Unmanned supermarket data processing method, device, system and storage medium

Abstract

The present invention discloses an unmanned supermarket data processing method, device, system and storage medium. The method comprises: obtaining a semantic identifier of a target object; determining an instance corresponding to the target object in an unmanned supermarket entity based on the semantic identifier of the target object; resolving the instance according to a first attribute of the instance; wherein the target object is an Internet of Things object with a semantic identifier, the semantic identifier comprises a semantic prefix and a first identifier, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket entity, the first identifier is the source identifier information of the target object, and the first attribute is used to determine an identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things, and in particular to an unmanned supermarket data processing method, device, system and storage medium. Background Art

[0002] With the development of Internet of Things technology, traditional supermarkets are gradually evolving towards unmanned supermarkets. Unmanned supermarkets adopt a model where customers enter the store to verify their identity, and the payment is automatically deducted after the goods are purchased. Without the need for waiters and cashiers, transactions can be easily completed. In related technologies, the goods in unmanned supermarkets all use homogeneous identification (that is, the same identification resolution system). Users scan the QR code on their mobile phones at the entrance of the supermarket to confirm their identity. A large number of sensors are used to identify the user's actions, goods and the location of the goods. Based on image recognition, the user is tracked and located. The user's action of taking the goods is judged based on the position and posture, and the shopping list is pushed to the user's mobile phone. The user completes the shopping in the APP (application) checkout. If the goods in the unmanned supermarket use heterogeneous identification, the identification resolution system cannot be correctly resolved, and automatic settlement cannot be achieved. Summary of the invention

[0003] In view of this, embodiments of the present invention provide an unmanned supermarket data processing method, device, system and storage medium, which are intended to enable the interaction of IoT objects with heterogeneous identifiers in an unmanned supermarket.

[0004] The technical solution of the embodiment of the present invention is achieved as follows:

[0005] An embodiment of the present invention provides an unmanned supermarket data processing method, comprising:

[0006] Get the semantic identification of the target object;

[0007] Determine the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object;

[0008] parsing the instance according to a first attribute of the instance;

[0009] Among them, the target object is an Internet of Things object with a semantic identifier, and the semantic identifier includes a semantic prefix and a first identifier. The semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, and the first identifier is the source identification information of the target object. The first attribute is used to determine the identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system.

[0010] The embodiment of the present invention further provides an unmanned supermarket data processing device, comprising:

[0011] An acquisition module, used to acquire the semantic identification of the target object;

[0012] A determination module, used for determining the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object;

[0013] A parsing module, configured to parse the instance according to a first attribute of the instance;

[0014] Among them, the target object is an Internet of Things object with a semantic identifier, and the semantic identifier includes a semantic prefix and a first identifier. The semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, and the first identifier is the source identification information of the target object. The first attribute is used to determine the identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system.

[0015] An embodiment of the present invention further provides an unmanned supermarket data processing system, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the method described in any embodiment of the present invention when running the computer program.

[0016] An embodiment of the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any embodiment of the present invention are implemented.

[0017] The technical solution provided by the embodiment of the present invention obtains the semantic identification of the target object; determines the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identification of the target object; and resolves the instance according to the first attribute of the instance; wherein the semantic identification includes a semantic prefix and a first identification, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, the first identification is the source identification information of the target object, and the first attribute is used to determine the identification resolution system corresponding to the first identification, so that the instance can be resolved according to the corresponding identification resolution system, thereby supporting the unified resolution of instances with heterogeneous identifications. The embodiment of the present invention can be compatible with IoT objects with heterogeneous identifications, so that the unmanned supermarket ontology supports the interaction between IoT objects with heterogeneous identifications, and further realizes the unmanned management of the unmanned supermarket based on the unmanned supermarket ontology. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the data processing method of the unmanned supermarket according to an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the structure of a semantic identifier in an application example of the present invention;

[0020] Figure 3 This is a structural schematic diagram of an unmanned supermarket body in an application example of the present invention;

[0021] Figure 4 It is a schematic diagram of the principle of mapping an IoT object into an ontology instance in an application example of the present invention;

[0022] Figure 5 It is a flow chart of the unmanned supermarket data processing method according to an application example of the present invention;

[0023] Figure 6 This is a structural schematic diagram of an unmanned supermarket data processing device according to an embodiment of the present invention;

[0024] Figure 7 It is a structural schematic diagram of the unmanned supermarket data processing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0027] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are applicable to the following interpretations:

[0028] Ontology: Ontology is a collection of terms used to describe a field. Its organizational structure is hierarchical and can be used as the skeleton and foundation of a knowledge base to obtain, describe and represent knowledge in related fields. Ontology can provide a common understanding of the knowledge in the field, determine the commonly recognized vocabulary (classes, also known as concepts) in the field, as well as domain-specific concept definitions and the relationship between concepts (attributes), and achieve sharing between people and between people and machines. As a way of expressing knowledge, ontology plays an important role in realizing the intelligent scenarios of the Internet of Things and improving the quality of Internet data retrieval. Ontology gives the basic terms and relationships that constitute the vocabulary in the relevant field, and uses these terms and relationships to define the rules for the extension of these terms. Ontology can be compiled using OWL (Web Ontology Language), which includes 5 basic modeling primitives: class, relations, properties, instances, and rules.

[0029] Class: A class, also called a concept, is used to describe actual concepts in a field. It can be a real thing or an abstract concept, such as a university, a movie, or a person. Semantically speaking, it represents a collection of objects.

[0030] Relation: used to describe the relationship between classes (concepts), such as part-of, kind-of, subclass-of, etc. It can be formally defined as a subset of the n-dimensional Cartesian product.

[0031] Attributes: The properties, characteristics, features, features and parameters that an object and / or class may have. They are divided into object properties and data properties. Object properties represent the connection between concepts or instances; data properties represent the connection between instances and specific data, which can be understood as a certain attribute value of the instance. When creating Properties, you can specify the domain and range.

[0032] Instance: is a specific instance of a concept, such as TS_0130_C is an instance of the concept of temperature sensor.

[0033] Rule: A statement in the form of an if-then statement that describes the logical inferences that can be drawn from an assertion of a particular form.

[0034] In related technologies, IoT objects are generally marked with IoT identifiers. For example, product codes, device serial numbers, device network addresses, page URIs (Uniform Resource Identifiers), etc. can be used as IoT identifiers. With the rapid development of the IoT, a variety of heterogeneous IoT identifiers coexist. Since the encoding methods are different, for the use of different encoding methods in a process, it is necessary to first identify the encoding method, and then the corresponding identification resolution system completes the resolution. It is impossible to use a unified identification system to complete the resolution and intercommunication of different encodings. Here, resolution refers to decoding the identification information according to the corresponding encoding information to determine the object to which the identification information actually corresponds.

[0035] In the field of unmanned supermarkets, in related technologies, homogeneous identification is generally used for all IoT objects in the supermarket system. For example, Amazon Go (Amazon's unmanned retail store) uses a QR code generated by the Amazon Go APP for identity authentication, an Amazon account for settlement, and Amazon's unique identification for goods. Alibaba's unmanned supermarket uses Taobao or Alipay accounts for identity authentication and Alipay accounts for settlement. This type of unmanned supermarket does not support other types of identity authentication and payment methods. However, in real life, an object usually has multiple heterogeneous identifications. For example, a person's identity information can be represented by ID card number, passport number, WeChat account, Alipay account, etc.; a person's payment account includes bank cards, Alipay, WeChat, and packages, each of which has its own unique source identification, resulting in the inability of IoT objects with heterogeneous identifications to interact, making it difficult to truly achieve unmanned management.

[0036] Based on this, in various embodiments of the present invention, a semantic identifier is used to be compatible with IoT objects with heterogeneous identifiers, and the identification information corresponding to the IoT object can be accurately parsed, so that the unmanned supermarket entity supports the interaction between IoT objects with heterogeneous identifiers, and then unmanned management of the unmanned supermarket is realized based on the unmanned supermarket entity.

[0037] In the embodiment of the present invention, the unmanned supermarket ontology is a set of terms that describe the unmanned supermarket field. The classes of the unmanned supermarket ontology may include: supermarket, goods, customer, and payment account; wherein, supermarket is a set of supermarket objects of unmanned supermarkets, goods is a set of goods objects of various IoT goods, customers are a set of various customer objects with IoT identification identities, and payment accounts are a set of various account objects.

[0038] The embodiment of the present invention provides a method for processing data in an unmanned supermarket. Figure 1 As shown, the method includes:

[0039] Step 101, obtaining the semantic identifier of the target object.

[0040] Here, the target object is an IoT object with a semantic identifier, and the target object may be any one of the aforementioned supermarket object, goods object, customer object, and account object.

[0041] In actual application, before identifying the target object, it is necessary to first create the semantic identifier for the target object, and the semantic identifier is determined based on the source identification information of the target object (i.e. the aforementioned IoT identifier) ​​and the class to which the target object belongs in the unmanned supermarket entity. The semantic identifier can be solidified physical identification information, such as a QR code label set on the surface of the goods; the semantic identifier can also be digital identification information, such as electronic barcode information displayed on an electronic terminal (such as a user's mobile phone), web page URI, etc.

[0042] Step 102: determining the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object.

[0043] In the embodiment of the present invention, the semantic identifier includes a semantic prefix and a first identifier, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, and the first identifier is the source identification information of the target object. Figure 2 The structure corresponding to the semantic identifier in an application example is shown. Figure 2 As shown in the figure, the semantic identifier (S-Code) is mainly composed of two parts, the semantic prefix and the legacy identifier, which are connected by the symbol " / ". The prefix part in the S-Code corresponds to a class in the unmanned supermarket ontology. In actual application, a label is added to each class in the unmanned supermarket ontology. The value of the label is a code composed of a segment of numbers, and each class has a unique label code. Figure 3 As shown, the label code corresponding to the class Person is 1001, and the label code corresponding to the class Coffee is 3002. Therefore, according to the semantic prefix in the S-Code, the category of the target object can be determined, and thus the instance corresponding to the S-Code in the unmanned supermarket ontology can be determined. The name of the instance can be the S-Code identifier.

[0044] Step 103: parse the instance according to the first attribute of the instance.

[0045] Since the first identifier in S-Code is the source identification information, it is often impossible to uniformly resolve heterogeneous identifiers. In the embodiment of the present invention, in order to be compatible with existing heterogeneous identifiers, the data attribute Legacy_ID_Category (i.e., the first attribute) is defined in the unmanned supermarket ontology, and the category of the heterogeneous identifier compatible with S-Code is judged by its attribute value, so that the corresponding identifier resolution system can be selected according to the category of the source identification information for unified resolution, thereby determining the target object corresponding to the instance during encoding. Through semantic identification, all objects with heterogeneous identifiers in the unmanned supermarket system can be mapped to an instance in the unmanned supermarket ontology, and unified resolution of heterogeneous identifiers is supported.

[0046] In an application example, Figure 4 As shown, the unmanned supermarket entity (i.e. Figure 4 The four types of objects (people, supermarkets, commodities, and payments) in the IoT Ontology in the unmanned supermarket ontology have different source identification information. Commodities (coffee) are identified by EAN codes, people are identified by passport numbers, supermarkets are identified by the party location code (GLN), and payment methods are identified by credit card numbers. S-Code adds different semantic prefixes based on the source identification information to indicate different categories in the unmanned supermarket ontology. For example, 1001 indicates that the object is a person who enters a supermarket to consume. In addition, the system category of the source identification corresponds to the Legacy_ID_Category attribute value of the mapped ontology instance. For example, the value of the Legacy_ID_Category attribute of the supermarket instance is GLN, indicating that the source identification information is a GLN code. In this way, the instance corresponding to the target object in the unmanned supermarket ontology can be determined by obtaining the S-Code of the target object.

[0047] In the unmanned supermarket ontology, in addition to realizing the collection of different IoT objects through classes (Class), attribute information is also required to describe the relationship between instances and the inherent characteristics of instances. The attributes of the unmanned supermarket ontology include object attributes and data attributes. In one embodiment, the unmanned supermarket data processing method also includes: determining the object attributes of the unmanned supermarket ontology based on the association relationship between instances of different classes in the unmanned supermarket ontology; and / or, determining the data attributes of the unmanned supermarket ontology based on the characteristic parameters corresponding to the instances in the unmanned supermarket ontology.

[0048] In one embodiment, the object attributes include at least one of the following: a second attribute for associating the supermarket with the customer, a third attribute for associating the supermarket with the goods, a fourth attribute for associating the customer with the goods, a fifth attribute for associating the customer with the payment account, and a sixth attribute for associating the goods with the payment account.

[0049] In one embodiment, in addition to the aforementioned first attribute, the data attribute also includes at least one of the following: a seventh attribute for determining the price of the goods, an eighth attribute for determining the sales time of the goods, a ninth attribute for determining the returnable deadline of the goods, a tenth attribute for determining whether the goods can be returned, an eleventh attribute for determining the amount to be paid by the payment account, and a twelfth attribute for determining the brand of the goods. Accordingly, the characteristic parameters of the goods object may include price, sales time, returnable deadline, whether the goods can be returned, brand, etc., and the characteristic parameters of the account object may include the amount to be paid.

[0050] In an application example, the object attributes of the unmanned supermarket entity are shown in Table 1.

[0051] Property Name Domain range hasPerson Store Person hasCommodity Store Commodity Buy Person Commodity hasPayment Person Payment paidBy Commodity Payment

[0052] Table 1

[0053] Among them, hasPerson (i.e. the second attribute) has a domain of "Store" class and a range of "Person" class, which is used to indicate which customers are in a supermarket; hasCommodity (i.e. the third attribute) has a domain of "Store" class and a range of "Commodity", which indicates which commodities are in the supermarket; Buy (i.e. the fourth attribute) has a domain of "Person" and a range of "Commodity", which indicates which commodities a person has bought; hasPayment (i.e. the fifth attribute) has a domain of "Person" and a range of "Payment", which indicates a person's payment account; payedBy (i.e. the sixth attribute) has a domain of "Commodity" and a range of "Payment", which indicates which account a commodity is settled through.

[0054] In an application example, the data attributes of the unmanned supermarket entity are shown in Table 2.

[0055] Property Name Domain range Legacy_ID_Category Thing xs:string hasPrice Commodity xs:float saleTime Commodity xs:dateTime returnableDays Commodity xs:int isReturnable Commodity xs:boolean paymentAmount Payment xs:float hasBrand Commodity xs:string

[0056] Table 2

[0057] Among them, Legacy_ID_Category (i.e. the first attribute) represents the identification resolution system corresponding to the source identification information of the IoT object; hasPrice (i.e. the seventh attribute) represents the price information of a commodity; saleTime (i.e. the eighth attribute) represents the sales time of a commodity, returnableDays (i.e. the ninth attribute) represents the number of days for return; isReturnable (i.e. the tenth attribute) represents whether a commodity can be returned; paymentAmount (i.e. the eleventh attribute) represents the amount that the customer account needs to pay for the purchased commodity; hasBrand (i.e. the twelfth attribute) represents the brand information of the commodity.

[0058] In the embodiment of the present invention, the connection between the IoT objects in the unmanned supermarket and their description information can be determined through the object attributes and data attributes of the unmanned supermarket entity, so that semantic query can be used to determine who enters the supermarket, what they buy, how much money they need to pay, and which account to use to pay, so as to automatically realize a complete automatic shopping settlement process.

[0059] In order to make the information of the object attributes and data attributes of the unmanned supermarket entity complete, in one embodiment, the method also includes: updating the object attributes and / or the data attributes of the unmanned supermarket entity according to rules; wherein the rules include at least one of the following: a first rule for determining the correspondence between the goods object and the account object in the supermarket object; a second rule for determining whether the goods object exceeds the return deadline.

[0060] In an application example, the first rule includes two inference rules, rule1 and rule2. Rule1 means that if a customer B enters supermarket a and buys product c, which is a product of supermarket a, and customer B's payment account is d, then this product c should be settled by account d. Rule2 means that the price of product a is b, customer C buys product a, and a is settled through account d, then the amount that account d needs to pay is b. Based on the joint reasoning of rule1 and rule2, it can be inferred which account should pay how much money for the supermarket's products.

[0061] In an application example, the second rule includes rule 3, which indicates that if product b belongs to supermarket a, b is sold at time c, the number of days for return of b is d, and the number of days f obtained by subtracting c from the return time e is less than or equal to the number of days for return d, then product b can be returned. This rule can be used to infer whether a product can be returned by the supermarket.

[0062] In one embodiment, the unmanned supermarket data processing method further includes: acquiring data information corresponding to a shopping event of a supermarket object, and updating the unmanned supermarket entity based on the data information.

[0063] Here, the shopping events of the supermarket object include: the behavior of people entering and exiting the unmanned supermarket, the behavior of people taking away goods, and the behavior of people returning goods. In actual application, various shopping events can be detected based on visual recognition technology, radio frequency identification (RFID) technology, etc., so as to obtain data information corresponding to each shopping event and update the object attributes and / or data attributes of the unmanned supermarket entity.

[0064] In one embodiment, the unmanned supermarket data processing method further includes: outputting corresponding query results based on input information corresponding to the semantic query. Business operations related to the intelligent management of unmanned supermarkets can be implemented through semantic query. The business operations may include: intelligent settlement, intelligent return, intelligent shopping guide and other applications.

[0065] In one embodiment, outputting corresponding query results based on input information corresponding to the semantic query includes:

[0066] Acquire first semantic query input information, where the first voice query input information includes a semantic identifier corresponding to a supermarket object;

[0067] Determining an instance corresponding to the supermarket object in the unmanned supermarket ontology based on the semantic identifier corresponding to the supermarket object;

[0068] determining, based on the second attribute, an instance of the customer associated with the instance corresponding to the supermarket object;

[0069] determining, based on the instance of the customer and the fourth attribute, an instance of the goods associated with the instance of the customer;

[0070] determining, based on the instance of the good and the sixth attribute, an instance of the payment account associated with the instance of the good;

[0071] The payment information corresponding to the instance of the goods is sent to the payment account corresponding to the instance of the payment account.

[0072] In this way, corresponding payment information can be generated for goods that have been sold but not yet settled in a supermarket object to facilitate intelligent settlement.

[0073] In one embodiment, outputting corresponding query results based on input information corresponding to the semantic query includes:

[0074] Acquire second semantic query input information, where the second voice query input information includes a semantic identifier corresponding to a cargo object;

[0075] Determining an instance corresponding to the cargo object in the unmanned supermarket ontology based on the semantic identifier corresponding to the cargo object;

[0076] Based on the eighth attribute, the ninth attribute and the current query time of the instance corresponding to the cargo object, it is determined whether the cargo object supports return, and if so, a first prompt message of successful return is generated.

[0077] In this way, the automatic return of a certain product can be achieved without the intervention of staff, thus realizing self-service returns in unmanned supermarkets.

[0078] In one embodiment, outputting corresponding query results based on input information corresponding to the semantic query includes:

[0079] Acquire third semantic query input information, wherein the third voice query input information includes a semantic identifier corresponding to a cargo object and a query condition;

[0080] Determining, in the unmanned supermarket ontology, data attributes corresponding to the goods object that meet the query condition based on the semantic identifier corresponding to the goods object;

[0081] Display the data attributes corresponding to the cargo object;

[0082] The query condition includes at least one of the following: price query condition and brand query condition.

[0083] In this way, intelligent shopping guide for goods in unmanned supermarkets can be realized. Users can query the data attributes corresponding to the goods according to the query conditions of the goods, which is convenient for users to purchase according to the price, brand and other attributes of the goods.

[0084] The unmanned supermarket data processing method of the embodiment of the present invention supports unified parsing of source identification information through semantic identification of IoT objects with compatible heterogeneous identification, and can support interaction between IoT objects with heterogeneous identification, thereby supporting multiple identity verification methods and multiple payment methods. Compared with unmanned supermarkets using homogeneous identification, the application of the method is more flexible and it is convenient to truly realize unmanned management of unmanned supermarkets.

[0085] In addition, the unmanned supermarket data processing method of the embodiment of the present invention updates the object attributes and / or the data attributes of the unmanned supermarket entity according to the rules; and can meet the intelligent interaction requirements between instances.

[0086] In addition, the unmanned supermarket data processing method of the embodiment of the present invention can support the automatic recording of self-service shopping, self-service return and other behaviors in the unmanned supermarket by acquiring data information corresponding to the shopping events of the supermarket object and updating the unmanned supermarket body based on the data information.

[0087] Thirdly, the unmanned supermarket data processing method of the embodiment of the present invention can realize business operations related to the intelligent management of the unmanned supermarket through semantic query, enrich the self-service business of the unmanned supermarket, and support the unmanned operation of the entire unmanned supermarket system.

[0088] The present invention is further described in detail below in conjunction with application examples.

[0089] Figure 5 This is a flow chart of the unmanned supermarket data processing method of the application embodiment of the present invention. In this application embodiment, after the unmanned supermarket entity is created, various objects in the supermarket identified by S-Code can be intelligently interacted and collaborated unattended through the following process, thereby realizing self-service shopping and settlement. The specific process is as follows:

[0090] 1. Map the IoT objects identified by S-Code to the unmanned supermarket ontology according to the semantic prefix, and make them instances of different classes. The names of the instances are the values ​​identified by S-Code.

[0091] 2. Continue to add or update the data generated by the supermarket object (i.e., the data information corresponding to the shopping event) to the unmanned supermarket ontology. For example, when a customer (1001 / E501129487) enters the supermarket through identity authentication, add an instance of this customer to the "Person" class, and the instance name is his S-Code identifier; add a hasPerson attribute between the supermarket instance (1002 / 8713381138577) and the 1001 / E501129487 instance. If this customer takes a product (3002 / 8938515483013), add a Buy attribute between the 1001 / E501129487 instance and 3002 / 8938515483013. If the customer puts the product back, the Buy attribute between the two is deleted from the ontology. The identification of the goods purchased by customers in the unmanned supermarket is directly implemented by visual recognition technology, RFID technology, etc., which will not be elaborated here.

[0092] 3. Set inference rules to perform logical reasoning on the unmanned supermarket entity to obtain more implicit knowledge. For example, rule r: if (?a Buy?b), (?a hasPayment?c)→(?b payedBy?c) means that if a person a buys commodity b and a's account is c, then commodity b is paid by c. Based on the inference result of rule r, it can be determined which account a commodity is paid by.

[0093] 4. Based on the inferred ontology, semantic retrieval is performed through the SPARQL ontology query language to obtain the actions to be triggered by each object in the supermarket, such as paying a certain amount from an account, receiving a return from the supermarket, etc.

[0094] Based on the above workflow, on the basis of semantic identification and unmanned supermarket ontology, some typical application examples in the unmanned supermarket system are introduced through specific reasoning rules and SPARQL query statements.

[0095] 1) Self-service shopping

[0096] For self-service shopping and settlement, this application embodiment designs two reasoning rules, rule 1 and rule 2. Rule 1 means that if a customer B enters supermarket a and buys product c, which is a product of supermarket a, and customer B's payment account is d, then this product c should be settled by account d. Rule 2 means that the price of product a is b, customer c buys product a, and a settles through account d, then the amount that account d needs to pay is b. Based on the joint reasoning of rule 1 and rule 2, it can be inferred which account should pay how much money for the supermarket's products.

[0097] rule1:if(?a hasPerson?b),(?b Buy?c),(?a hasCommodity?c),(?bhasPayment?d)→(?c paidBy?d)

[0098] rule2:if(?a hasPrice?b),(?c Buy?a),(?a paidBy?d)→(?d paymentAmount?b)

[0099] By reasoning about the ontology and semantic rules, we get the reasoned ontology. We can use the following SPARQl query language to retrieve the payment information corresponding to the goods (i.e., goods) in the supermarket (1002 / 8713381138577) from the current ontology. The customer and payment information corresponding to the goods in the unmanned supermarket are shown in Table 3. Then, according to the Legacy_ID_Category information of the Payment instance, we can determine the account type and complete the payment of the specified amount through the corresponding payment system.

[0100] SPARQL1:

[0101] Select? Person? Commodity? Payment? Amount where{

[0102] "1002 / 8713381138577"hasPerson? Person.

[0103] ? Person Buy? Commodity.

[0104] ? Commodity paidBy? Payment.

[0105] ? Payment paymentAmount? Amount.}

[0106] Person Commodity Payment Amount 1001 / E501129487 3002 / 8938515483013 1003 / 6221260012170051 18 1001 / wx3000570 2003 / 80050278 1003 / 134644030642599578 20 1001 / 110111199711021111 3004 / 6901285991530 1003 / Jeff@gmai.com 5

[0107] Table 32), Self-service return

[0108] For self-service returns, this application embodiment designs the following inference rules. If product b belongs to supermarket a, b is sold at time c, the number of days for b to be returned is d, and the number of days f obtained by subtracting c from the return time e is less than or equal to the number of days for return d, then product b can be returned. This rule can be used to infer whether a product can be returned by the supermarket.

[0109] rule3:(?a hasCommodity?b),(?b saleTime?c),(?b returnableDays?d),le(difference(now(?e),?c,?f),?d)→(?b isReturnable'true')

[0110] After reasoning with the supermarket ontology and rule 3, the information on whether the product accepts returns can be obtained through SPARQL2 query statements. As shown in Table 4, when the return event occurs on March 22, 2019, the first product can be returned, and the second product will not be supported for return because it has exceeded the returnable days.

[0111] SPARQL2:

[0112] Select? Commodity? day? time? return where{

[0113] ? Commodity returnableDays? day.

[0114] ? Commodity saleTime? time.

[0115] ? Commodity isReturnable? return.}

[0116] Commodity day time return 3004 / 6901285991240 2019-3-15 7 true 3004 / 6921168509256 2019-3-10 7 false

[0117] Table 4

[0118] 3) Smart shopping guide

[0119] Based on the unmanned supermarket ontology, the intelligent shopping guide task can be realized. SPARQL3 is a query statement for drinking water with a price not exceeding 3 yuan. The query result returns the S-Code identifier, price and brand of the product, as shown in Table 5. Corresponding to different shopping guide needs, they can all be completed through corresponding SPARQL semantic queries.

[0120] SPARQL3:

[0121] Select? Commodity? Price? Brand where{

[0122] ? Commodity rdf:type:Water.

[0123] ? Commodity:hasPrice? Price.

[0124] ? Commodity:hasBrand? Brand.

[0125] FILTER(?Price<=3)}

[0126] Commodity Price Brand 3004 / 6901285991240 1.5 Yibao 3004 / 6921168509256 2.0 Nongfu Spring

[0127] Table 5

[0128] In order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides an unmanned supermarket data processing device, such as Figure 6 As shown, the device comprises:

[0129] An acquisition module 601 is used to acquire a semantic identifier of a target object;

[0130] A determination module 602 is used to determine the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object;

[0131] A parsing module 603, configured to parse the instance according to the first attribute of the instance;

[0132] Among them, the semantic identifier includes a semantic prefix and a first identifier, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, the first identifier is the source identification information of the target object, and the first attribute is used to determine the identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system.

[0133] In some embodiments, the device further includes: an identification module 604, which is used to create the semantic identification for the target object, and the semantic identification is determined based on the source identification information of the target object and the class to which the target object belongs in the unmanned supermarket ontology.

[0134] In some embodiments, the determination module 602 is also used to: determine the object attributes of the unmanned supermarket entity based on the association relationship between instances of different classes in the unmanned supermarket entity; and / or determine the data attributes of the unmanned supermarket entity based on the characteristic parameters corresponding to the instances in the unmanned supermarket entity.

[0135] Among them, the classes in the unmanned supermarket ontology include: supermarket, goods, customers, payment accounts;

[0136] The object attributes include at least one of the following: a second attribute for associating the supermarket with the customer, a third attribute for associating the supermarket with the goods, a fourth attribute for associating the customer with the goods, a fifth attribute for associating the customer with the payment account, and a sixth attribute for associating the goods with the payment account;

[0137] The data attributes also include at least one of the following: a seventh attribute for determining the price of the goods, an eighth attribute for determining the sales time of the goods, a ninth attribute for determining the return deadline of the goods, a tenth attribute for determining whether the goods can be returned, an eleventh attribute for determining the amount required to be paid by the payment account, and a twelfth attribute for determining the brand of the goods.

[0138] In some embodiments, the device also includes: an inference module 605, which is used to: update the object attributes and / or the data attributes of the unmanned supermarket entity according to rules; wherein the rules include at least one of the following: a first rule for determining the correspondence between the goods object and the account object in the supermarket object; a second rule for determining whether the goods object exceeds the return deadline.

[0139] In some embodiments, the device further includes: an updating module 606, which is used to obtain data information corresponding to shopping events of the supermarket object, and update the unmanned supermarket body based on the data information.

[0140] In some embodiments, the device further includes: a semantic query module 607, which is used to output corresponding query results based on input information corresponding to the semantic query.

[0141] In some embodiments, the semantic query module 607 is specifically used to:

[0142] Acquire first semantic query input information, where the first voice query input information includes a semantic identifier corresponding to a supermarket object;

[0143] Determining an instance corresponding to the supermarket object in the unmanned supermarket ontology based on the semantic identifier corresponding to the supermarket object;

[0144] determining, based on the second attribute, an instance of the customer associated with the instance corresponding to the supermarket object;

[0145] determining, based on the instance of the customer and the fourth attribute, an instance of the goods associated with the instance of the customer;

[0146] determining, based on the instance of the good and the sixth attribute, an instance of the payment account associated with the instance of the good;

[0147] The payment information corresponding to the instance of the goods is sent to the payment account corresponding to the instance of the payment account.

[0148] In some embodiments, the semantic query module 607 is specifically used to:

[0149] Acquire second semantic query input information, where the second voice query input information includes a semantic identifier corresponding to a cargo object;

[0150] Determining an instance corresponding to the cargo object in the unmanned supermarket ontology based on the semantic identifier corresponding to the cargo object;

[0151] Based on the eighth attribute, the ninth attribute and the current query time of the instance corresponding to the cargo object, it is determined whether the cargo object supports return, and if so, a first prompt message of successful return is generated.

[0152] In some embodiments, the semantic query module 607 is specifically used to:

[0153] Acquire third semantic query input information, wherein the third voice query input information includes a semantic identifier corresponding to a cargo object and a query condition;

[0154] Determining, in the unmanned supermarket ontology, data attributes corresponding to the goods object that meet the query condition based on the semantic identifier corresponding to the goods object;

[0155] Display the data attributes corresponding to the cargo object;

[0156] The query condition includes at least one of the following: price query condition and brand query condition.

[0157] In actual application, the acquisition module 601, the determination module 602, the analysis module 603, the identification module 604, the reasoning module 605, the update module 606 and the semantic query module 607 can be implemented by a processor in the unmanned supermarket data processing device. Of course, the processor needs to run the computer program in the memory to realize its function.

[0158] It should be noted that: the unmanned supermarket data processing device provided in the above embodiment only uses the division of the above program modules as an example when performing unmanned supermarket data processing. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the unmanned supermarket data processing device provided in the above embodiment and the unmanned supermarket data processing method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0159] Based on the hardware implementation of the above program modules and in order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides an unmanned supermarket data processing system. Figure 7 Only the exemplary structure of the unmanned supermarket data processing system is shown, not the entire structure, and can be implemented as needed. Figure 7 Partial or complete structure shown.

[0160] like Figure 7 As shown, the unmanned supermarket data processing system 700 provided in the embodiment of the present invention includes: at least one processor 701, a memory 702, a user interface 703 and at least one network interface 704. The various components in the unmanned supermarket data processing system 700 are coupled together through a bus system 705. It can be understood that the bus system 705 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 705 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 7 Various buses are labeled as bus system 705.

[0161] The user interface 703 may include a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad or a touch screen.

[0162] The memory 702 in the embodiment of the present invention is used to store various types of data to support the operation of the unmanned supermarket data processing system. Examples of such data include: any computer program used to operate on the unmanned supermarket data processing system.

[0163] The unmanned supermarket data processing method disclosed in the embodiment of the present invention can be applied to the processor 701, or implemented by the processor 701. The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the unmanned supermarket data processing method can be completed by the hardware integrated logic circuit or software instructions in the processor 701. The above-mentioned processor 701 can be a general-purpose processor, a digital signal processor (DSP, DigitalSignal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 701 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 702. The processor 701 reads the information in the memory 702 and completes the steps of the unmanned supermarket data processing method provided in the embodiment of the present invention in combination with its hardware.

[0164] In an exemplary embodiment, the unmanned supermarket data processing system can be implemented by one or more application-specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), FPGA, general-purpose processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned method.

[0165] It can be understood that the memory 702 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0166] In an exemplary embodiment, the present invention also provides a storage medium, namely a computer storage medium, which can be a computer-readable storage medium, for example, a memory 702 storing a computer program, and the computer program can be executed by a processor 701 of the unmanned supermarket data processing system to complete the steps described in the method of the present invention. The computer-readable storage medium can be a memory such as a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disk, or a CD-ROM.

[0167] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0168] In addition, the technical solutions described in the embodiments of the present invention can be arbitrarily combined without conflict.

[0169] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for processing data in an unmanned supermarket, characterized in that: include: Get the semantic identification of the target object; Determine the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object; parsing the instance according to a first attribute of the instance; The target object is an IoT object with a semantic identifier, the semantic identifier includes a semantic prefix and a first identifier, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, the first identifier is the source identifier information of the target object, and the first attribute is used to determine the identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system; The method further comprises: Determining the object attributes of the unmanned supermarket ontology based on the association relationship between instances of different classes in the unmanned supermarket ontology; and / or, Determine the data attributes of the unmanned supermarket ontology based on the characteristic parameters corresponding to the instances in the unmanned supermarket ontology; Among them, the classes in the unmanned supermarket ontology include: supermarket, goods, customers, payment accounts; The object attribute includes at least one of the following: a second attribute for associating the supermarket with the customer, a third attribute for associating the supermarket with the goods, a fourth attribute for associating the customer with the goods, a fifth attribute for associating the customer with the payment account, and a sixth attribute for associating the goods with the payment account; The data attributes include the first attribute, and the data attributes also include at least one of the following: a seventh attribute for determining the price of the goods, an eighth attribute for determining the sales time of the goods, a ninth attribute for determining the return deadline of the goods, a tenth attribute for determining whether the goods can be returned, an eleventh attribute for determining the amount required to be paid by the payment account, and a twelfth attribute for determining the brand of the goods.

2. The method according to claim 1, characterized in that The method further comprises: The semantic identifier is created for the target object, where the semantic identifier is determined based on the source identifier information of the target object and the class to which the target object belongs in the unmanned supermarket ontology.

3. The method according to claim 1, characterized in that The method further comprises: Update the object attributes and / or the data attributes of the unmanned supermarket entity according to the rules; The rules include at least one of the following: A first rule for determining a correspondence between a commodity object and an account object in a supermarket object; A second rule is used to determine whether a cargo object has exceeded a return deadline.

4. The method according to claim 1, characterized in that: The method further comprises: The data information corresponding to the shopping event of the supermarket object is obtained, and the unmanned supermarket entity is updated based on the data information.

5. The method according to claim 1, characterized in that The method further comprises: Based on the input information corresponding to the semantic query, the corresponding query result is output.

6. The method according to claim 5, characterized in that The step of outputting corresponding query results based on input information corresponding to the semantic query includes: Acquire first semantic query input information, where the first semantic query input information includes a semantic identifier corresponding to a supermarket object; Determining an instance corresponding to the supermarket object in the unmanned supermarket ontology based on the semantic identifier corresponding to the supermarket object; determining, based on the second attribute, an instance of the customer associated with the instance corresponding to the supermarket object; determining, based on the instance of the customer and the fourth attribute, an instance of the goods associated with the instance of the customer; determining, based on the instance of the good and the sixth attribute, an instance of the payment account associated with the instance of the good; The payment information corresponding to the instance of the goods is sent to the payment account corresponding to the instance of the payment account.

7. The method according to claim 5, characterized in that The step of outputting corresponding query results based on input information corresponding to the semantic query includes: Acquire second semantic query input information, where the second semantic query input information includes a semantic identifier corresponding to a cargo object; Determining an instance corresponding to the cargo object in the unmanned supermarket ontology based on the semantic identifier corresponding to the cargo object; Based on the eighth attribute, the ninth attribute and the current query time of the instance corresponding to the cargo object, it is determined whether the cargo object supports return, and if so, a first prompt message of successful return is generated.

8. The method according to claim 5, characterized in that The step of outputting corresponding query results based on input information corresponding to the semantic query includes: Acquire third semantic query input information, wherein the third semantic query input information includes a semantic identifier corresponding to a cargo object and a query condition; Determining, in the unmanned supermarket ontology, data attributes corresponding to the goods object that meet the query condition based on the semantic identifier corresponding to the goods object; Display the data attributes corresponding to the cargo object; The query condition includes at least one of the following: price query condition and brand query condition.

9. An unmanned supermarket data processing device, characterized in that: include: An acquisition module, used to acquire the semantic identification of the target object; A determination module, used for determining the instance corresponding to the target object in the unmanned supermarket ontology based on the semantic identifier of the target object; A parsing module, configured to parse the instance according to a first attribute of the instance; The semantic identifier includes a semantic prefix and a first identifier, the semantic prefix is ​​used to identify the class to which the target object belongs in the unmanned supermarket ontology, the first identifier is the source identification information of the target object, and the first attribute is used to determine the identifier resolution system corresponding to the first identifier, so that the instance can be resolved according to the corresponding identifier resolution system; The determining module is further used for: Determine the object attributes of the unmanned supermarket ontology based on the association relationship between instances of different classes in the unmanned supermarket ontology; and / or determine the data attributes of the unmanned supermarket ontology based on the feature parameters corresponding to the instances in the unmanned supermarket ontology; Among them, the classes in the unmanned supermarket ontology include: supermarket, goods, customers, payment accounts; The object attribute includes at least one of the following: a second attribute for associating the supermarket with the customer, a third attribute for associating the supermarket with the goods, a fourth attribute for associating the customer with the goods, a fifth attribute for associating the customer with the payment account, and a sixth attribute for associating the goods with the payment account; The data attributes also include at least one of the following: a seventh attribute for determining the price of the goods, an eighth attribute for determining the sales time of the goods, a ninth attribute for determining the return deadline of the goods, a tenth attribute for determining whether the goods can be returned, an eleventh attribute for determining the amount required to be paid by the payment account, and a twelfth attribute for determining the brand of the goods.

10. An unmanned supermarket data processing system, characterized in that: include: A processor and a memory for storing a computer program that can be executed on the processor, wherein: The processor is used to execute the steps of the method according to any one of claims 1 to 8 when running a computer program.

11. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images