CN115112407A - Sample collection method for food detection - Google Patents
Sample collection method for food detection Download PDFInfo
- Publication number
- CN115112407A CN115112407A CN202211038486.9A CN202211038486A CN115112407A CN 115112407 A CN115112407 A CN 115112407A CN 202211038486 A CN202211038486 A CN 202211038486A CN 115112407 A CN115112407 A CN 115112407A
- Authority
- CN
- China
- Prior art keywords
- food
- data
- target
- evaluation
- information
- 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
- 235000013305 food Nutrition 0.000 title claims abstract description 292
- 238000001514 detection method Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 81
- 239000002994 raw material Substances 0.000 claims abstract description 79
- 238000009826 distribution Methods 0.000 claims abstract description 39
- 230000002159 abnormal effect Effects 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims description 49
- 238000005070 sampling Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 235000015219 food category Nutrition 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 235000019219 chocolate Nutrition 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000004615 ingredient Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Security & Cryptography (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Human Resources & Organizations (AREA)
- Immunology (AREA)
- Educational Administration (AREA)
- Biochemistry (AREA)
- Entrepreneurship & Innovation (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a sample collection method for food detection, relates to the technical field of food safety, and solves the technical problem that the food safety problem is incomplete in detection because the type of food to be detected cannot be determined by combining multiple data sources when food samples are collected in the prior art; according to the food detection method, whether the food information in the detection area is abnormal or not is determined through multi-source data, if the food information is abnormal, the target food in the detection area is determined, the collection weight is determined according to the circulation information, so that the collection of food samples is completed, the target food is determined from two dimensions of food raw materials and consumer evaluation, and the food detection can be guaranteed to meet the market demand; according to the food detection method, a food acquisition plan is established based on multi-source data, and the accuracy of food types in food detection can be guaranteed by combining with a conventional detection plan; meanwhile, the distribution ranges, even the collection number of each target address, are determined according to the collection weight, so that the typicality of the food sample can be realized.
Description
Technical Field
The invention belongs to the field of food safety, relates to a food sample collection technology, and particularly relates to a sample collection method for food detection.
Background
The purpose of food safety detection is to avoid the generation of toxic and harmful substances affecting human health during the processes of processing, storing, selling and the like of food, so that food samples need to be reasonably collected to ensure the food detection precision and efficiency.
The prior art (patent application publication No. CN 110196251A) discloses a sampling system and method for food detection, which obtains the type of food sample through image analysis, and manages the storage state of the food sample by combining with the corresponding storage time information; in the prior art, when food samples are collected, the types and the quantity of the food samples are collected according to a detection plan, and the types of the food to be detected cannot be determined by combining various data sources, so that the food safety problem is not detected comprehensively; therefore, a method for collecting samples for food detection is needed.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art; therefore, the invention provides a food detection sample collection method, which is used for solving the technical problem that in the prior art, when food samples are collected, the types and the quantity of the food samples are collected according to a detection plan, and the types of the food to be detected cannot be determined by combining multiple data sources, so that the food safety problem is not completely detected.
According to the invention, multi-source data and big data technologies are combined, the target food to be detected is extracted from the multi-source data, a sample collection rule is established according to the target food, the collection of food samples is realized by combining with the traditional detection planning, the collection range of the food samples is expanded, and a foundation is laid for improving the food safety.
In order to achieve the above object, a first aspect of the present invention provides a sample collection method for food detection, including:
analyzing food information based on multi-source data, and determining target food to be detected according to whether an analysis result is abnormal; the food information comprises food types, food batches and corresponding supply production places, and the multi-source data comprises raw material related data and evaluation related data;
determining the distribution range of the target food, determining an acquisition weight according to circulation information of the target food in each distribution range, and acquiring a food sample corresponding to the target food according to the acquisition weight; wherein the circulation information includes a circulation time and a circulation number.
Preferably, before analyzing the food information, a food database is established, including:
acquiring food transaction data; wherein the food transaction data includes supplier, demander and food information;
extracting the distribution address of the demand party in the food transaction data, and establishing the food database by combining a set detection area; wherein the food information is extracted from the established food database.
Preferably, analyzing the food information based on the multi-source data to obtain a raw material analysis tag includes:
extracting the raw material related data from the multi-source data; wherein the raw material association data refers to information related to food raw materials;
intelligently analyzing the raw material correlation data to determine whether the corresponding food raw materials are normal or not; when the food raw materials are abnormal, extracting the batches of the food corresponding to the food raw materials, and marking the batches as target batches;
performing one-way matching on the target batch and the food information, and setting the raw material analysis label corresponding to the food information as 1 when the target batch and the food information are successfully matched; otherwise, it is set to 0.
Preferably, after the raw material analysis tag is set, the food information is analyzed based on multi-source data to obtain an evaluation analysis tag, including:
after the raw material analysis label is set, extracting the evaluation associated data corresponding to the food information; wherein the evaluation-related data refers to evaluation data related to the food category;
intelligently extracting safety evaluation data in the evaluation associated data; wherein the safety evaluation data refers to the evaluation related to food safety;
when the safety evaluation data is not lower than a safety evaluation threshold value, setting the evaluation analysis tag corresponding to the food information to be 1; otherwise, set to 0; wherein the safety evaluation threshold is set according to actual experience.
Preferably, the determining the target food according to the raw material analysis tag and the evaluation analysis tag comprises:
labeling the raw material analysis tag and the evaluation analysis tag as YFB and PFB, respectively;
obtaining a food evaluation coefficient SPX by the formula SPX = α × YFB + β × PFB; wherein alpha and beta are characteristic weights determined according to historical detection data;
when the SPX is larger than or equal to the SPY, marking the corresponding food information as the target food; wherein SPY is a food evaluation threshold value, and the food evaluation threshold values corresponding to different food types are different.
Preferably, determining the feature weight according to the historical detection data includes:
acquiring the historical detection data;
extracting the data proportion of the food type abnormity detected due to the abnormity of the raw material related data in the historical detection data as the characteristic weight of the raw material analysis label;
and extracting the data proportion of the food type abnormity detected due to the abnormity of the evaluation related data in the historical detection data as the characteristic weight of the evaluation analysis label.
Preferably, determining the acquisition weight corresponding to each distribution range according to the circulation information includes:
determining a plurality of target addresses in the detection area according to the circulation information; wherein the target address refers to a storage address and a sale address of the target food;
defining a plurality of distribution ranges according to the distance between a plurality of target addresses;
and acquiring the proportion of the circulation quantity of the target food in the distribution range as the acquisition weight corresponding to the distribution range.
Preferably, sampling the target food according to the collection weight to obtain the food sample, including:
determining the corresponding collection quantity according to the collection weight;
and collecting the target food from a plurality of target addresses according to the collection quantity to serve as the food sample corresponding to the distribution range.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the food detection method, whether the food information in the detection area is abnormal or not is determined through multi-source data, if the food information is abnormal, the target food in the detection area is determined, the collection weight is determined according to the circulation information, the collection of food samples is further completed, the target food is determined from two dimensions of food raw materials and consumer evaluation, and the food detection can be guaranteed to meet market demands.
2. According to the food detection method, a food acquisition plan is established based on multi-source data, and the accuracy of food types in food detection can be guaranteed by combining with a conventional detection plan; meanwhile, the distribution ranges, even the collection number of each target address, are determined according to the collection weight, so that the typicality of the food sample can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram of the working steps of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In the traditional food safety detection, according to a detection plan which is made in advance, for example, sampling detection is carried out on a plurality of foods or a plurality of merchants, and workers randomly collect food samples from the corresponding merchants according to the detection plan; it can be known that, the detection plan as a product of the work task of the detection unit cannot predict the influence of the food raw material problem on the food safety, and cannot accurately know the evaluation of the consumer on various foods, so that the formulated detection plan cannot meet the market demand.
The method and the device can analyze and determine the target food by combining multi-source data, for example, the possibility of the abnormality of the corresponding food is predicted according to whether the food raw materials are normal or not and whether the food evaluation is normal or not, if the possibility of the abnormality is high, the food is determined as the target food, and then the target food is sampled, so that the comprehensiveness of the food detection can be ensured.
Referring to fig. 1, a first embodiment of the present invention provides a sample collection method for food detection, including:
analyzing food information based on multi-source data, and determining target food to be detected according to whether an analysis result is abnormal; determining the distribution range of the target food, determining the acquisition weight according to the circulation information of the target food in each distribution range, and acquiring the food sample corresponding to the target food according to the acquisition weight.
The food information in the invention comprises food types, food batches, ingredient tables and corresponding supply production places; the food type and the food batch can quickly determine the raw material related data and the evaluation related data which are related to the food type and the food batch so as to determine whether the corresponding food is abnormal or not; the multi-source data comprises raw material associated data and evaluation associated data; the raw material associated data is data associated with food raw materials and mainly data issued by raw material suppliers or authoritative detection organizations; the evaluation related data is the actual evaluation data of the consumers for the food, mainly comes from the consumers, but can be obtained from related data platforms, namely from an e-commerce platform, and can also be extracted from complaints of the consumers.
The circulation information in the invention comprises the flow time, the circulation quantity and the like, and the flow time and the circulation quantity of the target food in each distribution range can be determined according to the circulation information, so that the acquisition weight can be conveniently determined, and a data base is laid for the acquisition of food samples.
Before analyzing food information, the invention establishes a food database, which comprises the following steps:
acquiring food transaction data; and extracting the distribution address of the demand party in the food transaction data, and establishing a food database by combining the set detection area.
Food transaction data may be understood as a record of food transactions, such as a consumer purchasing 10 tons of pork from a supplier; therefore, the food transaction data comprises supplier information, demander information, food information and the like, and the food transaction data can be aggregated and screened from a plurality of platforms to obtain a complete food transaction record; the data of food transactions aggregated and obtained from a plurality of platforms can refer to a thesis "application of R language in commodity transaction data association rule mining" published by the Standyland science and technology (1 st 2017, page 100-102) "and a doctor's position thesis" research on business data analysis method based on empirical mode decomposition and dynamic data mining "of Liu Ting of the university of Hefei industry (11 th 2008).
The invention analyzes food information based on multi-source data to obtain a raw material analysis label, which comprises the following steps:
extracting raw material associated data from the multi-source data; intelligently analyzing the raw material correlation data to determine whether the corresponding food raw materials are normal or not; when the food raw materials are abnormal, extracting the batches of the food corresponding to the food raw materials, and marking the batches as target batches; performing one-way matching on the target batch and the food information, and setting a raw material analysis label corresponding to the food information as 1 when the target batch and the food information are successfully matched; otherwise, it is set to 0.
In the embodiment of the invention, the raw material association data refers to information related to food raw materials; acquiring raw material related data from a platform such as the Internet, analyzing whether the recorded food raw materials are normal or not based on the raw material related data, and if the food raw materials are abnormal, acquiring food related to the abnormal food raw materials, namely extracting food batches corresponding to the food raw materials; for example, the following steps are carried out:
suppose that a chocolate ingredient supplier has a problem publishing a batch of ingredients on its official platform;
and tracing the chocolate batch corresponding to the batch of raw materials, wherein the chocolate batch is the target batch.
It is worth noting that when the raw material associated data is obtained, the detection area does not need to be considered, namely, the raw material associated data is continuously aggregated, and after the detection area is determined, the raw material associated data can be directly extracted; of course, the detection area may be determined first, and raw material related data corresponding to the food in the detection area may be directly obtained by aggregation, which may cause a delay in the aggregation efficiency, but may result in a low data processing amount.
The detection area in the invention can be obtained through an administrative area, or can be obtained by manually defining the area, for example, a certain administrative area is used as the detection area (food safety inspection can be performed by referring to a food safety supervision unit), and after the detection area determines that which food batches in the detection area are abnormal through raw material related data, the raw material analysis label corresponding to the abnormal food batches is 1.
The embodiment of the invention performs one-way matching on the target batch and the food information, namely the target batch and the food batch in the food information in the detection area can be matched after the target batch is obtained, and if the matching is successful, the problem of the food type (possible) in the food information is shown; the food batches in the food information can also be matched with the target batches to determine the possibility of food safety.
The application scenario of single item matching is illustrated:
1. analyzing the aggregated raw material associated data, determining that part of the food raw materials are abnormal, and determining a target batch;
and matching the target batch with the food information in each detection area, wherein if the matching is successful, the food type corresponding to the food information is abnormal.
2. In order to ensure the significance of food safety detection, a certain food detection unit compares a food batch corresponding to food information in a detection area with a target batch, and when the food batch and the target batch are successfully matched, the raw material analysis label corresponding to the food of the food batch is 1.
After the raw material analysis label is set, food information is analyzed based on multi-source data to obtain an evaluation analysis label, and the method comprises the following steps:
after the raw material analysis label is set, extracting evaluation associated data corresponding to the food information; intelligently extracting safety evaluation data in the evaluation associated data; when the safety evaluation data is not lower than the safety evaluation threshold value, setting an evaluation analysis label corresponding to the food information as 1; otherwise, it is set to 0.
The evaluation-related data in the embodiment of the present invention refers to evaluation data related to the type of food; the safety evaluation data refers to the evaluation related to food safety, for example, the evaluation related to food expiration, food deterioration and the like in a plurality of evaluation data in a certain e-commerce platform is safety evaluation data, and can also be food safety complaints on a certain complaint website.
In the embodiment of the invention, when the safety evaluation data is not lower than the safety evaluation threshold, the corresponding food (possibly) has problems, and the corresponding evaluation analysis tag is 1; in other preferred embodiments, the evaluation analysis tag may also be set according to the proportion of the security evaluation data in the evaluation related data.
The invention determines target food according to a raw material analysis label and an evaluation analysis label, and comprises the following steps:
respectively marking a raw material analysis label and an evaluation analysis label as YFB and PFB; obtaining a food evaluation coefficient SPX by the formula SPX = α × YFB + β × PFB; and when the SPX is more than or equal to the SPY, marking the corresponding food information as the target food.
According to the embodiment of the invention, the raw material analysis label and the evaluation analysis label are unified to judge whether the food needs to be detected or not, namely, the target food is obtained; when the food evaluation coefficient is not lower than the food evaluation threshold value, the food needs to be detected; it can be understood that the food evaluation coefficient is not lower than the food evaluation threshold, which indicates that both food raw material and evaluation are abnormal, or food raw material is abnormal, or evaluation is abnormal, and food needs to be detected; it will be appreciated that the food safety issues associated with assessing anomalies are primarily focused on the food production and shipping and storage processes.
In the embodiment of the invention, the characteristic weight mainly represents the relation between the corresponding analysis tag and food safety, if food raw materials have problems, the probability of safety problems of the corresponding batches of food is 0.6, and the characteristic weight corresponding to the raw material analysis tag is 0.6; determining the characteristic weight according to the historical detection data, for example, extracting the data proportion of the food type abnormity detected due to the abnormity of the raw material related data in the historical detection data, and using the data proportion as the characteristic weight of the raw material analysis label; extracting the data proportion of the food type abnormity detected due to the abnormity of the evaluation related data in the historical detection data as the characteristic weight of the evaluation analysis label; reasonable feature weights may of course be obtained in other ways.
The invention determines the acquisition weight corresponding to each distribution range according to the circulation information, which comprises the following steps:
determining a plurality of target addresses in the detection area according to the circulation information; defining a plurality of distribution ranges according to the distances among a plurality of target addresses; and acquiring the proportion of the circulation quantity of the corresponding target food in the distribution range as the acquisition weight corresponding to the distribution range.
The target address in the embodiment of the invention refers to a storage address and a sale address of target food, the storage address mainly corresponds to a food warehouse, and the sale address mainly corresponds to a sale unit of the food; and dividing a distribution range according to the target address, and determining how many food samples should be collected in each distribution range according to the circulation information.
Illustrating how the distribution range is determined based on the target address, and how the food sample is collected:
selecting a target address A optionally, and acquiring a target address B adjacent to the target address A;
when the distance between A and B is less than 1km, the target address B meets the requirement, and a target address C adjacent to B is obtained;
when the distance between B and C is less than 1km, the target address C is satisfied, … …
Defining a distribution range, the distribution range including target address A, B, C …;
and acquiring the ratio of the target address A, B, C … in the distribution range to the target food circulation in the circulation total amount as the acquisition weight of the distribution range, and acquiring the food sample by acquiring the total amount and the acquisition weight.
The invention samples target food according to the collection weight to obtain food samples, which comprises the following steps:
determining the corresponding collection quantity according to the collection weight; and collecting target food from a plurality of target addresses according to the collection quantity to serve as food samples corresponding to the distribution range.
It can be understood that after the collection quantity is determined by combining the total collection quantity, the corresponding quantity of target food is collected from the distribution range according to the food sampling principle; the food sampling principle can refer to a blog (https:// www.antpedia.com/news/59/n-2318159.html), which discloses the sampling rule and the sampling quantity of samples during detection, and can ensure the typicality of food samples.
Part of data in the formula is obtained by removing dimension and taking the value to calculate, and the formula is obtained by simulating a large amount of collected data through software and is closest to a real situation; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or obtained through simulation of a large amount of data.
The working principle of the invention is as follows:
and establishing a food database corresponding to the detection area according to the food transaction data, extracting food information from the food database, analyzing the food information by combining multi-source data, and determining the target food according to whether the analysis result is abnormal.
Determining the distribution range of the target food, determining the collection weight according to the circulation information of the target food in the distribution range, and collecting the food sample from the distribution range according to the collection weight.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (6)
1. A sample collection method for food detection is characterized by comprising the following steps:
analyzing food information based on multi-source data, and determining target food to be detected according to whether an analysis result is abnormal; the food information comprises food types, food batches and corresponding supply production places, the multi-source data comprises raw material associated data and evaluation associated data, and the evaluation associated data is from consumers;
determining the distribution range of the target food, determining an acquisition weight according to circulation information of the target food in each distribution range, and acquiring a food sample corresponding to the target food according to the acquisition weight; wherein the circulation information includes a circulation time and a circulation number; wherein the distribution range is determined based on the distance between the target addresses in the circulation information;
analyzing the raw material associated data to obtain a raw material analysis label, after the raw material analysis label is set, analyzing the food information based on multi-source data to obtain an evaluation analysis label, comprising:
after the raw material analysis label is set, extracting the evaluation associated data corresponding to the food information; wherein the evaluation-related data refers to evaluation data related to the food category;
intelligently extracting safety evaluation data in the evaluation associated data; wherein the safety evaluation data refers to the evaluation related to food safety;
when the safety evaluation data is not lower than a safety evaluation threshold value, setting the evaluation analysis tag corresponding to the food information to be 1; otherwise, set to 0; wherein the safety evaluation threshold is set according to actual experience;
determining the target food product from the raw material analysis tag and the evaluation analysis tag, comprising:
labeling the raw material analysis tag and the evaluation analysis tag as YFB and PFB, respectively;
obtaining a food evaluation coefficient SPX by the formula SPX = α × YFB + β × PFB; wherein alpha and beta are characteristic weights determined according to historical detection data;
when the SPX is larger than or equal to the SPY, marking the corresponding food information as the target food; wherein SPY is a food evaluation threshold value, and the food evaluation threshold values corresponding to different food types are different.
2. The method as claimed in claim 1, wherein before analyzing the food information, a food database is established, comprising:
acquiring food transaction data; wherein the food transaction data includes supplier, demander and food information;
extracting the distribution address of the demand party in the food transaction data, and establishing the food database by combining a set detection area; wherein the food information is extracted from the established food database.
3. The method for collecting samples for food detection according to claim 1, wherein analyzing the food information based on the multi-source data to obtain a raw material analysis tag comprises:
extracting the raw material related data from the multi-source data; wherein the raw material association data refers to information related to food raw materials;
intelligently analyzing the raw material correlation data to determine whether the corresponding food raw materials are normal or not; when the food raw materials are abnormal, extracting the batches of the food corresponding to the food raw materials, and marking the batches as target batches;
performing one-way matching on the target batch and the food information, and setting the raw material analysis label corresponding to the food information as 1 when the target batch and the food information are successfully matched; otherwise, it is set to 0.
4. The method as claimed in claim 1, wherein determining the feature weight according to the historical detection data comprises:
acquiring the historical detection data;
extracting the data proportion of the food type abnormity detected due to the abnormity of the raw material related data in the historical detection data as the characteristic weight of the raw material analysis label;
and extracting the data proportion of the food type abnormity detected due to the abnormity of the evaluation related data in the historical detection data as the characteristic weight of the evaluation analysis label.
5. The method according to claim 1 or 4, wherein determining the collection weight corresponding to each distribution range according to the circulation information includes:
determining a plurality of target addresses in the detection area according to the circulation information; wherein the target address refers to a storage address and a sale address of the target food;
defining a plurality of distribution ranges according to the distance between a plurality of target addresses;
and acquiring the proportion of the circulation quantity of the target food in the distribution range as the acquisition weight corresponding to the distribution range.
6. The method for collecting the sample for food detection according to claim 5, wherein sampling the target food according to the collection weight to obtain the food sample comprises:
determining the corresponding collection quantity according to the collection weight;
and collecting the target food from a plurality of target addresses according to the collection quantity to serve as the food sample corresponding to the distribution range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211038486.9A CN115112407A (en) | 2022-08-29 | 2022-08-29 | Sample collection method for food detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211038486.9A CN115112407A (en) | 2022-08-29 | 2022-08-29 | Sample collection method for food detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115112407A true CN115112407A (en) | 2022-09-27 |
Family
ID=83335360
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211038486.9A Pending CN115112407A (en) | 2022-08-29 | 2022-08-29 | Sample collection method for food detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115112407A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115329905A (en) * | 2022-10-13 | 2022-11-11 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
CN115406706A (en) * | 2022-11-03 | 2022-11-29 | 君华高科集团有限公司 | Full-automatic food material sampling robot based on image recognition |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679779A (en) * | 2017-11-21 | 2018-02-09 | 深圳市检验检疫科学研究院 | A kind of imported food sampling safe evaluation method |
CN108960637A (en) * | 2018-07-08 | 2018-12-07 | 华中农业大学 | A kind of food safety risk online evaluation and control method |
CN110196251A (en) * | 2019-06-13 | 2019-09-03 | 六盘水市食品药品检验检测所 | A kind of sampling system and method for food inspection |
CN110276390A (en) * | 2019-06-14 | 2019-09-24 | 六盘水市食品药品检验检测所 | A kind of third party's food inspection synthesis of mechanism information processing system and method |
CN110969400A (en) * | 2018-09-28 | 2020-04-07 | 北京国双科技有限公司 | Supply chain upstream and downstream data association method and device |
CN112257995A (en) * | 2020-10-09 | 2021-01-22 | 贵州省产品质量检验检测院 | Internet-based product quality risk monitoring sampling method and system |
CN112381364A (en) * | 2020-10-30 | 2021-02-19 | 浪潮云信息技术股份公司 | Comprehensive evaluation method for food quality spot check |
JP2021135869A (en) * | 2020-02-28 | 2021-09-13 | 高砂香料工業株式会社 | Food product/beverage selection behavior prediction method by function evaluation and personality data, and food product/beverage |
CN113887978A (en) * | 2021-10-13 | 2022-01-04 | 北京工商大学 | Food risk comprehensive evaluation method based on improved matter element extension model |
CN114862421A (en) * | 2022-05-25 | 2022-08-05 | 仲检(宁夏)技术服务有限公司 | Food sampling method |
-
2022
- 2022-08-29 CN CN202211038486.9A patent/CN115112407A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107679779A (en) * | 2017-11-21 | 2018-02-09 | 深圳市检验检疫科学研究院 | A kind of imported food sampling safe evaluation method |
CN108960637A (en) * | 2018-07-08 | 2018-12-07 | 华中农业大学 | A kind of food safety risk online evaluation and control method |
CN110969400A (en) * | 2018-09-28 | 2020-04-07 | 北京国双科技有限公司 | Supply chain upstream and downstream data association method and device |
CN110196251A (en) * | 2019-06-13 | 2019-09-03 | 六盘水市食品药品检验检测所 | A kind of sampling system and method for food inspection |
CN110276390A (en) * | 2019-06-14 | 2019-09-24 | 六盘水市食品药品检验检测所 | A kind of third party's food inspection synthesis of mechanism information processing system and method |
JP2021135869A (en) * | 2020-02-28 | 2021-09-13 | 高砂香料工業株式会社 | Food product/beverage selection behavior prediction method by function evaluation and personality data, and food product/beverage |
CN112257995A (en) * | 2020-10-09 | 2021-01-22 | 贵州省产品质量检验检测院 | Internet-based product quality risk monitoring sampling method and system |
CN112381364A (en) * | 2020-10-30 | 2021-02-19 | 浪潮云信息技术股份公司 | Comprehensive evaluation method for food quality spot check |
CN113887978A (en) * | 2021-10-13 | 2022-01-04 | 北京工商大学 | Food risk comprehensive evaluation method based on improved matter element extension model |
CN114862421A (en) * | 2022-05-25 | 2022-08-05 | 仲检(宁夏)技术服务有限公司 | Food sampling method |
Non-Patent Citations (2)
Title |
---|
李冉: ""基于多源数据综合分析的食品安全风险预警"", 《工程科技Ⅰ辑》 * |
李太平: "基于分类抽样原理的我国食品安全状况定量评价研究", 《农业经济问题》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115329905A (en) * | 2022-10-13 | 2022-11-11 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
CN115329905B (en) * | 2022-10-13 | 2022-12-09 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
CN115406706A (en) * | 2022-11-03 | 2022-11-29 | 君华高科集团有限公司 | Full-automatic food material sampling robot based on image recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115112407A (en) | Sample collection method for food detection | |
Li et al. | A MIDAS modelling framework for Chinese inflation index forecast incorporating Google search data | |
CN114066242A (en) | Enterprise risk early warning method and device | |
CN107993143A (en) | A kind of Credit Risk Assessment method and system | |
CN102789618B (en) | Generate the monitoring system and method for brisk market index | |
Hryhoruk et al. | Model for assessment of the financial security level of the enterprise based on the desirability scale | |
CN106384256A (en) | Power supplying service satisfaction dynamic testing system based on index system dynamic change | |
CN116596305A (en) | Risk grading method for food safety management | |
Djekic et al. | Quality costs in a fruit processing company: a case study of a Serbian company | |
CN113919865A (en) | Network retail amount statistical method | |
CN113283768A (en) | Food detection item extraction method, device, equipment and storage medium | |
CN116611796A (en) | Exception detection method and device for store transaction data | |
WO2019112064A1 (en) | Brand value calculation device | |
CN114282951B (en) | Network retail prediction method, device and medium | |
CN114398562B (en) | Shop data management method, device, equipment and storage medium | |
Domashova et al. | Application of machine learning methods for risk analysis of unfavorable outcome of government procurement procedure in building and grounds maintenance domain | |
KR101960863B1 (en) | System of valuation of technology | |
CN112734211B (en) | Coal consistency evaluation method, device, equipment and readable storage medium | |
Deodhar | Motivation for and cost of HACCP in Indian food processing industry | |
CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
KR20170034527A (en) | How to analyze price information of competitors using web logs | |
Rosiawan et al. | Activity-based management as economic effect measurement for implementing ISO 9001: 2015 clause | |
JP4413056B2 (en) | Evaluation method and system for evaluation | |
CN111160834A (en) | Inventory prediction method based on daily order and inventory | |
Subhan et al. | THE INFLUENCE OF ECONOMIC FACTORS ON THE STOCK PRICE OF KIMIA FARMA COMPANIES ON THE INDONESIAN STOCK EXCHANGE |
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 |