasing the same type of commodity from the next time; according to the collected user information, making a consumption image of the user; acquiring shopping preferential information of a mall or an entity store, and automatically judging the matching degree of the preferential information and a shopping list of a user;
the commodity recommending module is used for generating commodity list recommending to the user according to the past commodity using time length and commodity consumption period of the user and when the commodity consumption period reaches the corresponding time point; recommending commodities purchased by users with similar images to the users according to the consumption images of the users; and generating a recommended shopping list and recommending the preferential information to the user when the preferential information matches the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user.
Specifically, the information analysis module comprises a shopping period analysis unit, a user portrait analysis unit and a preferential information analysis unit;
the shopping period analysis unit is used for analyzing shopping habits of users and counting commodity consumption periods of the users, and the time of purchasing the same type of commodity from the next time;
the user portrait analysis unit is used for making a consumption portrait of a user according to the collected user information;
the preferential information analysis unit is used for acquiring shopping preferential information of a mall or a physical store and automatically judging the matching degree of the preferential information and a shopping list of a user.
Specifically, the commodity recommendation module comprises a periodic commodity recommendation unit, a similar commodity recommendation unit and a preferential commodity recommendation unit;
the periodic commodity recommending unit is used for generating commodity list recommendation required by the user to the user when the commodity consumption period reaches a corresponding time point according to the past commodity use time length of the user and the commodity consumption period;
the similar commodity recommending unit is used for recommending commodities purchased by the user with similar portrait to the user according to the consumption portrait of the user;
the preferential commodity recommending unit is used for generating a recommended shopping list and preferential information recommendation to the user when the preferential is matched with the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user.
Specifically, the recommendation method of the commodity recommendation module specifically includes:
collaborative filtering recommendation is carried out on the basis of content recommendation, preference of a user on commodities is calculated firstly to form a U-V matrix, then similarity of U-U and V-V is calculated according to user attributes, similarity of U and V is calculated according to preference of the user on the commodities, and a method for calculating the similarity is used for calculating Manhattan distance and Pearson correlation coefficients respectively;
manhattan distance represents the sum of the absolute wheelbases of two n-dimensional vectors a (x 11, x11, … x1 n) and b (x 21, x21, … x2 n) on a standard coordinate system:
k is the latitude of which, and the minimum value is the highest similarity after obtaining the values of all vectors;
the Pearson correlation coefficient measures the linear correlation between two variables X, Y, pearson: -1;
-1: complete negative correlation; 1: complete positive correlation; 0: uncorrelated, its calculation formula is:
where E is a mathematical expectation and N represents the number of values of the variable.
The invention can enhance the stability of the unmanned vending machine, improve the interactivity of the unmanned vending machine, reduce the operation cost, greatly facilitate the shopping demand of the user and improve the shopping experience of the user.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. The intelligent retail terminal system is characterized by comprising a retail terminal, a server, an Internet of things platform and a user side;
the retail terminal comprises a network unit, a central control unit, a payment identification module and an intelligent terminal interaction module;
the server comprises a data processing unit, a data storage unit and an intelligent terminal shopping guide module;
the internet of things platform comprises a Lot network unit, a Lot message unit and a Lot rule unit;
the network unit is used for providing network connection; the method comprises the steps of establishing socket long connection with a Lot network unit, and sending machine information acquired by a central control unit to a Lot message unit; after the network unit is successfully connected with the Lot network unit, the commodity data of the terminal is requested to the server data processing unit and displayed to the user through the central control unit;
the central control unit is used for receiving the instruction sent by the operator and processed by the data processing unit and forwarded by the Lot network unit, analyzing the instruction to operate the machine, and sending feedback information to the Lot network unit;
the payment identification module is used for identifying user information through payment of the commodity purchased by the user;
the intelligent terminal interaction module is used for carrying out voice dialogue with a user, after a voice command of the user is sent out, converting the voice command into a word command, and sending the word command and user information to the intelligent terminal shopping guide module;
the intelligent terminal shopping guide module is used for acquiring shopping information of a user according to the user information, predicting a future shopping list of the user through comparison and intelligent analysis of the shopping information, matching coupons, and recommending the shopping information to the user according to a text instruction;
the user side is used for displaying recommended shopping information;
the data processing unit is used for processing the api request and inquiring data from the data storage unit; receiving an instruction sent by an operator, storing instruction information into a data storage unit after processing, and sending the processed instruction to a Lot network unit; receiving a machine state change message sent by the Lot message unit, performing machine state processing, and simultaneously storing the machine state change message into the data storage unit;
the data storage unit is used for storing service data;
the Lot network unit is used for providing stable Lot connection service to connect the retail terminal and the server; receiving an instruction sent by an operator after being processed by the data processing unit, and forwarding the instruction to the central control unit through the network unit; receiving feedback information of the central control unit, and judging whether to forward to the data processing unit according to a rule preset by the Lot rule unit;
the Lot message unit is used for sending a message to the retail terminal and the data processing unit; receiving machine information sent by a network unit, after verification is passed, sending heartbeat information to the network unit at fixed time to be responsible for maintaining socket connection, and after connection is successful, sending state information to a data processing unit of a server for machine state processing every time the machine state is changed;
the Lot rule unit is used for setting message forwarding rules;
the intelligent terminal shopping guide module comprises:
the information acquisition module is used for acquiring shopping records and consumption lists of a user on a shopping platform of a mall each time according to user information;
the information analysis module is used for analyzing shopping habits of users and counting commodity consumption periods of the users, and the time of purchasing the same type of commodity from the next time; according to the collected user information, making a consumption image of the user; acquiring shopping preferential information of a mall or an entity store, and automatically judging the matching degree of the preferential information and a shopping list of a user;
the commodity recommending module is used for generating commodity list recommending to the user according to the past commodity using time length and commodity consumption period of the user and when the commodity consumption period reaches the corresponding time point; recommending commodities purchased by users with similar images to the users according to the consumption images of the users; generating a recommended shopping list and preferential information recommendation to the user when the preferential matching is carried out on the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user;
the recommendation method of the commodity recommendation module specifically comprises the following steps:
collaborative filtering recommendation is carried out on the basis of content recommendation, preference of a user on commodities is calculated firstly to form a U-V matrix, then similarity of U-U and V-V is calculated according to user attributes, similarity of U and V is calculated according to preference of the user on the commodities, and a method for calculating the similarity is used for calculating Manhattan distance and Pearson correlation coefficients respectively;
manhattan distance represents the sum of the absolute wheelbases of two n-dimensional vectors a (x 11, x11, … x1 n) and b (x 21, x21, … x2 n) on a standard coordinate system:
k is the dimension, and after values of all vectors are obtained, the minimum value is the highest similarity;
the Pearson correlation coefficient measures the linear correlation between two variables X, Y, pearson: -1;
-1: complete negative correlation; 1: complete positive correlation; 0: uncorrelated, its calculation formula is:
where E is a mathematical expectation and N represents the number of values of the variable.
2. The intelligent retail terminal system according to claim 1, wherein the retail terminal comprises a bluetooth communication unit, the user side comprises a bluetooth unit, the bluetooth communication unit of the retail terminal is used for providing a function of connecting the bluetooth unit of the user side, and in case of a network unit failure, a limited network connection service is provided;
the payment recognition module includes:
the camera is used for acquiring an image of a user and sending the image information to the WeChat face-brushing payment unit;
and the WeChat face-brushing payment unit is used for receiving the image information, carrying out face-brushing payment of the commodity purchased by the user through the image information, and identifying the user information.
3. The smart retail terminal system of claim 1, wherein the smart terminal interaction module comprises:
a voice device unit for providing input and output of sound;
the voice recognition unit is used for performing real-time voice recognition by using intelligent voice interaction;
the problem recording unit is used for recording dialogue information of a user, performing semantic analysis, providing a hot word model for the self-learning platform to perform machine learning, and improving the accuracy of voice recognition;
the self-learning platform unit is used for performing machine learning by using a deep learning algorithm, so that the recognition rate is improved;
and the electronic commerce unit is used for converting the voice into text information and sending the text information and the user information to the intelligent terminal shopping guide module.
4. A smart retail terminal system according to claim 3, characterised in that the voice recognition unit uses an LMS adaptive filtering noise reduction algorithm for signal noise reduction, in particular:
1) Given W (0), and 1 < mu < 1/lambda max ；
2) Calculating an output value: y (k) =w (k) T x(k)；
3) Calculating an estimation error: e (k) =d (k) -y (k);
4) And (5) updating the weight: w (k+1) =w (k) +μe (k) x (k);
wherein w is the array of adaptive filter weighting coefficients updated once with each update of the estimation error e (k);
y (k) is the actual output signal, d (k) is the ideal output signal, x (k) is the input signal, k is the input signal length, μ is the convergence factor, and λ is the lagrangian multiplier.
5. A smart retail terminal system according to claim 3, characterised in that the voice recognition unit uses wiener filtering to reduce the signal noise, in particular:
first, for a degraded image process, one of the following forms is written:
wherein ,
for the wiener filtered image, E is the expected value operatorF is an undegraded image, min is the minimum mean square error, and the expression of the wiener filtered image is expressed in the frequency domain as:
wherein ,
h (u, v) represents a degradation function;
|H(u，v)| 2 ＝H * (u，v)H(u，v)；
H * (u, v) represents the complex conjugate of H (u, v);
S η (u，v)＝|N(u，v)| 2 a power spectrum representing noise;
S f (u，v)＝|F(u，v)| 2 a power spectrum representing an undegraded image;
n (u, v) is the noise function, G (u, v) is the sampling result of the image, u, v is the point of the acquisition matrix.
6. The intelligent retail terminal system according to claim 3, wherein the self-learning platform unit uses a deep learning algorithm to increase the recognition rate, in particular:
if the function f (x, y) has a first order continuous bias, for any point p (x 0 ，y 0 ) There is one such vector: f (x) 0 ，y 0 ) x i+f(x 0 ，y 0 ) y j, then this vector is called the gradient of f (x, y) at p, denoted grad f (x) 0 ，y 0 ) The method comprises the steps of carrying out a first treatment on the surface of the So that
The unit vector of the point L is e= (cos alpha, cos beta), the direction derivative is the slope of the function in all directions, the gradient is the direction with the largest slope, and the value of the gradient is the value with the largest direction derivative, so if the unit vector can descend fastest along the opposite direction of the gradient, the unit vector can reach the lowest as soon as possible, the system is stable, and the deep learning efficiency is improved.
7. The intelligent retail terminal system of claim 1, wherein the information analysis module comprises:
the shopping period analysis unit is used for analyzing shopping habits of users and counting commodity consumption periods of the users, wherein the purchased commodity is longer than the time for purchasing similar commodities next time;
the user portrait analysis unit is used for making a consumption portrait of the user according to the collected user information;
and the preferential information analysis unit is used for acquiring shopping preferential information of the mall or the physical store and automatically judging the matching degree of the preferential information and the shopping list of the user.
8. The intelligent retail terminal system of claim 1, wherein the item recommendation module comprises:
the periodic commodity recommending unit is used for generating commodity list recommendation required by the user to the user when the commodity consumption period reaches a corresponding time point according to the past commodity use time length of the user and the commodity consumption period;
a similar commodity recommending unit for recommending commodities purchased by the user with similar portrait to the user according to the consumer portrait of the user;
and the preferential commodity recommending unit is used for generating a recommended shopping list and preferential information recommendation for the user when the preferential matching is carried out on the shopping habit of the user according to the matching degree of the preferential information and the shopping list of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297341.5A CN111652606B (en) | 2020-04-15 | 2020-04-15 | Intelligent retail terminal system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297341.5A CN111652606B (en) | 2020-04-15 | 2020-04-15 | Intelligent retail terminal system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111652606A CN111652606A (en) | 2020-09-11 |
| CN111652606B true CN111652606B (en) | 2023-05-02 |
Family
ID=72343000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010297341.5A Active CN111652606B (en) | 2020-04-15 | 2020-04-15 | Intelligent retail terminal system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652606B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113129104A (en) * | 2021-04-20 | 2021-07-16 | 深圳优地科技有限公司 | Intelligent shopping method, equipment and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559758A (en) * | 2013-11-06 | 2014-02-05 | 上海煦荣信息技术有限公司 | Intelligent vending system and intelligent vending method |
| CN106910061A (en) * | 2017-03-01 | 2017-06-30 | 深圳绱慧科技有限公司 | A kind of intelligence sale shopping guide method and system |
| CN106921945A (en) * | 2017-02-22 | 2017-07-04 | 上海斐讯数据通信技术有限公司 | The positioning shopping guide method and system of a kind of commodity |
| CN107767217A (en) * | 2017-10-19 | 2018-03-06 | 康佳集团股份有限公司 | Shopping recommendation method, mobile terminal and storage medium |
| CN108922025A (en) * | 2018-07-09 | 2018-11-30 | Ut斯达康通讯有限公司 | Settle accounts method of payment, device, Intelligent cargo cabinet and server |
-
2020
- 2020-04-15 CN CN202010297341.5A patent/CN111652606B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559758A (en) * | 2013-11-06 | 2014-02-05 | 上海煦荣信息技术有限公司 | Intelligent vending system and intelligent vending method |
| CN106921945A (en) * | 2017-02-22 | 2017-07-04 | 上海斐讯数据通信技术有限公司 | The positioning shopping guide method and system of a kind of commodity |
| CN106910061A (en) * | 2017-03-01 | 2017-06-30 | 深圳绱慧科技有限公司 | A kind of intelligence sale shopping guide method and system |
| CN107767217A (en) * | 2017-10-19 | 2018-03-06 | 康佳集团股份有限公司 | Shopping recommendation method, mobile terminal and storage medium |
| CN108922025A (en) * | 2018-07-09 | 2018-11-30 | Ut斯达康通讯有限公司 | Settle accounts method of payment, device, Intelligent cargo cabinet and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111652606A (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11361364B2 (en) | Shopping recommendation method, client, and server | |
| CN111932144B (en) | Customer service agent distribution method and device, server and storage medium | |
| CN111353091A (en) | Information processing method and device, electronic equipment and readable storage medium | |
| CN111382359B (en) | Service policy recommendation method and device based on reinforcement learning, and electronic equipment | |
| US20180218432A1 (en) | Recommendation integrated online digital sales service chat system | |
| CN111949887A (en) | Item recommendation method and device and computer-readable storage medium | |
| CN111652620A (en) | Intelligent terminal interaction system | |
| CN112036954A (en) | Item recommendation method and device, computer-readable storage medium and electronic device | |
| CN114331512A (en) | Method for modeling visual data and portraying big data | |
| CN114417174B (en) | Content recommendation method, device, equipment and computer storage medium | |
| CN111652606B (en) | Intelligent retail terminal system | |
| CN116304007A (en) | Information recommendation method and device, storage medium and electronic equipment | |
| CN112836515A (en) | Text analysis method, recommendation device, electronic equipment and storage medium | |
| US11900067B1 (en) | Multi-modal machine learning architectures integrating language models and computer vision systems | |
| CN111652668B (en) | Block chain supply chain financial system | |
| CN112183408B (en) | Customer portrait system and method based on field image | |
| CN109493186A (en) | The method and apparatus for determining pushed information | |
| KR20210133818A (en) | method for providing voice recognition shopping service based on deep learning AI | |
| CN116821513A (en) | Parameter searching method, device, equipment and medium under recommended scene | |
| CN112308648A (en) | Information processing method and device | |
| CN111787042A (en) | Method and device for pushing information | |
| CN115601047A (en) | Data processing method and device | |
| CN113762415A (en) | Neural network-based intelligent matching method and system for automobile financial products | |
| JP7366218B1 (en) | Information processing device, method and program | |
| CN114186129B (en) | Package recommendation method, package recommendation device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |