CN116596300A - Intelligent supervision method, system, equipment and medium for food production enterprises - Google Patents
Intelligent supervision method, system, equipment and medium for food production enterprises Download PDFInfo
- Publication number
- CN116596300A CN116596300A CN202310445565.XA CN202310445565A CN116596300A CN 116596300 A CN116596300 A CN 116596300A CN 202310445565 A CN202310445565 A CN 202310445565A CN 116596300 A CN116596300 A CN 116596300A
- Authority
- CN
- China
- Prior art keywords
- food production
- food
- time period
- risk
- enterprise
- 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 342
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 title claims description 296
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 47
- 239000010813 municipal solid waste Substances 0.000 claims description 35
- 238000012544 monitoring process Methods 0.000 claims description 29
- 230000005611 electricity Effects 0.000 claims description 28
- 238000007689 inspection Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 22
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000002699 waste material Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 239000002778 food additive Substances 0.000 description 1
- 235000013373 food additive Nutrition 0.000 description 1
- 235000012055 fruits and vegetables Nutrition 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 235000013402 health food Nutrition 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent supervision method, system, equipment and medium for food manufacturers, which relate to the field of enterprise supervision.
Description
Technical Field
The invention relates to the technical field of enterprise supervision, in particular to an intelligent supervision method, system, equipment and medium for a food production enterprise.
Background
Along with the continuous development of technology, intellectualization, digitization and networking have become the trend of modern industry development, and food production is no exception. The food is an indispensable part of daily life of people, and brings delicacies and nutrition to people. However, food safety issues for food manufacturers are also often of concern. Aiming at the supervision work of food production enterprises, the traditional supervision method is mainly to conduct spot check on a plurality of food production enterprises at random, and the high-risk food production enterprises can not be inspected at times due to the fact that the food production enterprises are numerous, so that supervision omission is caused. The supervision method is time-consuming and labor-consuming, cannot accurately discover high-risk food production enterprises, and can effectively supervise the high-risk food production enterprises.
Therefore, how to accurately monitor food production enterprises is a current urgent problem to be solved.
Disclosure of Invention
The invention mainly solves the technical problem of accurately supervising food production enterprises.
According to a first aspect, the present invention provides a method for intelligent supervision of a food production enterprise, comprising: acquiring basic information of a food producer, a camera monitoring video in a first time period of a gate of the food producer, power utilization time sequence data in the first time period of the food producer and water utilization time sequence data in the first time period of the food producer; determining a first risk degree of the food production enterprise by using a first risk degree model based on the basic information of the food production enterprise, the camera monitoring video in the first time period of the gate of the food production enterprise, the power utilization time series data in the first time period of the food production enterprise and the water utilization time series data in the first time period of the food production enterprise; the method comprises the steps of obtaining garbage cleaning and conveying capacity in a first time period of a food production enterprise and food production capacity in the first time period of the food production enterprise; determining a second risk level of the food production facility using a second risk level model based on the volume of trash clear during the first time period of the food production facility and the volume of food production during the first time period of the food production facility; determining a risk level of the food production enterprise based on the first risk level and the second risk level; and determining the inspection frequency of the food production enterprises based on the risk degree of the food production enterprises.
Further, the input of the first risk degree model comprises basic information of the food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time series data in the first time period of the food production enterprise and water utilization time series data in the first time period of the food production enterprise, and the output of the first risk degree model is a first risk degree of the food production enterprise; the input of the second risk degree model comprises garbage collection amount in the first time period of the food producer and food production amount in the first time period of the food producer, and the output of the second risk degree model is the second risk degree of the food producer.
Still further, the determining the risk level of the food production enterprise based on the first risk level and the second risk level includes: and obtaining the risk degree of the food production enterprise by weighting and summing the first risk degree and the second risk degree according to a preset weight coefficient.
Still further, the inspection frequency includes one-month inspection, one-quarter inspection, one-half-year inspection, and one-year inspection.
Still further, the second risk model is obtained through a training process comprising: acquiring a plurality of training samples, wherein the training samples comprise sample input data and labels corresponding to the sample input data, the sample input data is garbage collection and transportation amount in a first time period of a sample food producer and food production amount in the first time period of the sample food producer, and the labels are second risk degrees of the sample food producer; and training an initial second risk degree model based on the plurality of training samples to obtain the second risk degree model.
According to a second aspect, the present invention provides an intelligent supervision system for a food production enterprise, comprising: the first acquisition module is used for acquiring basic information of a food producer, a camera monitoring video in a first time period of a gate of the food producer, power utilization time series data in the first time period of the food producer and water utilization time series data in the first time period of the food producer; the first risk degree determining module is used for determining a first risk degree of the food production enterprise by using a first risk degree model based on basic information of the food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time series data in the first time period of the food production enterprise and water utilization time series data in the first time period of the food production enterprise; the second acquisition module is used for acquiring the garbage cleaning and transporting amount in the first time period of the food production enterprises and the food production amount in the first time period of the food production enterprises; a second risk degree determination module for determining a second risk degree of the food production enterprise using a second risk degree model based on the garbage collection amount in the first time period of the food production enterprise and the food production amount in the first time period of the food production enterprise; the risk degree determining module is used for determining the risk degree of the food production enterprise based on the first risk degree and the second risk degree; and the checking frequency determining module is used for determining the checking frequency of the food production enterprises based on the risk degree of the food production enterprises.
According to a third aspect, the present invention provides an electronic device comprising: a memory; a processor; a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method described above.
According to a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a program executable by a processor to implement a method as in any of the above aspects.
According to the intelligent supervision method, system, equipment and medium for the food production enterprises, provided by the invention, the first risk degree of the food production enterprises is determined through the basic information, the electricity time sequence data and the water time sequence data of the food production enterprises, the second risk degree of the food production enterprises is determined through the garbage disposal amount and the food production amount, the risk degree of the food production enterprises is determined based on the first risk degree and the second risk degree, and finally the inspection frequency of the food production enterprises is determined based on the risk degree of the food production enterprises, so that the food production enterprises with high risk can be accurately found, and the food production enterprises are accurately supervised.
Drawings
Fig. 1 is a schematic flow chart of an intelligent supervision method for a food production enterprise according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of power consumption time series data according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of water consumption time series data according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an intelligent supervision system of a food production enterprise according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The invention will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present invention.
In the embodiment of the invention, an intelligent supervision method of a food production enterprise is provided, as shown in fig. 1, comprising the following steps of S1 to S6:
step S1, basic information of a food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time series data in the first time period of the food production enterprise and water utilization time series data in the first time period of the food production enterprise are obtained.
The basic information of the food production enterprises comprises information such as operation category, business license, production license, organization code card, legal representative identity card scanning piece, enterprise laboratory technician certificate, key post personnel certificate, practitioner health card, quality management responsible person certificate, quality safety office member, production operation scale, food enterprise quality safety commitment book, relevant qualification and the like.
The food manufacturing enterprise may include livestock manufacturing enterprise, aquatic product manufacturing enterprise, fermentation product manufacturing enterprise, grain and oil product manufacturing enterprise, fruit and vegetable manufacturing enterprise, beverage manufacturing enterprise, food additive manufacturing enterprise, candy manufacturing enterprise, health food manufacturing enterprise, other food manufacturing enterprise, etc.
The first period of time may be one day, one week or one month. In some embodiments, the first time period may be the first few hours, e.g., the first 12 hours, after the business is started. In some embodiments, the first time period may also be 8 points to 12 points in the day or 14 points to 18 points in the day.
The camera surveillance video within a first time period of the food production enterprise doorway represents the surveillance video captured by the camera at the first time period of the food production enterprise personnel entering and exiting the doorway. The camera monitoring video of the first time period comprises the entering and exiting situations of personnel at the gate of the food production enterprise in the first time period, and the situations of the number of personnel, the time of working and discharging the personnel, the proportion of the personnel, whether the personnel is late to early retreating or not and the like of the food production enterprise can be approximately judged based on the camera monitoring video of the first time period. The camera monitoring video in the first time period can be used for judging whether staff of the food production enterprises work normally or not, so that whether the food production enterprises work normally or not is judged. For example, the camera monitoring video shows that no personnel enter or exit from a door of a food production enterprise in the time period of going up and down, so that the food production enterprise may have abnormal operation, for example, the camera monitoring video shows that the number of people going up and down on each day of the week has great difference, so that a large number of staff work situation is indicated, and so that the food production enterprise may have abnormal operation. As another example, a camera monitoring video shows that there is abnormal congestion of a large number of unlicensed transport vehicles at the gate of an enterprise, which indicates that there may be abnormal operations of a food production enterprise.
The camera monitoring video in the first time period refers to a dynamic image recorded in an electric signal mode and consists of a plurality of continuous static images in time. Wherein each image is a frame of video data.
In some embodiments, the format of the video data may include, but is not limited to: high density digital Video disc (Digital Video Disc, DVD), streaming media format (Flash Video, FLV), moving picture experts group (MPEG, motion Picture Experts Group), audio Video interleave (Audio Video Interleaved, AVI), home Video recording system (Video Home System, VHS), and Video container file format (Real Media file format, RM), etc.
The electricity consumption time series data in the first time period of the food production enterprise represents time series data of the change of the electricity consumption of the food production enterprise along with the change of the time period in the first time period. The electricity consumption of food production enterprises comprises factory building electricity consumption, office electricity consumption, illumination electricity consumption and the like. The power consumption time series data of the food production enterprises can reflect the production condition of the food production enterprises, for example, the food production enterprises use large electric quantity in a certain time period, and the large electric quantity of equipment, manpower, illumination and the like is indicated, so that the production capacity of the food production enterprises is indicated to be large, and the enterprise operation is normal. For example, the food production enterprises use very little electricity in a certain time period, and the electricity consumption of equipment, manpower, illumination and the like is very little, so that the production capacity of the food production enterprises is very little, and the operation of the enterprises is abnormal. For another example, if the enterprise has abnormal electricity consumption in the first period, for example, the electricity consumption is too high, the electricity consumption is too low or the electricity consumption is suddenly high or suddenly low, it is indicated that the enterprise is running abnormally. Fig. 2 is a schematic diagram of electricity consumption time series data according to an embodiment of the present invention, where an abscissa of the electricity consumption time series data indicates a number of hours, and an ordinate of the electricity consumption time series data indicates a corresponding amount of electricity consumption of the number of hours, for example, 40000 kwh is the corresponding amount of electricity consumption of the 2 nd hour. In some embodiments, processing may be performed based on the electricity time series data of the food manufacturing enterprise to determine whether the enterprise is operating properly. In some embodiments, the time series data of electricity usage during the first time period of the food manufacturing company may be obtained through a company electricity meter record.
The water consumption time series data in the first time period of the food production company represents time series data in which the water consumption of the food production company changes with the change of the time period in the first time period. The water consumption of the food production enterprises comprises domestic water for staff, factory building water, canteen water and the like. The water consumption time series data of the food producer can also reflect the production condition of the food producer, for example, the food producer uses large water consumption in a certain time period, and the large water consumption of equipment, staff and the like is indicated, so that the production activity of the food producer is more vigorous at the moment, and vice versa. For another example, an enterprise having abnormal water usage consumption in a first period of time, such as too high, too low, or sudden low water usage, indicates that the enterprise is operating more abnormally. Fig. 3 is a schematic diagram of water time series data according to an embodiment of the present invention. As shown in fig. 3, the abscissa of the water use time series data indicates the number of hours, and the ordinate indicates the amount of water used at the number of hours, for example, at the 4 th hour, the amount of water used is 10 tons. In some embodiments, the water usage time series data for the first time period of the food manufacturing facility may be obtained from a water meter record of the facility.
In some embodiments, there is a positive correlation between the time series data of electricity consumption in the first time period of the food manufacturing company and the time series data of water consumption in the first time period of the food manufacturing company, that is, the water consumption is high when the electricity consumption is high.
And S2, determining a first risk degree of the food production enterprise by using a first risk degree model based on the basic information of the food production enterprise, the camera monitoring video in the first time period of the gate of the food production enterprise, the power utilization time series data in the first time period of the food production enterprise and the water utilization time series data in the first time period of the food production enterprise.
The first risk level may represent a risk level of whether a food production enterprise production operation is at risk. The first risk degree is a numerical value between 0 and 1, and the larger the numerical value is, the higher the risk degree of production and management of the food production enterprises is. For example, when the first risk degree is 0.2, the risk degree of production and management of the food production enterprises is lower, and for example, when the first risk degree is 0.8, the risk degree of production and management of the food production enterprises is higher, and enterprise management may have problems.
The first risk degree model is a long-term and short-term neural network model. The Long and Short Term neural network model includes a Long and Short Term neural network (LSTM), which is one of RNNs (Recurrent Neural Network, recurrent neural networks). The long-term and short-term neural network model can process sequence data with any length, capture sequence information and output results based on the association relationship of front data and rear data in the sequence. The camera monitoring video, the electricity consumption time series data and the water consumption time series data in the continuous time period are processed through the long-short-term neural network model, so that the characteristics of the incidence relation among the camera monitoring video, the electricity consumption time series data and the water consumption time series data, which comprehensively consider all time points, can be output, and the output characteristics are more accurate and comprehensive.
The input of the first risk degree model comprises basic information of the food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time series data in the first time period of the food production enterprise and water utilization time series data in the first time period of the food production enterprise, and the output of the first risk degree model is the first risk degree of the food production enterprise.
The first risk model may be trained by training samples. The training sample comprises sample input data and a label corresponding to the sample input data, wherein the sample input data is basic information of a sample food production enterprise, a camera monitoring video in a first time period of a gate of the sample food production enterprise, power utilization time sequence data in the first time period of the sample food production enterprise and water utilization time sequence data in the first time period of the sample food production enterprise, and the label is a first risk degree of the sample food production enterprise. The output label of the training sample can be obtained through artificial labeling. For example, basic information of a sample food manufacturing enterprise, a camera monitoring video in a first time period of a doorway of the sample food manufacturing enterprise, power consumption time series data in the first time period of the sample food manufacturing enterprise, and water consumption time series data in the first time period of the sample food manufacturing enterprise can be manually marked, and a corresponding first risk degree is determined. In some embodiments, the initial first risk model may be trained by a gradient descent method to obtain a trained first risk model. Specifically, according to the training sample, constructing a loss function of the first risk degree model, and adjusting parameters of the first risk degree model through the loss function of the first risk degree model until the loss function value is converged or smaller than a preset threshold value, so that training is completed. The loss function may include, but is not limited to, a log (log) loss function, a square loss function, an exponential loss function, a range loss function, an absolute value loss function, and the like.
After training is completed, basic information of the food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time sequence data in the first time period of the food production enterprise and water utilization time sequence data in the first time period of the food production enterprise are input into a first risk degree model after training is completed, and a first risk degree of the food production enterprise is output and obtained. For example, the input of the long-short-term neural network model is basic information of a food production enterprise, a camera monitoring video of a gate of the food production enterprise for 12 hours, power consumption time series data of the food production enterprise for 12 hours and water consumption time series data of the food production enterprise for 12 hours, and then the output first risk degree is 0.23.
And step S3, obtaining garbage cleaning and transporting amount in the first time period of the food production enterprises and food production amount in the first time period of the food production enterprises.
The garbage disposal amount means a garbage yield generated in a food production process by a food production enterprise and transferred to a garbage disposal site or a transfer site. As an example, the daily trash can be 1 ton for a food manufacturing company. In some embodiments, the trash clearance may be calculated from trash clearance records of the food manufacturing facility.
Food throughput refers to the food throughput of a food producer during the production process. As an example, the food production business may have a food throughput of 5 tons per day. In some embodiments, the food throughput may be calculated from food production records of a food manufacturing company.
Under normal operation conditions, the garbage cleaning and transporting amount and the food production amount in a period of time of a food production enterprise have normal corresponding relations. As an example, under normal operating conditions, a food production facility has a 1-day food throughput of 1 ton, which corresponds to a 1-day garbage collection of 0.1 ton to 0.3 ton. If the 1-day food throughput is 1 ton and the corresponding 1-day garbage collection amount is 0.6 ton, it is indicated that other operations may exist in the food producer, such as processing unlicensed food, processing food using privately imported raw materials, and the like, resulting in increased garbage collection amount. As another example, if the 1 day food throughput is 1 ton, and its corresponding 1 day waste purge is 0.01 ton, it is indicated that the food producer may have other waste disposal channels, such as in situ incineration of waste, landfill of waste, dumping of waste into rivers, etc. non-compliance activities.
S4, determining a second risk degree of the food production enterprise by using a second risk degree model based on the garbage collection amount in the first time period of the food production enterprise and the food production amount in the first time period of the food production enterprise.
The second risk level may also represent a risk level of whether or not there is a risk in the production operations of the food production enterprises. For example, the second risk degree is also a value between 0 and 1, and the greater the value, the higher the risk degree of production and management of the food production enterprises is, and the second risk degree is similar to the first risk degree and is not described herein.
The second risk degree model can judge whether the garbage collection and transportation amount in the first time period of the food production enterprises and the food production amount in the first time period of the food production enterprises are in a normal corresponding relation or not, and output the second risk degree based on a judging result.
The second risk degree model is a deep neural network model, the deep neural network model comprises a deep neural network, the deep neural network model comprises a plurality of processing layers, each processing layer comprises a plurality of neurons, and each neuron performs matrix transformation on data. The parameters used by the matrix may be obtained by training. The deep neural network model may also be any existing neural network model that enables processing of multiple features, such as RNN (recurrent neural network), CNN (convolutional neural network), DNN (deep neural network), and so on. The input of the second risk degree model comprises garbage collection amount in the first time period of the food producer and food production amount in the first time period of the food producer, and the output of the second risk degree model is the second risk degree of the food producer.
The second risk model may be trained by a plurality of training samples. The training samples comprise sample input data and labels corresponding to the sample input data, the sample input data is garbage collection and transportation amount in a first time period of a sample food production enterprise and food production amount in the first time period of the sample food production enterprise, and the labels are second risk degrees of the sample food production enterprise. The sample output label of the training sample can be obtained through manual labeling by a worker. In some embodiments, an initial second risk degree model is trained based on a plurality of training samples, resulting in the second risk degree model.
And step S5, determining the risk degree of the food production enterprise based on the first risk degree and the second risk degree.
The risk level of the food production enterprise represents a risk level of the food production enterprise that is ultimately determined based on the first risk level and the second risk level. The higher the risk level of the food production enterprise, the higher the risk level of the offensiveness.
In some embodiments, the risk degree of the food production enterprise may be obtained by weighted summation of the first risk degree and the second risk degree according to a preset weight coefficient. For example, the first risk degree is 0.4, the second risk degree is 0.2, the preset weight coefficient is that the coefficient of the first risk degree is 0.6, and the coefficient of the second risk degree is 0.4, and the risk degree of the food production enterprises obtained by weighting and summing is 0.32.
And step S6, determining the inspection frequency of the food production enterprises based on the risk degree of the food production enterprises.
The risk level of the food production enterprise may correspond to A, B, C, D four grades, for example, risk level 0-0.25 corresponds to grade a, risk level 0.25-0.5 corresponds to grade B, risk level 0.5-0.75 corresponds to grade C, and risk level 0.75-1 corresponds to grade D. A. B, C, D the risk levels rise sequentially, the A-level risk level is lowest, and the D-level risk level is highest.
In some embodiments, the supervisory authorities may conduct hierarchical management based on the risk level of the food manufacturing company, such as determining different inspection frequencies for different levels of food manufacturing company. The inspection frequency may include one month inspection, one quarter inspection, one half year inspection, and one year inspection. For example, a class A business may be inspected once a year, a class B business may be inspected once a half year, a class C business may be inspected once a quarter, and a class D business may be inspected once a month.
Based on the same inventive concept, fig. 4 is a schematic diagram of an intelligent supervision system of a food production enterprise according to an embodiment of the present invention, where the intelligent supervision system of the food production enterprise includes: a first obtaining module 41, configured to obtain basic information of a food producer, a camera monitoring video in a first period of time at a gate of the food producer, power consumption time series data in the first period of time of the food producer, and water consumption time series data in the first period of time of the food producer; a first risk level determining module 42, configured to determine a first risk level of the food production enterprise using a first risk level model based on basic information of the food production enterprise, a camera surveillance video in a first period of time at a gate of the food production enterprise, power usage time series data in the first period of time at the food production enterprise, and water usage time series data in the first period of time at the food production enterprise; a second obtaining module 43, configured to obtain a garbage collection amount in a first time period of a food production enterprise and a food throughput in the first time period of the food production enterprise; a second risk level determination module 44 for determining a second risk level of the food production facility using a second risk level model based on the volume of trash clear during the first time period of the food production facility and the volume of food production during the first time period of the food production facility; a risk level determining module 45, configured to determine a risk level of the food production enterprise based on the first risk level and the second risk level; an inspection frequency determination module 46 is configured to determine an inspection frequency for the food manufacturing facility based on the risk level of the food manufacturing facility.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as shown in fig. 5, including:
a processor 51; a memory 52 for storing executable program instructions in the processor 51; wherein the processor 51 is configured to execute to implement a method of intelligent supervision of a food production enterprise as provided above, the method comprising: acquiring basic information of a food producer, a camera monitoring video in a first time period of a gate of the food producer, power utilization time sequence data in the first time period of the food producer and water utilization time sequence data in the first time period of the food producer; determining a first risk degree of the food production enterprise by using a first risk degree model based on the basic information of the food production enterprise, the camera monitoring video in the first time period of the gate of the food production enterprise, the power utilization time series data in the first time period of the food production enterprise and the water utilization time series data in the first time period of the food production enterprise; the method comprises the steps of obtaining garbage cleaning and conveying capacity in a first time period of a food production enterprise and food production capacity in the first time period of the food production enterprise; determining a second risk level of the food production facility using a second risk level model based on the volume of trash clear during the first time period of the food production facility and the volume of food production during the first time period of the food production facility; determining a risk level of the food production enterprise based on the first risk level and the second risk level; and determining the inspection frequency of the food production enterprises based on the risk degree of the food production enterprises.
Based on the same inventive concept, the present embodiment provides a non-transitory computer readable storage medium, which when executed by the processor 51 of the electronic device, enables the electronic device to perform a method of implementing intelligent supervision of a food producer as provided above, the method comprising acquiring basic information of the food producer, camera surveillance video in a first period of a doorway of the food producer, electricity consumption time series data in the first period of the food producer, and water consumption time series data in the first period of the food producer; determining a first risk degree of the food production enterprise by using a first risk degree model based on the basic information of the food production enterprise, the camera monitoring video in the first time period of the gate of the food production enterprise, the power utilization time series data in the first time period of the food production enterprise and the water utilization time series data in the first time period of the food production enterprise; the method comprises the steps of obtaining garbage cleaning and conveying capacity in a first time period of a food production enterprise and food production capacity in the first time period of the food production enterprise; determining a second risk level of the food production facility using a second risk level model based on the volume of trash clear during the first time period of the food production facility and the volume of food production during the first time period of the food production facility; determining a risk level of the food production enterprise based on the first risk level and the second risk level; and determining the inspection frequency of the food production enterprises based on the risk degree of the food production enterprises.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (10)
1. An intelligent supervision method for a food production enterprise, comprising the following steps:
acquiring basic information of a food producer, a camera monitoring video in a first time period of a gate of the food producer, power utilization time sequence data in the first time period of the food producer and water utilization time sequence data in the first time period of the food producer;
determining a first risk degree of the food production enterprise by using a first risk degree model based on the basic information of the food production enterprise, the camera monitoring video in the first time period of the gate of the food production enterprise, the power utilization time series data in the first time period of the food production enterprise and the water utilization time series data in the first time period of the food production enterprise;
the method comprises the steps of obtaining garbage cleaning and conveying capacity in a first time period of a food production enterprise and food production capacity in the first time period of the food production enterprise;
determining a second risk level of the food production facility using a second risk level model based on the volume of trash clear during the first time period of the food production facility and the volume of food production during the first time period of the food production facility;
determining a risk level of the food production enterprise based on the first risk level and the second risk level;
and determining the inspection frequency of the food production enterprises based on the risk degree of the food production enterprises.
2. The method of intelligent supervision of a food production facility of claim 1, wherein the input of the first risk model includes basic information of the food production facility, a camera surveillance video within a first time period of a doorway of the food production facility, electricity time series data within the first time period of the food production facility, and water time series data within the first time period of the food production facility, and the output of the first risk model is a first risk of the food production facility;
the input of the second risk degree model comprises garbage collection amount in the first time period of the food producer and food production amount in the first time period of the food producer, and the output of the second risk degree model is the second risk degree of the food producer.
3. The method of intelligent supervision of a food production facility of claim 1, wherein the determining a risk level of the food production facility based on the first risk level and the second risk level comprises: and obtaining the risk degree of the food production enterprise by weighting and summing the first risk degree and the second risk degree according to a preset weight coefficient.
4. The method of intelligent supervision of a food production facility of claim 1, wherein the inspection frequency comprises one month inspection, one quarter inspection, one half year inspection, and one year inspection.
5. The method of intelligent supervision of a food production facility of claim 1, wherein the second risk model is obtained by a training process comprising:
acquiring a plurality of training samples, wherein the training samples comprise sample input data and labels corresponding to the sample input data, the sample input data is garbage collection and transportation amount in a first time period of a sample food producer and food production amount in the first time period of the sample food producer, and the labels are second risk degrees of the sample food producer;
and training an initial second risk degree model based on the plurality of training samples to obtain the second risk degree model.
6. An intelligent supervision system for a food production facility, comprising:
the first acquisition module is used for acquiring basic information of a food producer, a camera monitoring video in a first time period of a gate of the food producer, power utilization time series data in the first time period of the food producer and water utilization time series data in the first time period of the food producer;
the first risk degree determining module is used for determining a first risk degree of the food production enterprise by using a first risk degree model based on basic information of the food production enterprise, a camera monitoring video in a first time period of a gate of the food production enterprise, power utilization time series data in the first time period of the food production enterprise and water utilization time series data in the first time period of the food production enterprise;
the second acquisition module is used for acquiring the garbage cleaning and transporting amount in the first time period of the food production enterprises and the food production amount in the first time period of the food production enterprises;
a second risk degree determination module for determining a second risk degree of the food production enterprise using a second risk degree model based on the garbage collection amount in the first time period of the food production enterprise and the food production amount in the first time period of the food production enterprise;
the risk degree determining module is used for determining the risk degree of the food production enterprise based on the first risk degree and the second risk degree;
and the checking frequency determining module is used for determining the checking frequency of the food production enterprises based on the risk degree of the food production enterprises.
7. The intelligent supervisory system of a food manufacturing facility according to claim 6, wherein the input of the first risk model includes basic information of the food manufacturing facility, a camera surveillance video within a first time period of a doorway of the food manufacturing facility, time series data of electricity usage within the first time period of the food manufacturing facility, and time series data of water usage within the first time period of the food manufacturing facility, and wherein the output of the first risk model is a first risk of the food manufacturing facility;
the input of the second risk degree model comprises garbage collection amount in the first time period of the food producer and food production amount in the first time period of the food producer, and the output of the second risk degree model is the second risk degree of the food producer.
8. The intelligent supervisory system of a food manufacturing company according to claim 6, wherein the risk level determining module is further configured to obtain the risk level of the food manufacturing company by performing weighted summation on the first risk level and the second risk level according to a preset weight coefficient.
9. An electronic device, comprising: a memory; a processor; a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the steps of the intelligent supervision method of a food product manufacturing enterprise as claimed in any one of claims 1 to 5.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps corresponding to the intelligent supervision method of a food production enterprise as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310445565.XA CN116596300A (en) | 2023-04-19 | 2023-04-19 | Intelligent supervision method, system, equipment and medium for food production enterprises |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310445565.XA CN116596300A (en) | 2023-04-19 | 2023-04-19 | Intelligent supervision method, system, equipment and medium for food production enterprises |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116596300A true CN116596300A (en) | 2023-08-15 |
Family
ID=87599870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310445565.XA Pending CN116596300A (en) | 2023-04-19 | 2023-04-19 | Intelligent supervision method, system, equipment and medium for food production enterprises |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596300A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573924A (en) * | 2024-01-16 | 2024-02-20 | 口碑(上海)信息技术有限公司 | Kitchen data processing method and electronic equipment |
| CN118279808A (en) * | 2024-06-04 | 2024-07-02 | 杭州祐全科技发展有限公司 | Spot check evidence obtaining method, system, electronic equipment and medium based on video analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948870A (en) * | 2017-12-20 | 2019-06-28 | 联易软件有限公司 | Food safety risk grade determines method and device |
| CN110189057A (en) * | 2019-06-11 | 2019-08-30 | 浙江清华长三角研究院 | A kind of the food enterprises risk stratification early warning system and method |
| CN112801431A (en) * | 2021-04-13 | 2021-05-14 | 广东浩迪智云技术有限公司 | Enterprise operation risk assessment method and system based on artificial intelligence analysis |
| WO2021232588A1 (en) * | 2020-05-21 | 2021-11-25 | 平安国际智慧城市科技股份有限公司 | Food safety risk assessment method, apparatus, device, and storage medium |
-
2023
- 2023-04-19 CN CN202310445565.XA patent/CN116596300A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948870A (en) * | 2017-12-20 | 2019-06-28 | 联易软件有限公司 | Food safety risk grade determines method and device |
| CN110189057A (en) * | 2019-06-11 | 2019-08-30 | 浙江清华长三角研究院 | A kind of the food enterprises risk stratification early warning system and method |
| WO2021232588A1 (en) * | 2020-05-21 | 2021-11-25 | 平安国际智慧城市科技股份有限公司 | Food safety risk assessment method, apparatus, device, and storage medium |
| CN112801431A (en) * | 2021-04-13 | 2021-05-14 | 广东浩迪智云技术有限公司 | Enterprise operation risk assessment method and system based on artificial intelligence analysis |
Non-Patent Citations (3)
| Title |
|---|
| 刘世新: "制造业质量风险评估体系实证研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》, no. 05, pages 1 - 65 * |
| 宜昌市市场监督管理局: "关于公开征求《宜昌市食品生产企业食品安全信用分级分类监管工作管理办法（试行）》意见的公告", 《百度HTTP://XXGK.YICHANG.GOV.CN/SHOW.HTML?ID=213112&DEPID=846》 * |
| 李艳红: "基于BP的海产食品出口风险分析模型研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 02, pages 1 - 43 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573924A (en) * | 2024-01-16 | 2024-02-20 | 口碑(上海)信息技术有限公司 | Kitchen data processing method and electronic equipment |
| CN118279808A (en) * | 2024-06-04 | 2024-07-02 | 杭州祐全科技发展有限公司 | Spot check evidence obtaining method, system, electronic equipment and medium based on video analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116596300A (en) | Intelligent supervision method, system, equipment and medium for food production enterprises | |
| CN106598791B (en) | Industrial equipment fault preventive identification method based on machine learning | |
| CN111461555B (en) | Production line quality monitoring method, device and system | |
| CN110864795B (en) | Weighing abnormity alarm system | |
| CN114140094B (en) | Intelligent risk monitoring and early warning system for food enterprises | |
| CN115309871B (en) | Industrial big data processing method and system based on artificial intelligence algorithm | |
| CN117152119A (en) | Profile flaw visual detection method based on image processing | |
| CN116579715A (en) | Remote supervision method, equipment and medium for grain warehouse | |
| CN116703368B (en) | Synchronous line loss intelligent closed-loop monitoring method based on data mining | |
| CN112990546A (en) | Chemical plant power transformer fault prediction method based on particle swarm and neural network | |
| CN113988711A (en) | Power consumption data-based monitoring method for stopping or limiting production of sewage disposal enterprises in control state | |
| CN115545473A (en) | LSTM-based intelligent prediction method for domestic garbage throwing trend | |
| CN117541988B (en) | Object detection method of renewable resource recycling system | |
| Akcay | An alert-assisted inspection policy for a production process with imperfect condition signals | |
| CN117250201B (en) | Swimming pool brick layer defect detection method and system | |
| CN116993012B (en) | Block chain-based commodity packaging method and system | |
| CN117648658A (en) | Abnormal detection method for traffic violation model training process | |
| CN117522203A (en) | Management system and method for measuring and calculating carbon emission | |
| CN110727910B (en) | Method and system for realizing copying and collecting risk prediction and business linkage | |
| CN115356990A (en) | Material yard equipment fault prediction method and system based on deep learning and storage medium | |
| CN114693466B (en) | Monitoring method and monitoring device for operation of manufacturing enterprises based on big data | |
| CN115759460A (en) | Method for predicting cooperation relationship between core enterprise and supplier based on convolutional neural network | |
| Chen et al. | Learn to predict vertical track irregularity with extremely imbalanced data | |
| CN117875946B (en) | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment | |
| CN110956340A (en) | Engineering test detection data management early warning decision method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230815 |
|
| RJ01 | Rejection of invention patent application after publication |