CN113487032A - Aquatic product HACCP knowledge reasoning system and method - Google Patents
Aquatic product HACCP knowledge reasoning system and method Download PDFInfo
- Publication number
- CN113487032A CN113487032A CN202110800202.4A CN202110800202A CN113487032A CN 113487032 A CN113487032 A CN 113487032A CN 202110800202 A CN202110800202 A CN 202110800202A CN 113487032 A CN113487032 A CN 113487032A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- haccp
- data
- aquatic product
- aquatic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000011059 hazard and critical control points analysis Methods 0.000 title abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000001965 increasing effect Effects 0.000 claims abstract description 10
- 230000002708 enhancing effect Effects 0.000 claims abstract description 6
- 241000237502 Ostreidae Species 0.000 claims description 38
- 235000020636 oyster Nutrition 0.000 claims description 38
- 238000012544 monitoring process Methods 0.000 claims description 36
- 238000000605 extraction Methods 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 10
- 235000013372 meat Nutrition 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 2
- 235000014102 seafood Nutrition 0.000 claims description 2
- 238000005728 strengthening Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000003860 storage Methods 0.000 description 10
- 238000005057 refrigeration Methods 0.000 description 8
- 239000002994 raw material Substances 0.000 description 7
- 244000052616 bacterial pathogen Species 0.000 description 6
- 235000013305 food Nutrition 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 239000003256 environmental substance Substances 0.000 description 3
- 231100000765 toxin Toxicity 0.000 description 3
- 238000011109 contamination Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 230000008929 regeneration Effects 0.000 description 2
- 238000011069 regeneration method Methods 0.000 description 2
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000003640 drug residue Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000009364 mariculture Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a system and a method for reasoning HACCP knowledge of aquatic products, wherein the method comprises the following steps: establishing an HACCP knowledge application model based on the HACCP schedule of the aquatic products, and analyzing the whole aquatic product business process and the standard structure of the HACCP system; analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure; scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products; and describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared. The aquatic product HACCP knowledge reasoning system and the method can improve the production safety of aquatic products and the application of HACCP.
Description
Technical Field
The invention relates to the technical field of aquatic product food safety, in particular to an aquatic product HACCP knowledge reasoning system and method.
Background
The aquatic product market in China is continuously improved in the production and consumption levels, the production taking artificial culture as a container shows a stable increase sign, the fresh water culture yield is stable, and the mariculture is rapidly developed. Meanwhile, the development of the aquatic product market gradually exposes the problems of production and sale links, the common drug residue problem and the pollution event of the environment of the aquaculture water area which appears from time to time, the narrow regional distribution of the sale link and the shortage of deep processing of the aquatic products, and all put forward higher requirements on how to produce high-quality aquatic products for further serving the citizens in the aquatic product industry.
Knowledge engineering studies how to organize knowledge in a computer, build a high quality knowledge base, how to enable the computer to acquire and search for useful knowledge, and how to use the knowledge to solve problems, i.e., acquisition, representation, and utilization of knowledge. The critical control point (HACCP) for hazard analysis is a comprehensive and systematic control system, has a strict record keeping program, is easy to find out the cause once a product has a problem, is beneficial to timely correcting errors and tracking and recovering the product, and avoids unacceptable health risks to consumers to the maximum extent. The HACCP related information has positive effects on the improvement of the cold chain safety and reliability, and can not only guide the specific operation of a service management layer, but also integrate the experience and knowledge accumulated by cold chain related decision makers in practical operation.
Chinese invention patent CN 109685522B discloses a food cold chain quality monitoring system and method, including: the system comprises an HACCP information base module, an information acquisition module, an information representation module, an information relationship determination module, an information relationship analysis module and a control module. The HACCP control plan of each key control link of upstream and downstream of the food cold chain can be determined more automatically and more completely, HACCP information can be transmitted and shared effectively in time, quality safety risks generated in the food cold chain business process are reduced, and cold chain management and control efficiency is improved.
However, the HACCP program of the system of the patent needs to be further improved, different kinds of aquatic products need to be considered in an expanding way, and a knowledge frame applicable to all the aquatic products is established, so that the system has higher practicability and application and popularization values.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an aquatic product HACCP knowledge reasoning system and method capable of improving the production safety and HACCP application of aquatic products.
In order to solve the problems, the technical scheme of the invention is as follows:
a seafood HACCP knowledge inference system, the system comprising:
a domain knowledge layer: based on an HACCP (aquatic product control and communications protocol) schedule, taking key control points as a core, wherein each key control point covers obvious hazards, key limit values, monitoring contents, deviation rectifying actions, verification and records to obtain related knowledge;
knowledge representation layer: analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure;
knowledge modeling layer: scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products; and
knowledge reasoning layer: describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared;
the domain knowledge layer is the basis of a knowledge representation layer, the knowledge representation layer is the basis of a knowledge modeling layer, and the knowledge modeling layer is the basis of a knowledge reasoning layer.
Optionally, the knowledge representation layer includes concept extraction, relationship extraction, rule extraction, and instance extraction.
Optionally, the knowledge modeling layer uses OWL2 language to implement semantic knowledge described by the model.
Optionally, a semantic web rules language SWRL is used to describe the business logic rules, so as to increase the automatic reasoning capability of the knowledge.
Further, the invention also provides a method for reasoning the HACCP knowledge of aquatic products, which comprises the following steps:
establishing an HACCP knowledge application model based on the HACCP schedule of the aquatic products, and analyzing the whole aquatic product business process and the standard structure of the HACCP system;
analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure;
scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products; and
and describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared.
Optionally, the HACCP knowledge application model is extracted based on an HACCP schedule of raw oysters, and discussions are carried out around three key control points of live oyster receiving, dry refrigeration and oyster meat storage, wherein each key control point covers significant hazards, key limit values, monitoring contents, deviation rectifying actions, verification and records to obtain related knowledge.
Optionally, the step of analyzing semantics among data by using a description logic language to enhance understanding of the data by a machine, so that the data is abstracted into a knowledge structure specifically includes: abstracting knowledge in the HACCP plan table of the aquatic product into a concept set, a relation set, a rule set and an entity set.
Optionally, the step of scientifically representing, acquiring, organizing and storing the knowledge in the HACCP schedule of the aquatic product specifically includes:
determining the domain and the range of the ontology;
enumerating important concepts, terms, etc. in the art;
defining a class;
defining attributes of the class;
defining the relationship among concepts in the field;
an instance is created.
Optionally, in the step of describing the business logic rules and increasing the automatic reasoning capability of knowledge to effectively perfect and share the links of the HACCP of the aquatic products, the business logic rules are described by using a semantic network rule language SWRL to increase the automatic reasoning capability of knowledge.
Compared with the prior art, the aquatic product HACCP knowledge inference system and the method combine knowledge modeling with the HACCP standard of the aquatic product to construct a cold chain HACCP knowledge application model, monitor, correct and record the processes of receiving, refrigerating, storing and the like of the aquatic product, carry out semantic description on knowledge formed in the HACCP, enable the knowledge to be uniformly expressed and shared in each link of the cold chain, provide technical support for a decision maker in a semantic mode, and have important practical significance for further improving the production safety of the aquatic product and the application of the HACCP.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a block diagram of a knowledge inference system for HACCP of aquatic products according to an embodiment of the present invention;
FIG. 2 is a model block diagram of a aquatic product HACCP knowledge inference system provided by an embodiment of the invention;
FIG. 3 is a flow chart of a method for reasoning knowledge of HACCP of aquatic products according to an embodiment of the present invention;
FIG. 4 is another flow chart of the aquatic product HACCP knowledge inference method provided by the embodiment of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
The HACCP system is a scientific system for identifying, evaluating and controlling food safety hazards, and plans around seven main steps of key control points, hazard analysis, monitoring, deviation correction, verification and recording. An aquatic product Hazard Analysis and Critical Control Point (HACCP) system and an application guide thereof are provided for establishing a basic plan of the HACCP system, preparing steps of the HACCP plan, making the HACCP plan, controlling potential hazards and related hazards in aquatic products and applying guide for implementing and maintaining the HACCP system in the aquatic product processing industry on the basis of the HACCP principle.
Specifically, in the embodiment of the invention, the HACCP plan of the aquatic product is based on the HACCP plan of the raw oysters, a cold chain HACCP knowledge application model is constructed, and the whole raw oyster business process and the detailed interpretation of the HACCP system standard structure are analyzed.
Fig. 1 is a structural block diagram of an aquatic product HACCP knowledge inference system provided in an embodiment of the present invention, and fig. 2 is a model block diagram of the aquatic product HACCP knowledge inference system provided in an embodiment of the present invention, and as shown in fig. 1 and fig. 2, the system includes: the system comprises a domain knowledge layer 1, a knowledge representation layer 2, a knowledge modeling layer 3 and a knowledge reasoning layer 4. The domain knowledge layer 1 is the basis of the knowledge representation layer 2, the knowledge representation layer 2 is the basis of the knowledge modeling layer 3, and the knowledge modeling layer 3 is the basis of the knowledge reasoning layer 4, so that the domain knowledge layer 1 is the basis of the research of the invention and can carry out extensive analysis on knowledge in the domain, thereby being important for extracting concepts, relations and the like.
The domain knowledge layer 1 is based on an HACCP schedule of aquatic products and comprises seven steps of HACCP, the seven steps of HACCP take a key control point as a core, and other principles surround the key control point to provide services for users. The HACCP system has both structured knowledge and unstructured knowledge and is related to workflow problems, so that the related knowledge in the HACCP is accurately described, the understanding of a machine to data is enhanced, and a good foundation is laid for subsequent practical application to become a key problem to be solved.
In the embodiment, discussion is carried out around three key control points of live oyster receiving, dry refrigeration and oyster meat storage, and each key control point covers significant hazards, key limit values, monitoring contents, deviation rectifying actions, verification and records so as to acquire related knowledge. The live oysters are subjected to dry refrigeration and then stored in the oyster meat, and the raw materials are supplied by a fisher and are fished to generate marks such as a fishing signboard, a fishing license, a fishing time board and the like. The oyster is processed by a production processor, and the embodiment is directed to raw oysters, so the processing process is only simple treatment on the oysters. The logistics transportation party is responsible for transporting the uncooked oysters from the fishing to the cold storage and from the cold storage to the storage room, so that the safety of food in the transportation process is ensured. And finally, the retailer is responsible for selling the product to the consumer. The live oysters receive four obvious hazards including pathogenic bacteria pollution, pathogenic bacteria growth, environmental chemical pollution and natural toxin, and a HACCP plan is made for each hazard.
And (3) determining that the growth of pathogenic bacteria is obvious harm in the dry refrigeration and oyster meat storage links, and establishing a HACCP plan around the growth of the pathogenic bacteria. In implementing HACCP programs, there is monitoring information like licenses that need to be proven scientifically and reasonably in each business process. The monitoring content monitors the temperature, time and the like which may be included in the key limit value, if the requirement of the key limit value is met, the receiving record is directly generated, and if the requirement of the key limit value is not met, the rejected deviation rectifying action is generated. Meanwhile, monitoring, deviation correction and the like need to be verified, and whether the monitoring result meets the requirement of a key limit value or not, the monitoring result is recorded to be used as the basis for receiving or rejecting the batch of goods.
The knowledge representation layer 2 includes concept extraction, relationship extraction, rule extraction, and instance extraction.
Specifically, the semantics among the data are analyzed by adopting a description logic language, so that the understanding of a machine to the data is enhanced, and the data is abstracted into a knowledge structure. The HACCP semantic of the raw oyster is expressed as a quadruple: use-HACCP ═ { C, R, U, I }, where C (concept) is the set of concepts in the field; r (relationship) is the set of attribute relationships of the domain concept; u (rule) is a set of associative rules described using SWRL; i (instant) is a relevant example extracted on the basis of the HACCP schedule of raw oysters.
1. Concept extraction
The establishment of a complete concept extraction set is the basis of establishing an ontology, and a concept set C of use-HACCP comprises an aquatic product cold chain role concept, a hazard analysis and key control point concept, an aquatic product cold chain business process concept and a monitoring information carrier concept.
The role concept in the aquatic product cold chain mainly comprises a raw material supplier, a production processor, a logistics transporter, a retailer and the like, wherein the raw material supplier is responsible for providing required raw materials, the production processor is responsible for processing, the raw materials are delivered to a wholesaler, and the raw materials are conveyed to the retailer through the logistics transporter.
According to seven principles of HACCP, the HACCP is divided into obvious hazards, key control points, key limit values, monitoring contents, deviation rectifying actions, verification and recording. According to the HACCP system of aquatic products and the HACCP schedule of the raw oyster in the application guide, the hazard analysis also comprises four hazards of pathogenic bacteria pollution, pathogenic bacteria growth, environmental chemical pollution and natural toxin. The key limit value defines whether the product is qualified or not, and scientific and reasonable key limit values can be formulated from the aspects of temperature, time, inspection and detection indexes, limiting parameters, allowed operation index parameters and the like.
The business process concept is an abstraction of concrete steps in the aquatic product cold chain business process, the cold chain business process is divided into three links of a receiving link, a dry refrigeration link and a storage link according to the needs of the text, and the business processes of a cold chain transportation link, a selling link, goods acceptance inspection and the like can be added according to the needs subsequently.
The concept of monitoring information carriers is used to prove that a certain step in the process is scientific and reasonable, and is a requirement for proving that the step meets a key limit value by evidence.
2. Relationship extraction
The relationship is a "bridge" connecting two concepts, subject and object linked by attributes. The subject in the present invention represents a concept that triggers the attribute action, and the object represents a concept that triggers the attribute action. It is these attributes that form a set of relationships that represent interactions between concepts in the domain. There are five relationships in use-HACCP:
(1) part-of expresses the relationship between the concepts in part and in whole, for example, the contents of the monitored object, method, frequency, and person in charge are included in the monitored contents.
(2) The kind-of expresses an inheritance relationship between concepts similar to that between parent and child classes in object oriented, such as pathogenic contamination, pathogenic growth, environmental chemical contamination, natural toxins, etc., among the significant hazards.
(3) instance-of expresses the relationship between instances of concepts and concepts, similar to the relationship between objects and classes in object-oriented, each concept may have multiple instances, e.g., fishing-to-cold time is an instance that belongs to a critical limit.
(4) attribute-of expresses that a certain concept is an attribute of another concept, e.g., temperature, time, detection index, etc., are attributes belonging to key limits.
(5) The self-defined relationship set is divided into a concept attribute and a data attribute.
Concept attributes connect different concepts by creating a relationship, for example, for the relationship "next step", meaning the next link, the subject and object that it acts on are both cold chain business processes.
In addition, some of the concept attributes have their own attributes. The concept attribute next _ step describes the logical relationship between the front and the back of the cold chain service step time, and has transitivity, so that the symmetric attribute is set for the next _ step, and the transitivity characteristic is increased. The concept attribute monitor _ CL is added with an inverse attribute monitor _ by for describing a monitoring measure to monitor the monitoring limit value. The concept attribute is _ charged _ by is added with an inverse attribute responsile _ for describing that the cold chain main body is responsible for the cold chain business flow. The concept attribute cause _ by is added with an inverse attribute cause for describing hazard analysis, which is the basis for establishing a key limit value. The concept attribute step _ generate _ proof is added with the inverse attribute proof _ from _ step for describing the formation of monitoring information in the cold chain business process.
The concepts are not only connected with each other in a relationship, but also have some data attributes belonging to the concepts, and the common data attributes are as follows: dataTime, double, float, int, integer, long, string, etc.
3. Rule extraction
A rule describes a logical inference that can be drawn upon some assertion in a specific form. The corresponding association on the class between a plurality of simple peer ontologies is realized by applying and expanding the SWRL (semantic web rule) rule, so that the aims of constructing ontologies and acquiring larger and more knowledge through the association between the ontologies are fulfilled. Both the preconditions and conclusions can include single or multiple basic propositions, with logical and relationships between the basic propositions, declarations in the form of if-then statements. In the constraint formula P (? ' indicates that the semantic element is some variable.
The principle of HACCP is to analyze raw materials, key production procedures and human factors influencing product safety, determine key links in the processing process, establish and perfect monitoring programs and monitoring standards, take standard corrective measures, and take records generated in each step as receiving records. Based on the raw oyster HACCP schedule, and referring to the contents of the domain knowledge layer, the relevant main rules in this document are as follows:
rule-1: if a Step instance Step in the cold chain has a certain obvious hazard, the key limit value of the corresponding preventive measure is provided according to the certain obvious hazard, the key limit value is monitored by the monitoring measure, and the record can be used for checking a deviation rectifying measure, so that the deviation rectifying measure is an instance of the deviation rectifying action and is generated in the Step instance. The rules are described as follows:
Has_HA_risk(？Step,？HA)，has_CL(？HA,？CL)，monitored_by(？CL,？CM)，CA_proved_by(？CA,？RE)→step_generate_CA(？Step,？CA)
rule-2: if a certain monitoring measure is implemented in a Step of a certain Step in the cold chain, the monitoring measure monitors the key limit value, and a monitored object information carrier (proof) records and proves the key limit value, the monitored object information carrier generated in the Step needs to be submitted in the Step so as to be used for a subsequent service Step to verify the cold chain damage monitoring effect in the Step. The rules are described as follows:
Has_CM(？Step,？CM)，monitor_CL(？CM,？CL)，CL_proved_by(？CL,？proof)，proof_from_step(？proof,？Step)→step_submit_proof(？Step,？proof)
rule-3: if there are Step1 and Step2 in the cold chain, and in the cold chain business process, Step2 is the business Step after Step1, the critical limit value in Step1 is monitored by the monitoring measure and is proved by the monitoring object information carrier Proof, then the critical limit value needs to be transferred to the next Step in Step 1. The rules are described as follows:
Differentfrom(？Step1,？Step2)，next_step(？Step1,？Step2)，proof_from_step(？proof,？step1)，monitored_by(？CL,？CM)，CL_proved_by(？CL,？proof)→step_deliver_CL(？Step1,？CL)
rule-4: if a Step instance Step in the cold chain has a certain obvious hazard, a certain monitoring measure is implemented, the key limit value is monitored by the obvious hazard, monitoring information is used as a record, the record can be used for checking a certain key limit value, a record can be generated in the Step instance, and a receiving record in the Step instance is recorded. The rules are described as follows:
Has_HA_risk(？Step,？HA)，Has_CM(？HA,？CM)，monitored_by(？CL,？CM)，has_RE(？CM,？RE)，CL_proved_by(？CL,？RE)→step_generate_RE(？Step,？RE)
rule-5: if the Step in the cold chain has a certain obvious hazard and each obvious hazard has a certain key limit value, the monitoring measures monitor the key limit values, the key limit values are proved by records, the monitoring measures are proved by records, and if errors exist, the deviation correcting measures are proved by records and are recorded. The rules are described as follows:
Has_HA_risk(？Step,？HA)，has_CL(？HA,？CL)，monitor_CL(？CM,？CL)，Cl_proved_by(？CL,？RE)，CM_proved_by(？CM,？RE)，has_CA(？CM,？CA)→CA_proved_by(？CA,？RE)
rule-6: if a certain key limit value exists in a Step in the cold chain, the monitoring measures monitor the key limit value, the monitoring information is proved by the record to generate deviation correction, and the verification measures verify the monitoring content, so that the verification information generates a relevant record. The rules are described as follows:
Has_CL(？Step,？CL)，monitor_CL(？CM,？CL)，CM_proved_by(？CM,？RE)，has_CA(？CM,？CA)，has_VE(？CM,？VE)→VE_generate_RE(？VE,？RE)
4. example extraction
In the foregoing, one of the limiting formulas in the SWRL rule is stated, in addition c (x): x may be an instance of a variable or an ontology, C is a class, stating that x is an instance of C. Such as:
CL(Limit_of_refrigeration_temperature)；
CM(monitoring_of_refrigeration_temperature)；
Monitor_CL(Limit_of_refrigeration_temperature，monitoring_of_refrigeration_temperature)；
this example describes a critical Limit of dry refrigerator temperature Limit of _ regeneration _ temperature, and a monitoring measure of refrigerator temperature monitoring threshold of _ regeneration _ temperature, which monitors the dry refrigerator temperature Limit.
On the basis of the HACCP plan of the raw oyster, an example related to the cold chain business is made.
The knowledge modeling layer 3 uses OWL2 language to realize semantic knowledge described by the model, and scientifically represents, acquires, organizes and stores knowledge in the HACCP schedule of the oysters.
Knowledge modeling in this embodiment refers specifically to ontology modeling, which is an explicit formal specification of a shared conceptual model. The body established in the embodiment mainly surrounds the process from catching to storing of the raw oysters, and aims to perfect the whole raw oyster HACCP plan and effectively perfect and share all links. And (3) adopting a top-down mode, and constructing an ontology in advance through an ontology editor by relying on knowledge obtained by structured data in the HACCP schedule of the uncooked oysters given by the national standard.
The knowledge reasoning layer 4 describes business logic rules by using a semantic network rule language SWRL, increases the automatic reasoning capability of knowledge, effectively perfects and shares all links of a cold chain, completes instantiation of raw oyster cold chain knowledge, provides knowledge services from the three aspects of live oyster receiving, dry refrigeration and oyster meat storage respectively, and realizes the practical application of HACCP in the cold chain.
Knowledge inference obtains new knowledge through rules or constraint conditions by an inference engine on the basis of ontology modeling, is a forward inference system and consists of a fact set, a rule set and an inference engine. The fact set stores facts in the current system, including concepts, concept attributes, and relationships, among others. The rule set consists of rules. The inference engine controls the execution of inference, matches the facts in the fact set with the condition part of the rule, triggers the set meeting the rule, selects one rule from the triggered multiple rules according to a certain strategy, and executes the selected rule to enrich the fact set.
Further, as shown in fig. 3, the present invention also provides a method for reasoning the HACCP knowledge of aquatic products, which comprises the following steps:
s1: establishing an HACCP knowledge application model based on the HACCP schedule of the aquatic products, and analyzing the whole aquatic product business process and the standard structure of the HACCP system;
specifically, the HACCP plan of the aquatic product in step S1 is based on the HACCP plan of raw oysters, the HACCP plan of raw oysters is provided by the national standard aquatic product HACCP system and the application guidelines thereof, the knowledge in step S1 is extracted based on the HACCP plan of raw oysters, and discussion is performed around three key control points, namely, live oyster receiving, dry refrigeration, and oyster meat storage, where each key control point covers significant hazards, key limit values, monitoring contents, corrective actions, verifications, and records, so as to obtain relevant knowledge.
S2: analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure;
specifically, the Description Logic (DL) language represents semantics among data, and enhances understanding of a machine on the data, so that the data is abstracted into a knowledge structure. The description logic is formalization of knowledge representation based on objects, is established on concepts and relations, is the basis of knowledge expression, and has strong expression capability and determinability.
In an alternative embodiment, the knowledge in the HACCP plan of the raw oysters is abstracted into a concept set, a relation set, a rule set and an entity set in step S2.
S3: scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products;
specifically, in the step S3, the OWL2 language is used to implement semantic knowledge described by the HACCP knowledge application model, improve the whole marine product HACCP plan, and scientifically represent, acquire, organize, and store knowledge in the HACCP plan table of the ecooyster.
As shown in fig. 4, the step S3 specifically includes:
s31: determining the domain and the range of the ontology;
s32: enumerating important concepts, terms, etc. in the field;
s33: defining a class;
s34: defining attributes of the class;
s35: defining the relationship among concepts in the field;
s36: an instance is created.
S4: and describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared.
Specifically, in the step S4, a semantic network rule language SWRL is used to describe business logic rules, so as to increase the automatic reasoning capability of knowledge, effectively perfect and share the links of the HACCP of the aquatic product, provide knowledge services from the three aspects of live oyster receiving, dry-method refrigeration and oyster meat storage, and realize the practical application of the HACCP in the cold chain.
Compared with the prior art, the aquatic product HACCP knowledge inference system and the aquatic product HACCP knowledge inference method combine knowledge modeling with the HACCP standard of the aquatic product, construct a cold chain HACCP knowledge application model, monitor, correct and record the processes of receiving, refrigerating, storing and the like of the aquatic product, semantically describe knowledge formed in the HACCP, enable the knowledge to be uniformly expressed and shared in each link of the cold chain, provide technical support for a decision maker in a semantic mode, and have important practical significance for further improving the production safety of the aquatic product and the application of the HACCP.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (9)
1. A seafood HACCP knowledge inference system, the system comprising:
a domain knowledge layer: based on an HACCP (aquatic product control and communications protocol) schedule, taking key control points as a core, wherein each key control point covers obvious hazards, key limit values, monitoring contents, deviation rectifying actions, verification and records to obtain related knowledge;
knowledge representation layer: analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure;
knowledge modeling layer: scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products; and
knowledge reasoning layer: describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared;
the domain knowledge layer is the basis of a knowledge representation layer, the knowledge representation layer is the basis of a knowledge modeling layer, and the knowledge modeling layer is the basis of a knowledge reasoning layer.
2. The aquatic product HACCP knowledge reasoning system of claim 1, wherein: the knowledge representation layer includes concept extraction, relationship extraction, rule extraction, and instance extraction.
3. The aquatic product HACCP knowledge reasoning system of claim 1, wherein: the knowledge modeling layer uses OWL2 language to realize semantic knowledge described by the model.
4. The aquatic product HACCP knowledge reasoning system of claim 1, wherein: and a semantic network rule language SWRL is used for describing service logic rules, so that the automatic reasoning capability of knowledge is improved.
5. A knowledge reasoning method for HACCP of aquatic products is characterized by comprising the following steps:
establishing an HACCP knowledge application model based on the HACCP schedule of the aquatic products, and analyzing the whole aquatic product business process and the standard structure of the HACCP system;
analyzing semantics among data by adopting a description logic language, and enhancing the understanding of a machine to the data to abstract the data into a knowledge structure;
scientifically representing, acquiring, organizing and storing knowledge in the HACCP schedule of the aquatic products; and
and describing business logic rules, and increasing the automatic reasoning capability of knowledge, so that all links of the HACCP of the aquatic products are effectively perfected and shared.
6. The aquatic product HACCP knowledge inference method according to claim 5, characterized by: the HACCP knowledge application model is extracted based on an HACCP schedule of uncooked oysters, discussion is carried out around three key control points of receiving live oysters, refrigerating by a dry method and storing oyster meat, and each key control point covers obvious hazards, key limit values, monitoring contents, deviation rectifying actions, verification and records to obtain related knowledge.
7. The aquatic product HACCP knowledge inference method according to claim 5, characterized by: the step of analyzing the semantics among the data by adopting the description logic language, strengthening the understanding of the machine to the data and abstracting the data into a knowledge structure specifically comprises the following steps: abstracting knowledge in the HACCP plan table of the aquatic product into a concept set, a relation set, a rule set and an entity set.
8. The aquatic product HACCP knowledge inference method according to claim 5, characterized by: the steps of scientifically representing, acquiring, organizing and storing the knowledge in the HACCP schedule of the aquatic products specifically comprise:
determining the domain and the range of the ontology;
enumerating important concepts, terms, etc. in the art;
defining a class;
defining attributes of the class;
defining the relationship among concepts in the field;
an instance is created.
9. The aquatic product HACCP knowledge inference method according to claim 5, characterized by: in the step of describing the business logic rules and increasing the automatic reasoning capability of knowledge to effectively perfect and share all links of the HACCP of the aquatic products, the semantic network rule language SWRL is used for describing the business logic rules and increasing the automatic reasoning capability of the knowledge.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800202.4A CN113487032A (en) | 2021-07-15 | 2021-07-15 | Aquatic product HACCP knowledge reasoning system and method |
| JP2021203447A JP2023013909A (en) | 2021-07-15 | 2021-12-15 | Deduction and application model for marine product cold chain haccp knowledge system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800202.4A CN113487032A (en) | 2021-07-15 | 2021-07-15 | Aquatic product HACCP knowledge reasoning system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113487032A true CN113487032A (en) | 2021-10-08 |
Family
ID=77938856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110800202.4A Pending CN113487032A (en) | 2021-07-15 | 2021-07-15 | Aquatic product HACCP knowledge reasoning system and method |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP2023013909A (en) |
| CN (1) | CN113487032A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196043A (en) * | 2023-11-07 | 2023-12-08 | 北京大数据先进技术研究院 | Ontology-based knowledge reasoning method and system and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570566A (en) * | 2016-10-28 | 2017-04-19 | 安徽农业大学 | Camellia sinensis insect pest knowledge expression and sharing method based on ontology |
| CN109597877A (en) * | 2018-11-08 | 2019-04-09 | 国家电网公司 | A kind of knowledge-based reasoning method and device |
| CN109685522A (en) * | 2018-11-15 | 2019-04-26 | 中国农业大学 | Food Cold Chain Quality Monitoring Control System and method |
| CN110781315A (en) * | 2019-10-16 | 2020-02-11 | 华中农业大学 | Food safety knowledge map and construction method of related intelligent question-answering system |
| CN112258082A (en) * | 2020-11-04 | 2021-01-22 | 成都市食品药品检验研究院 | Personalized risk prevention and control intelligent system for food production and operation enterprises |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4061607B2 (en) * | 1998-04-06 | 2008-03-19 | 株式会社前川製作所 | Sanitation and safety management method for fish |
| JP2001195478A (en) * | 2000-01-06 | 2001-07-19 | Toyo Eng Corp | Diagnosis check list and/or data generation management support system |
| JP2002063033A (en) * | 2000-08-21 | 2002-02-28 | Toko Seiki Co Ltd | Knowledge control system provided with ontology |
| JP2002191297A (en) * | 2000-12-27 | 2002-07-09 | Matsushita Environment Airconditioning Eng Co Ltd | Apparatus for supporting food sanitation supervision |
| CN201429862Y (en) * | 2009-06-29 | 2010-03-24 | 杭州汇农农业信息咨询服务有限公司 | Whole process traceable management system for quality safety of aquatic products |
-
2021
- 2021-07-15 CN CN202110800202.4A patent/CN113487032A/en active Pending
- 2021-12-15 JP JP2021203447A patent/JP2023013909A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570566A (en) * | 2016-10-28 | 2017-04-19 | 安徽农业大学 | Camellia sinensis insect pest knowledge expression and sharing method based on ontology |
| CN109597877A (en) * | 2018-11-08 | 2019-04-09 | 国家电网公司 | A kind of knowledge-based reasoning method and device |
| CN109685522A (en) * | 2018-11-15 | 2019-04-26 | 中国农业大学 | Food Cold Chain Quality Monitoring Control System and method |
| CN110781315A (en) * | 2019-10-16 | 2020-02-11 | 华中农业大学 | Food safety knowledge map and construction method of related intelligent question-answering system |
| CN112258082A (en) * | 2020-11-04 | 2021-01-22 | 成都市食品药品检验研究院 | Personalized risk prevention and control intelligent system for food production and operation enterprises |
Non-Patent Citations (3)
| Title |
|---|
| 朱麟;张友华;李绍稳;胡艺峰;刘金花;谢静;: "基于本体的HACCP体系知识获取与知识表示", 数字技术与应用, no. 09 * |
| 牟向伟、陈燕、曹妍: "农产品冷链HACCP管理体系知识建模与推理", 农业工程学报, vol. 32, no. 2, pages 308 - 316 * |
| 罗爱军;成黎;: "解读HACCP体系在我国食品行业的应用", 食品安全导刊, no. 09 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196043A (en) * | 2023-11-07 | 2023-12-08 | 北京大数据先进技术研究院 | Ontology-based knowledge reasoning method and system and electronic equipment |
| CN117196043B (en) * | 2023-11-07 | 2024-02-06 | 北京大数据先进技术研究院 | Ontology-based knowledge reasoning method and system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2023013909A (en) | 2023-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3126470A1 (en) | Systems and methods for organizing and finding data | |
| Shi‐Nash et al. | Data analytics and predictive analytics in the era of big data | |
| Xu et al. | Automated digital cause-and-effect diagrams to assist causal analysis in problem-solving: a data-driven approach | |
| Xie et al. | A systematic literature review for the recycling and reuse of wasted clothing | |
| Orriols-Puig et al. | Unsupervised KDD to creatively support managers' decision making with fuzzy association rules: A distribution channel application | |
| Zhang | [Retracted] Optimization of the Marketing Management System Based on Cloud Computing and Big Data | |
| Zou | Analysis of consumer online resale behavior measurement based on machine learning and BP neural network | |
| Vats et al. | Data lake: A plausible big data science for business intelligence | |
| Aristodemou et al. | A literature review on the state-of-the-art on intellectual property analytics | |
| CN113487032A (en) | Aquatic product HACCP knowledge reasoning system and method | |
| Agnihotri et al. | Social media analytics for business-to-business marketing | |
| Chen et al. | [Retracted] Improvement and Optimization of Feature Selection Algorithm in Swarm Intelligence Algorithm Based on Complexity | |
| Zhuang et al. | Sequential recommendation via cross-domain novelty seeking trait mining | |
| Binnewies et al. | OECEP: enriching complex event processing with domain knowledge from ontologies | |
| Duan et al. | Ultimate of Digital Economy: From Asymmetric Data Economy to Symmetric Knowledge and Wisdom Economy | |
| Pankratova et al. | Foresight process based on text analytics | |
| Miao et al. | Intelligent auxiliary operation and maintenance system of power communication network based on knowledge graph | |
| Zou et al. | A Sustainable Product Design Approach Based on Data Mining of Dynamic User Demands: A Case Study on HUAWEI Mate 40 Series | |
| KR20220108970A (en) | Method of risk analysis and technology transfer opportunity recommendation by technology-product-material based on machine learning or AI | |
| Wang | [Retracted] The Development Trend of China’s Agricultural Product Cold Chain Logistics from the Perspective of Big Data | |
| Feng et al. | Analysis of the characteristics and evolution of knowledge label networks in the Q&A community: taking the Zhihu platform as an example | |
| Primawati et al. | Business Intelligence and Analytics in Dairy Goat Livestock: Current and Future Challenge | |
| Cao et al. | A novel back propagation neural network optimized by rough set and particle swarm algorithm for remanufacturing service provider classification and selection | |
| Chen et al. | Research on service value chain model based on technology service platform | |
| Liao et al. | Applications of social network analysis in promoting circular economy: a literature review |
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 |