CN113283768A

CN113283768A - Food detection item extraction method, device, equipment and storage medium

Info

Publication number: CN113283768A
Application number: CN202110607826.4A
Authority: CN
Inventors: 何丽英
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2021-06-01
Filing date: 2021-06-01
Publication date: 2021-08-20

Abstract

The invention relates to the field of artificial intelligence, and discloses a method, a device, equipment and a storage medium for extracting food detection items, which are used for solving the technical problems of low efficiency and poor effect in extracting the food detection items in the prior art. The method comprises the following steps: receiving and analyzing at least one piece of spot check related information carried by a food detection item extraction request; determining corresponding food to be detected according to the sampling related information, and sequentially inputting the food to be detected into a preset risk parameter identification model to obtain risk parameters of the food to be detected; sequencing the food to be detected according to the risk parameters to obtain a food risk sequence; screening the food risk sequences according to a preset risk screening rule to obtain the risk food recommended for spot inspection; and extracting risk items and corresponding risk associated information from the food risk knowledge graph, and screening out corresponding food detection items. In addition, the invention also relates to a block chain technology, and the related information of the risk food can be stored in the block chain.

Description

Food detection item extraction method, device, equipment and storage medium

Technical Field

The invention relates to the field of artificial intelligence, in particular to a method, a device, equipment and a storage medium for extracting food detection items.

Background

Food safety supervision spot check is an important means for food safety supervision in China, but due to the characteristic of spot check, the situations of 'undetected' and 'substituted by points' occur occasionally, so that the problem finding capability of the food safety supervision spot check is weak, and the food safety supervision spot check is very important for selecting the type of the spot check food and food detection items during each spot check.

In the prior art, a sampling person generally selects food to be sampled and food detection items according to historical experience or a random mode, so that the efficiency is low and the selection effect is poor.

Disclosure of Invention

The invention mainly aims to solve the technical problems of low efficiency and poor selection effect in the process of extracting food detection items in the prior art.

The invention provides a food detection item extraction method in a first aspect, which comprises the following steps: receiving a food detection item extraction request, and analyzing at least one piece of selective examination related information carried in the food detection item extraction request, wherein the selective examination related information comprises selective examination time information and selective examination region information; determining corresponding food to be detected according to the selective examination time information and the selective examination region information; sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain the risk parameters of the food to be detected; sequencing the food to be detected according to the risk parameters to obtain a food risk sequence; screening the food risk sequence according to a preset risk screening rule to obtain the risk food recommended for spot inspection; and extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

Optionally, in a first implementation manner of the first aspect of the present invention, the risk parameters include a detection risk parameter and a public opinion risk parameter, and the sequentially inputting the food to be detected into a preset risk parameter identification model to identify the food risk parameters to obtain the risk parameters of the food to be detected includes: screening out relevant historical spot check data of the food to be detected from a pre-established historical food spot check database according to the spot check time information and the spot check area information, and calculating detection risk information based on the relevant historical spot check data; determining a public opinion time range according to the sampling inspection time information and the sampling inspection region information, and acquiring public opinion risk information of the food to be detected in the public opinion time range; and calling a preset risk parameter identification model to identify food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected.

Optionally, in a second implementation manner of the first aspect of the present invention, the detecting risk information includes historical risk information, regional risk information, and weather risk information, the screening out relevant historical spot check data of the food to be detected from a pre-established historical food spot check database according to the spot check time information and the spot check regional information, and calculating the detecting risk information based on the relevant historical spot check data includes: determining a historical sampling time information range according to the sampling time information, screening historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating the historical risk information based on the first sampling data set; screening the spot inspection data which are the same as the spot inspection area information from the historical spot inspection data according to the spot inspection area information to obtain a second spot inspection data set, and calculating the area risk information based on the second spot inspection data set; and acquiring the predicted climate information of the spot check according to the spot check time information and the spot check region information, screening spot check data which is the same as the predicted climate information of the spot check from the historical spot check data according to the predicted climate information of the spot check to obtain a third spot check data set, and calculating the climate risk information based on the third spot check data set.

Optionally, in a third implementation manner of the first aspect of the present invention, the determining a public opinion time range according to the sampling time information and the sampling region information, and the obtaining public opinion risk information of the food to be detected in the public opinion time range includes: determining a public opinion time range according to the spot inspection time information; acquiring public sentiment information related to the food to be detected and complaint reporting information on a food complaint reporting platform within the public sentiment time range; carrying out data normalization processing on the public opinion information and the complaint reporting information to obtain public opinion data and complaint reporting data; and calculating the public opinion risk information of the food to be detected within the public opinion time range according to the public opinion data and the complaint reporting data.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the preset risk screening rules include a level evaluation rule and a level screening rule, and the screening the food risk sequence according to the preset risk screening rule to obtain the risk food recommended for spot inspection includes: evaluating the risk grade of the food risk sequence according to the grade evaluation rule to obtain the risk grade of the food to be detected; and screening out the risk food recommended for the spot check based on the risk grade and the sequencing information in the food risk sequence according to the grade screening rule.

Optionally, in a fifth implementation manner of the first aspect of the present invention, after the extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food that is proposed for spot inspection, and screening out corresponding food detection items according to the risk associated information, the method further includes: acquiring factor association information of risk items and risk factors contained in the food risk knowledge graph; inquiring the item risk factors corresponding to the food detection items according to the factor correlation information; and generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

Optionally, in a sixth implementation manner of the first aspect of the present invention, before the receiving a food detection item extraction request and analyzing at least one piece of spot check related information carried in the food detection item extraction request, the method further includes: acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set; counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times; and acquiring the risk factors of the risk items from the existing knowledge base, and generating a food risk knowledge graph based on the food types, the risk items and the risk factors.

The second aspect of the present invention provides a food inspection item extraction device, including: the food detection system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for receiving a food detection item extraction request and analyzing at least one piece of selective examination related information carried in the food detection item extraction request, and the selective examination related information comprises selective examination time information and selective examination region information; the to-be-detected range determining module is used for determining corresponding to-be-detected food according to the sampling time information and the sampling region information; the identification module is used for sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters so as to obtain the risk parameters of the food to be detected; the sequencing module is used for sequencing the food to be detected according to the risk parameters to obtain a food risk sequence; the screening module is used for screening the food risk sequence according to a preset risk screening rule to obtain the risk food recommended for spot inspection; and the output module is used for extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food recommended for spot check, and screening out corresponding food detection items according to the risk associated information.

Optionally, in a first implementation manner of the second aspect of the present invention, the risk parameters include a detection risk parameter and a public opinion risk parameter, and the identifying module includes: the detection risk information calculation unit is used for screening out relevant historical spot check data of the food to be detected from a pre-established historical food spot check database according to the spot check time information and the spot check region information, and calculating detection risk information based on the relevant historical spot check data; the public opinion risk information calculation unit is used for determining a public opinion time range according to the sampling inspection time information and the sampling inspection region information and acquiring the public opinion risk information of the food to be detected in the public opinion time range; and the parameter identification unit is used for calling a preset risk parameter identification model to identify the food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected.

Optionally, in a second implementation manner of the second aspect of the present invention, the detection risk information includes historical risk information, regional risk information, and weather risk information, and the detection risk information calculating unit includes: the historical risk information calculation subunit is used for determining a historical sampling time information range according to the sampling time information, screening historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating the historical risk information based on the first sampling data set; the area risk information calculation subunit is used for screening the spot inspection data which are the same as the spot inspection area information from the historical spot inspection data according to the spot inspection area information to obtain a second spot inspection data set, and calculating the area risk information based on the second spot inspection data set; and the climate risk information calculating subunit is used for acquiring the sampling inspection predicted climate information according to the sampling inspection time information and the sampling inspection region information, screening out sampling inspection data which is the same as the sampling inspection predicted climate information from the historical sampling inspection data according to the sampling inspection predicted climate information to obtain a third sampling inspection data set, and calculating the climate risk information based on the third sampling inspection data set.

Optionally, in a third implementation manner of the second aspect of the present invention, the public opinion risk information calculating unit includes: the time range determining subunit is used for determining a public opinion time range according to the sampling inspection time information; the information acquisition subunit is used for acquiring public sentiment information related to the food to be detected and complaint reporting information on a food complaint reporting platform within the public sentiment time range; the data processing subunit is used for carrying out data normalization processing on the public opinion information and the complaint reporting information to obtain public opinion data and complaint reporting data; and the calculating subunit is used for calculating the public opinion risk information of the food to be detected within the public opinion time range according to the public opinion data and the complaint reporting data.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the screening module includes: the grade evaluation unit is used for evaluating the risk grade of the food risk sequence according to the grade evaluation rule to obtain the risk grade of the food to be detected; and the food screening unit is used for screening out the risk food recommended for the spot check based on the risk grade and the sequencing information in the food risk sequence according to the grade screening rule.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the food detection item extraction device further includes a detection item detail generation module, which is specifically configured to: acquiring factor association information of risk items and risk factors contained in the food risk knowledge graph; inquiring the item risk factors corresponding to the food detection items according to the factor correlation information; and generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the food detection item extraction device further includes a knowledge graph generation unit, specifically configured to: acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set; counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times; and acquiring the risk factors of the risk items from the existing knowledge base, and generating a food risk knowledge graph based on the food types, the risk items and the risk factors.

A third aspect of the present invention provides a food inspection item extracting apparatus including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the food test item extraction device to perform the steps of the food test item extraction method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-described food test item extraction method.

In the technical scheme provided by the invention, at least one piece of spot check related information carried by a food detection item extraction request is received and analyzed; determining corresponding food to be detected according to the sampling related information, and sequentially inputting the food to be detected into a preset risk parameter identification model to obtain risk parameters of the food to be detected; sequencing the food to be detected according to the risk parameters to obtain a food risk sequence; screening the food risk sequences according to a preset risk screening rule to obtain the risk food recommended for spot inspection; and extracting risk items and corresponding risk associated information from the food risk knowledge graph, and screening out corresponding food detection items. In the embodiment of the invention, the method can automatically extract the risk food and food detection items for suggesting the spot check, improve the efficiency of selecting the food detection items during the spot check of the food, and improve the selection effect of selecting the food detection items.

Drawings

FIG. 1 is a diagram illustrating a first embodiment of a method for extracting food inspection items according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating a second embodiment of a method for extracting food inspection items according to an embodiment of the present invention;

FIG. 3 is a diagram illustrating a method for extracting food inspection items according to a third embodiment of the present invention;

FIG. 4 is a diagram illustrating a fourth embodiment of a method for extracting food inspection items according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of an embodiment of a food item detection extraction apparatus according to the present invention;

FIG. 6 is a schematic diagram of another embodiment of a food item detection extraction apparatus in accordance with an embodiment of the present invention;

fig. 7 is a schematic diagram of an embodiment of a food inspection item extraction apparatus in an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a method, a device, equipment and a storage medium for extracting food detection items, wherein the method receives a food detection item extraction request and analyzes at least one piece of selective examination related information carried in the food detection item extraction request, wherein the selective examination related information comprises selective examination time information and selective examination region information; determining corresponding food to be detected according to the sampling inspection time information and the sampling inspection area information; sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain the risk parameters of the food to be detected; sequencing the food to be detected according to the risk parameters to obtain a food risk sequence; screening the food risk sequences according to a preset risk screening rule to obtain the risk food recommended for spot inspection; and extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information. The method can automatically extract the risk food and food detection items for suggesting the spot check, improve the efficiency of selecting the food detection items during the spot check of the food, and improve the selection effect of selecting the food detection items.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a method for extracting a food inspection item according to an embodiment of the present invention includes:

101. receiving a food detection item extraction request, and analyzing at least one piece of sampling related information carried in the food detection item extraction request;

it is to be understood that the executing subject of the present invention may be a food detection item extracting device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject. After receiving the food detection item extraction request, the server acquires a request information field contained in the extraction request, analyzes the content contained in the request information field, and obtains at least one piece of spot check related information. Wherein, the relevant information of the spot check can comprise the time information of the spot check; spot check regional information or other spot check related information may also be included. In addition, before the step, a food item table is established in advance, wherein the food item table comprises various item names of various types of food so as to classify the related information of the food. Various foods can be classified according to relevant information in the food category table for subsequent data processing.

102. Determining corresponding food to be detected according to the sampling inspection time information and the sampling inspection area information;

and determining the food to be inspected corresponding to the sampling inspection time information and the sampling inspection area information according to the acquired sampling inspection time information and the sampling inspection area information, wherein the food to be inspected can be determined by inputting a form to be inspected in advance when the food to be inspected is determined specifically, and different food to be inspected is generated in the form to be inspected in advance according to different areas and sampling inspection time information.

103. Sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain the risk parameters of the food to be detected;

inputting the food to be detected obtained in the previous step into a preset risk parameter identification model, and calling the risk parameter identification model to identify food risk parameters based on the sampling relevant information obtained in the previous step to obtain the risk parameters of a plurality of foods.

The preset risk parameter identification model can identify the risk parameters of food to be inspected based on the acquired spot inspection related information to obtain the risk parameters, and can acquire historical food spot inspection data in advance, screen and process the historical food spot inspection data to obtain a historical food risk data set, and call the historical food risk data set for training and establishment. Specifically, the risk parameter identification model in this embodiment is established based on the historical risk data set on a data classification tool preset with a clustering algorithm.

104. Sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

105. screening the food risk sequences according to a preset risk screening rule to obtain the risk food recommended for spot inspection;

in the steps, after the risk parameters of a plurality of foods are obtained, the foods are sequenced according to the obtained risk parameters to obtain a food risk sequence.

And after the food risk sequence is obtained, screening the food risk sequence obtained in the previous step according to a preset risk screening rule to obtain the recommended spot check food. In this embodiment, specifically, the risk level evaluation may be performed on the food risk sequence according to a preset risk level evaluation rule to obtain the risk level of the food; and after the risk grades are obtained, the risk grades and the sequencing information in the food risk sequence are integrated to screen out the risk food recommended for spot check.

106. And extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

In the step, a food risk knowledge graph which is established in advance based on historical spot inspection data needs to be acquired, wherein the food risk knowledge graph specifically comprises risk information of each food, and the risk information comprises information such as unqualified items, unqualified grades and unqualified factors appearing in the historical inspection process.

And then, searching for corresponding risk food suggested random inspection items in a food risk knowledge graph established in advance based on historical random inspection data according to the suggested random inspection foods obtained in the previous step. And finally, sequencing the risk food which is suggested for spot inspection and the corresponding suggested detection items according to the risk level and outputting the result, thereby finishing the extraction of the risk food and the detection items thereof.

According to the technical scheme, the method and the device for extracting the food detection items and the system for extracting the food detection items can automatically extract the risk food and the food detection items which are suggested for the spot check, so that the efficiency of selecting the food detection items during the spot check of the food is improved, and the selection effect of selecting the food detection items is improved.

Referring to fig. 2, a second embodiment of the method for extracting food inspection items according to the embodiment of the present invention includes:

201. acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set;

before the step, a historical food spot inspection database is established in advance, wherein the historical food spot inspection database can be a set of historical spot inspection data, historical spot inspection data containing unqualified items in all the historical spot inspection data are obtained, the spot inspection data containing the unqualified items form an unqualified spot inspection data set, and each food has different spot inspection items, such as microorganism items, fungaltoxin items, additive items, quality items, pesticide residue items and other items; labeling the unqualified items and the food of the unqualified items, and forming an unqualified spot inspection data set by the obtained data.

202. Counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times;

counting the unqualified times of the unqualified items of each food in the obtained unqualified spot inspection data set, and calculating the unqualified index of the unqualified items of each food according to the unqualified times and the detection times of each food; and sequencing the unqualified items of each food according to the unqualified index to obtain an unqualified item sequence. And obtaining a unqualified item sequence. And screening the risk items of each food according to the unqualified item sequence according to a preset risk item screening rule. The preset risk item screening rule can be used for screening a plurality of unqualified items with the ranked names of the unqualified item sequences as risk items, and can also be used for screening a plurality of percent unqualified items with the ranked names of the unqualified item sequences as risk items or other items.

203. Acquiring risk factors of risk items from an existing knowledge base, and generating a food risk knowledge graph based on food types, the risk items and the risk factors;

acquiring risk factors of the risk items in an existing knowledge base, wherein the knowledge base is established in advance and comprises factors such as human factors, improper storage factors and the like which are possibly generated by various unqualified items determined by food safety knowledge. And (3) taking the food types and the risk items as entities, and taking the risk factors and other relation data such as the unqualified index data as entity relations to generate a food risk knowledge graph.

204. Receiving a food detection item extraction request, and analyzing at least one piece of sampling related information carried in the food detection item extraction request;

205. determining corresponding food to be detected according to the sampling inspection time information and the sampling inspection area information;

the specific contents in step 204 and step 205 in this embodiment are substantially the same as those in step 101 and step 102 in the foregoing embodiment, and therefore, the details are not repeated herein.

206. Screening out relevant historical spot check data of the food to be detected from a pre-established historical food spot check database according to the spot check time information and the spot check area information, and calculating detection risk information based on the relevant historical spot check data;

in the step, relevant historical spot check data are screened out from a pre-established historical food spot check database according to the obtained spot check relevant information, wherein the number of the spot check relevant information can be multiple, and the spot check relevant information can be spot check time information and spot check area information, the relevant historical spot check data are screened out from the historical spot check database according to the multiple spot check relevant information, and detection risk information is calculated based on the relevant historical spot check data.

207. Determining a public sentiment time range according to the sampling inspection time information and the sampling inspection region information, and acquiring public sentiment risk information of the food to be detected in the public sentiment time range;

after the detection risk information is obtained according to the historical spot inspection data, in this embodiment, a public opinion related time range is obtained according to the spot inspection time information and the spot inspection area information in the spot inspection related information, and public opinion information of food is obtained according to the public opinion related time range, for example, hot food related information in a news website or a social website in two weeks or one month is screened, and the public opinion information is subjected to relevance analysis with food safety, positive and negative emotion judgment and relevant food type analysis, so as to obtain the public opinion risk information.

208. Calling a preset risk parameter identification model to identify food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected;

and after the detection risk information and the public opinion risk information are obtained, calling a preset risk parameter identification model according to the detection risk information and the public opinion risk information to identify the food risk, and obtaining a plurality of food risk parameters. The preset risk parameter identification model can identify the risk parameters of the food according to the obtained spot check related information, the risk parameter identification model can acquire historical food spot check data in advance, screen and process the historical food spot check data to obtain a historical food risk data set, and the historical food risk data set is called to train and establish a data classification tool preset with a clustering algorithm based on the historical risk data set.

209. Sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

210. Evaluating the risk level of the food risk sequence according to a level evaluation rule to obtain the risk level of the food to be detected;

after the food risk parameters are obtained, various food types are sequenced according to the food risk parameters to obtain a food risk sequence, the food risk sequence is subjected to risk grade assessment according to a preset risk grade assessment rule to obtain the risk grade of the food to be detected, and finally the risk grade information and the information in the food risk sequence are integrated to screen the foods to be suggested for selective inspection from various foods to be detected.

Next, a specific example will be described in which various foods are classified once according to a preset primary classification rule. In this embodiment, one grading operation will classify various food products into four grades, the four grades of risk being denoted from high to low as P0', P1', P2 'and P3'; and the primary classification in this step is performed based on the obtained food risk parameter, for example, in this step, a food risk parameter of 0.4 or more is classified as a P0', a food category having a food risk parameter of less than 0.4 and 0.2 or more is classified as a P1', a food category having a food risk parameter of less than 0.2 and 0.1 or more is classified as a P2', and a food category having a food risk parameter of less than 0.1 and 0.05 or more is classified as a P3'.

Subsequently, the various foods are secondarily classified according to a preset secondary classification rule. One grading operation in this embodiment will classify various food products into four grades with the four grades of risk, denoted from high to low as P0", P1", P2 "and P3"; the secondary classification in the step is performed according to the obtained food risk parameters, specifically, firstly, a risk early warning average value m and a risk early warning value standard deviation s are calculated according to all the food risk parameters, the food risk parameter which is greater than or equal to m + s is used as a P0 grade, the food type of which the food risk parameter is less than m + s and is greater than or equal to m + a s is used as a P1 grade, the food type of which the food risk parameter is less than m + a s and is greater than or equal to m + b s is used as a P2 grade, and the food type of which the food risk parameter is less than m + b s and is greater than or equal to m + c s is used as a P3 grade; wherein, the coefficients a, b and c are preset numerical values, are related to the number of the food types, and have the value ranges of 0 and 1.

211. Screening out the risk food which is suggested to be checked randomly based on the risk grade and the sorting information in the food risk sequence according to a grade screening rule;

finally, evaluating the risk grades of various food types by integrating the food risk sequence and the grading results of the primary grading and the secondary grading, wherein the food risk grades are divided into four grades, the four grades of risks are represented as P0, P1, P2 and P3 from high to low, and the food types which simultaneously belong to the 10 th grade, the P0 'grade and the P0' grade of the food risk sequence are evaluated as a food risk grade P0; the food categories which belong to the food risk sequences except the P0 grade and are ranked in the levels of 12, P1' and P1 after the P0 grade is removed are evaluated as the food risk grade P1; the food category in the rest food categories except the grades P0 and P1, which belong to the food risk sequence at the same time and are ranked in the grades 15, P2' and P2 after the grades P0 and P1 are removed, is evaluated as the food risk grade P2; the food categories belonging to the food risk series and ranked in the 18, P3 'and P3' grades after removing the P0, P1 and P2 grades in the food risk series except the P0 and P1P2 grades are evaluated as the food risk grade P3. In the present example, after the food types of P0, P1, P2 and P3 are screened, these food types are outputted to obtain the risk food recommended for spot check.

212. And extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

The specific content in this step is substantially the same as that in step 106 in the previous embodiment, and therefore, the detailed description thereof is omitted here.

According to the technical scheme, the method and the device for the food detection item selection can automatically extract the risk food and the food detection item for the suggested spot check, the food risk knowledge graph is established in advance, the suggested detection item corresponding to the risk food is determined according to the knowledge graph, the food detection item selection efficiency during the food spot check is improved, and the food detection item selection effect is improved.

Referring to fig. 3, a third embodiment of the method for extracting food inspection items according to the embodiment of the present invention includes:

301. receiving a food detection item extraction request, and analyzing at least one piece of sampling related information carried in the food detection item extraction request;

302. determining corresponding food to be detected according to the sampling inspection time information and the sampling inspection area information;

the specific contents in step 301 and step 302 in this embodiment are substantially the same as those in step 101 and step 102 in the foregoing embodiment, and therefore, the details are not repeated herein.

303. Determining a historical sampling time information range according to the sampling time information, screening the historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating historical risk information based on the first sampling data set;

the relevant information of the spot check in the embodiment comprises spot check time information, spot check area information and spot check estimated climate information, and the detection risk information comprises historical risk information, area risk information and climate risk information; in this embodiment, the historical risk information, the area risk information, and the climate risk information are calculated according to the sampling inspection time information, the sampling inspection area information, and the sampling inspection predicted climate information, respectively.

Specifically, based on the obtained sampling data in the sampling data sets, the reject indexes of each food in the different historical time periods are calculated, and a plurality of sampling reject indexes are obtained. And then, carrying out weighted calculation on the plurality of sampling inspection disqualification indexes according to the preset disqualification index weight to obtain historical risk information.

For example, when the weighting indices for the historical all-off index, the historical contemporaneous off-spec index, the historical contemporaneous and peri-monthly off-spec index, the most recent one-month off-spec index, the most recent three-month off-spec index, the most recent half-year off-spec index, and the most recent one-year off-spec index are a1, a2, a3, a4, a5, a6, and a7, respectively, then: historical risk information a1 historical all fail index + a2 historical contemporaneous fail index + a3 historical contemporaneous and contemporaneous monthly fail index + a4 latest one month fail index + a5 latest three months fail index + a6 latest half year fail index + a6 latest one year fail index.

304. Screening the spot check data which are the same as the spot check area information from the historical spot check data according to the spot check area information to obtain a second spot check data set, and calculating area risk information based on the second spot check data set;

secondly, according to the selective examination region information contained in the selective examination related information, acquiring selective examination data of various foods in the region, forming a plurality of second selective examination data sets according to the selective examination data, and calculating region risk information of various foods in historical selective examination of the region according to the information in the second selective examination data sets.

305. Acquiring sampling inspection predicted climate information according to the sampling inspection time information and the sampling inspection region information, screening sampling inspection data which are the same as the sampling inspection predicted climate information from historical sampling inspection data according to the sampling inspection predicted climate information to obtain a third sampling inspection data set, and calculating climate risk information based on the third sampling inspection data set;

specifically, in this embodiment, climate prediction information of an area to be spot-checked is first obtained, where the climate prediction information includes weather prediction information, temperature prediction information, and humidity prediction information, historical spot-check data that is the same as or similar to the climate prediction information is respectively screened from historical spot-check data according to the prediction information, a plurality of third spot-check data sets are respectively generated based on the extracted historical spot-check data, and then, the historical spot-check data in the plurality of third spot-check data sets are weighted and calculated according to the degree of association between each type of spot-check predicted climate information and an unqualified parameter, so as to obtain risk climate information. The relevance between the predicted climate information of the spot check and the unqualified parameters is the correlation degree between the detection items and the predicted climate information of the spot check, which is calculated by using a Pearson algorithm after a large amount of spot check data are obtained in advance according to historical spot check data sets.

306. Determining a public sentiment time range according to the sampling inspection time information and the sampling inspection region information, and acquiring public sentiment risk information of the food to be detected in the public sentiment time range;

the specific content in step 306 in this embodiment is substantially the same as that in step 207 in the previous embodiment, and therefore, the detailed description thereof is omitted here.

307. Calling a preset risk parameter identification model to identify food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected;

and after the detection risk information and the public opinion risk information are obtained, calling a preset risk parameter identification model according to the detection risk information and the public opinion risk information to identify the food risk, and obtaining a plurality of food risk parameters.

Wherein, the detection risk information in this step includes the historical risk information, the regional risk information and the weather risk information described in the foregoing embodiment; the preset risk parameter identification model can identify the risk parameters of the food according to the obtained spot check related information, the risk parameter identification model can acquire historical food spot check data in advance, screen and process the historical food spot check data to obtain a historical food risk data set, and the historical food risk data set is called to train and establish a data classification tool preset with a clustering algorithm based on the historical risk data set.

308. Sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

in the steps, after the risk parameters of a plurality of foods are obtained, the foods to be detected are sequenced according to the obtained risk parameters, and a food risk sequence is obtained.

309. Screening the food risk sequences according to a preset risk screening rule to obtain the risk food recommended for spot inspection;

310. extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information;

the specific contents in step 309 and step 310 in this embodiment are substantially the same as those in step 105 and step 106 in the foregoing embodiment, and therefore, the details are not repeated herein.

311. Acquiring factor association information of risk items and risk factors contained in a food risk knowledge graph;

and acquiring a pre-established food risk knowledge graph, reading the content in the knowledge graph, and acquiring factor association information of risk items and risk factors contained in the food risk knowledge graph.

312. Inquiring the item risk factors corresponding to the food detection items according to the factor correlation information;

and inquiring item risk factors corresponding to the food detection items obtained in the previous step according to the read factor association information, wherein the food detection items can specifically comprise microorganism items, mycotoxin items, additive items, quality items, pesticide residue items and other items, and the corresponding item risk factors can specifically comprise human factors, improper storage factors and the like.

313. And generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

And generating a detection item detail list according to the acquired risk food and food detection items for suggesting the spot check and the corresponding item risk factors, storing the detection item detail list into a database, and subsequently outputting the detection item detail list, the risk food for suggesting the spot check and the corresponding suggested detection items together according to the requirement.

According to the technical scheme, different historical spot inspection information can be determined according to various factors, and according to the obtained different spot inspection information, the risk food and food detection items suggested for spot inspection are automatically extracted, so that the efficiency of selecting the food detection items during food spot inspection is greatly improved, and the selection effect of selecting the food detection items is improved.

Referring to fig. 4, a fourth embodiment of the method for extracting food inspection items according to the embodiment of the present invention includes:

401. acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set;

402. counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times;

403. acquiring risk factors of risk items from an existing knowledge base, and generating a food risk knowledge graph based on food types, the risk items and the risk factors;

in this embodiment, the specific contents in steps 401 through 403 are substantially the same as those in steps 201 through 203, and therefore, the detailed description thereof is omitted.

404. Receiving a food detection item extraction request, and analyzing at least one piece of sampling related information carried in the food detection item extraction request;

405. determining corresponding food to be detected according to the sampling inspection time information and the sampling inspection area information;

the specific contents in step 403 and step 404 in this embodiment are substantially the same as those in step 101 and step 102 in the previous embodiment, and therefore, the details are not repeated herein.

406. Determining a historical sampling time information range according to the sampling time information, screening the historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating historical risk information based on the first sampling data set;

407. screening the spot check data which are the same as the spot check area information from the historical spot check data according to the spot check area information to obtain a second spot check data set, and calculating area risk information based on the second spot check data set;

408. acquiring sampling inspection predicted climate information according to the sampling inspection time information and the sampling inspection region information, screening sampling inspection data which are the same as the sampling inspection predicted climate information from historical sampling inspection data according to the sampling inspection predicted climate information to obtain a third sampling inspection data set, and calculating climate risk information based on the third sampling inspection data set;

in the present embodiment, the specific contents in steps 406-408 are substantially the same as those in steps 303-305, and therefore, the description thereof is omitted here.

409. Determining a public opinion time range according to the sampling inspection time information;

in this embodiment, before this step, a food item table is established in advance, where the food item table includes various names of various types of food, so as to classify the related information of the food. Various foods can be classified according to relevant information in the food category table for subsequent data processing.

First, a public opinion time range is determined according to the sampling time information according to a preset time division rule, in this embodiment, the public opinion time range may be a time range set before the sampling time information point, for example, two weeks or a month is selected as the public opinion time range.

410. Acquiring public sentiment information related to food to be detected within a public sentiment time range and complaint reporting information on a food complaint reporting platform;

411. carrying out data normalization processing on the public opinion information and the complaint reporting information to obtain public opinion data and complaint reporting data;

412. calculating public sentiment risk information of the food to be detected within a public sentiment time range according to the public sentiment data and the complaint reporting data;

extracting tools in a preset time period through a crawler tool or other data to obtain public opinion information which is disclosed on a network and related to food safety, such as screening hot food related information in a news website or a social website in nearly two weeks or one month, and judging the association degree analysis, positive and negative emotion judgment and associated food type analysis of the food safety of the public opinion information to obtain a public opinion information value; and carrying out numerical normalization processing on the public sentiment information value according to a preset public sentiment normalization calculation rule to obtain the public sentiment index of the food.

The method comprises the steps of obtaining food complaint reporting information with use authority, counting various food complaint reporting information and concrete reasons of the complaint reporting, and carrying out numerical normalization processing on the food complaint reporting information according to a preset food complaint reporting normalization calculation rule to obtain a complaint reporting index of the food.

Then, a pre-established public opinion risk information calculation method is obtained, where the public opinion risk information calculation method may be weighted calculation or other calculation methods, and in this embodiment, the weighted calculation is taken as an example for explanation, the weight values of each index are preset, and the obtained public opinion data and the complaint report data are calculated according to each weight value to obtain the public opinion risk information.

413. Calling a preset risk parameter identification model to identify food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected;

the specific content in this step is substantially the same as that in step 307 in the previous embodiment, and therefore, the detailed description thereof is omitted.

414. Sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

415. Evaluating the risk level of the food risk sequence according to a level evaluation rule to obtain the risk level of the food to be detected;

416. screening out the risk food which is suggested to be checked randomly based on the risk grade and the sorting information in the food risk sequence according to a grade screening rule;

in the present embodiment, the specific contents in

steps

415 and 416 are substantially the same as those in

steps

210 and 211, and therefore, the detailed description thereof is omitted here.

417. Extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information;

418. Acquiring factor association information of risk items and risk factors contained in a food risk knowledge graph;

419. inquiring the item risk factors corresponding to the food detection items according to the factor correlation information;

420. and generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

In the present embodiment, the specific contents in steps 418-420 are substantially the same as those in steps 311-313, and therefore, the description thereof is omitted here.

According to the technical scheme, different historical spot inspection information can be determined according to various factors, risk food and food detection items suggested for spot inspection are automatically extracted according to the obtained different spot inspection information, a food risk knowledge graph is established in advance, the food detection items corresponding to the risk food are determined according to the knowledge graph, the food detection item selection efficiency during food spot inspection is greatly improved, and the food detection item selection effect is improved.

With reference to fig. 5, the method for extracting food inspection items in the embodiment of the present invention is described above, and the food inspection item extraction device in the embodiment of the present invention is described below, where an embodiment of the food inspection item extraction device in the embodiment of the present invention includes:

an obtaining module 501, configured to receive a food detection item extraction request, and analyze at least one piece of sampling related information carried in the food detection item extraction request, where the sampling related information includes sampling time information and sampling area information;

a to-be-detected range determining module 502, configured to determine, according to the sampling time information and the sampling region information, a corresponding to-be-detected food;

the identification module 503 is configured to sequentially input the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain risk parameters of the food to be detected;

a sorting module 504, configured to sort the food to be detected according to the risk parameters, so as to obtain a food risk sequence;

the screening module 505 is configured to screen the food risk sequence according to a preset risk screening rule to obtain a risk food for which a selective inspection is suggested;

and the output module 506 is used for extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

Referring to fig. 6, another embodiment of the food inspection item extracting apparatus according to the embodiment of the present invention includes:

an obtaining module 501, configured to receive a food detection item extraction request, and analyze at least one piece of sampling related information carried in the food detection item extraction request, where the sampling related information includes sampling time information and sampling area information; a to-be-detected range determining module 502, configured to determine, according to the sampling time information and the sampling region information, a corresponding to-be-detected food; the identification module 503 is configured to sequentially input the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain risk parameters of the food to be detected; a sorting module 504, configured to sort the food to be detected according to the risk parameters, so as to obtain a food risk sequence; the screening module 505 is configured to screen the food risk sequence according to a preset risk screening rule to obtain a risk food for which a selective inspection is suggested; and the output module 506 is used for extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

Optionally, the risk parameters include a detection risk parameter and a public opinion risk parameter, and the identifying module 503 includes: a detection risk information calculation unit 5031 configured to screen, according to the sampling inspection time information and the sampling inspection area information, relevant historical sampling inspection data of the food to be inspected from a pre-established historical food sampling inspection database, and calculate detection risk information based on the relevant historical sampling inspection data; a public opinion risk information calculating unit 5032, configured to determine a public opinion time range according to the sampling time information and the sampling region information, and obtain public opinion risk information of the food to be detected within the public opinion time range; a parameter identification unit 5033, configured to invoke a preset risk parameter identification model to identify food risk parameters according to the detection risk information and public opinion risk information, so as to obtain the risk parameters of the food to be detected.

Optionally, the detection risk information includes historical risk information, regional risk information, and weather risk information, and the detection risk information calculating unit 5031 includes: the historical risk information calculation subunit is used for determining a historical sampling time information range according to the sampling time information, screening historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating the historical risk information based on the first sampling data set; the area risk information calculation subunit is used for screening the spot inspection data which are the same as the spot inspection area information from the historical spot inspection data according to the spot inspection area information to obtain a second spot inspection data set, and calculating the area risk information based on the second spot inspection data set; and the climate risk information calculating subunit is used for acquiring the sampling inspection predicted climate information according to the sampling inspection time information and the sampling inspection region information, screening out sampling inspection data which is the same as the sampling inspection predicted climate information from the historical sampling inspection data according to the sampling inspection predicted climate information to obtain a third sampling inspection data set, and calculating the climate risk information based on the third sampling inspection data set.

Optionally, the public opinion risk information calculation unit 5032 includes: the time range determining subunit is used for determining a public opinion time range according to the sampling inspection time information; the information acquisition subunit is used for acquiring public sentiment information related to the food to be detected and complaint reporting information on a food complaint reporting platform within the public sentiment time range; the data processing subunit is used for carrying out data normalization processing on the public opinion information and the complaint reporting information to obtain public opinion data and complaint reporting data; and the calculating subunit is used for calculating the public opinion risk information of the food to be detected within the public opinion time range according to the public opinion data and the complaint reporting data.

Optionally, the screening module 505 includes: a grade evaluation unit 5051, configured to evaluate a risk grade of the food risk sequence according to the grade evaluation rule to obtain a risk grade of the food to be detected; a food screening unit 5052, configured to screen out the risk food for which the spot check is suggested based on the risk level and the ranking information in the food risk sequence according to the level screening rule.

Optionally, the food detection item extraction device further includes a detection item detail generation module, specifically configured to: acquiring factor association information of risk items and risk factors contained in the food risk knowledge graph; inquiring the item risk factors corresponding to the food detection items according to the factor correlation information; and generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

Optionally, the food detection item extraction device further includes a knowledge graph generation unit, specifically configured to: acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set; counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times; and acquiring the risk factors of the risk items from the existing knowledge base, and generating a food risk knowledge graph based on the food types, the risk items and the risk factors.

Fig. 5 and 6 describe the food detection item extraction device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the food detection item extraction device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

Fig. 7 is a schematic structural diagram of a food inspection item extraction apparatus 700 according to an embodiment of the present invention, where the food inspection item extraction apparatus 700 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 710 (e.g., one or more processors) and a memory 720, one or more storage media 730 (e.g., one or more mass storage devices) for storing applications 733 or data 732. Memory 720 and storage medium 730 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations for the food detection item extraction apparatus 700. Still further, processor 710 may be configured to communicate with storage medium 730 to execute a series of instruction operations in storage medium 730 on food testing item extraction device 700.

The food testing item extraction apparatus 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input-output interfaces 760, and/or one or more operating systems 731, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the food testing item extraction device shown in FIG. 7 does not constitute a limitation of the food testing item extraction device, and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.

The present invention also provides a computer device, which can be any device capable of executing the food detection item extraction method described in the above embodiments, the computer device includes a memory and a processor, the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the food detection item extraction method in the above embodiments.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the food detection item extraction method.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A food detection item extraction method is characterized by comprising the following steps:

receiving a food detection item extraction request, and analyzing at least one piece of selective examination related information carried in the food detection item extraction request, wherein the selective examination related information comprises selective examination time information and selective examination region information;

determining corresponding food to be detected according to the selective examination time information and the selective examination region information;

sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters, so as to obtain the risk parameters of the food to be detected;

sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

screening the food risk sequence according to a preset risk screening rule to obtain the risk food recommended for spot inspection;

and extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food for which the spot check is suggested, and screening out corresponding food detection items according to the risk associated information.

2. The method for extracting food detection items according to claim 1, wherein the risk parameters include detection risk parameters and public opinion risk parameters, and the step of sequentially inputting the food to be detected into a preset risk parameter identification model to identify the food risk parameters comprises the steps of:

screening out relevant historical spot check data of the food to be detected from a pre-established historical food spot check database according to the spot check time information and the spot check area information, and calculating detection risk information based on the relevant historical spot check data;

determining a public opinion time range according to the sampling inspection time information and the sampling inspection region information, and acquiring public opinion risk information of the food to be detected in the public opinion time range;

and calling a preset risk parameter identification model to identify food risk parameters according to the detection risk information and the public opinion risk information to obtain the risk parameters of the food to be detected.

3. The method for extracting food inspection items according to claim 2, wherein the inspection risk information includes historical risk information, regional risk information, and weather risk information, the screening of the historical food inspection data related to the food to be inspected from a pre-established historical food inspection database according to the inspection time information and the inspection regional information, and the calculating of the inspection risk information based on the historical inspection data includes:

determining a historical sampling time information range according to the sampling time information, screening historical food sampling data according to the historical sampling time information range to obtain a first sampling data set, and calculating the historical risk information based on the first sampling data set;

screening the spot inspection data which are the same as the spot inspection area information from the historical spot inspection data according to the spot inspection area information to obtain a second spot inspection data set, and calculating the area risk information based on the second spot inspection data set;

and acquiring the predicted climate information of the spot check according to the spot check time information and the spot check region information, screening spot check data which is the same as the predicted climate information of the spot check from the historical spot check data according to the predicted climate information of the spot check to obtain a third spot check data set, and calculating the climate risk information based on the third spot check data set.

4. The method as claimed in claim 3, wherein the determining a public opinion time range according to the sampling time information and the sampling region information, and the obtaining the public opinion risk information of the food to be detected in the public opinion time range comprises:

determining a public opinion time range according to the spot inspection time information;

acquiring public sentiment information related to the food to be detected and complaint reporting information on a food complaint reporting platform within the public sentiment time range;

carrying out data normalization processing on the public opinion information and the complaint reporting information to obtain public opinion data and complaint reporting data;

and calculating the public opinion risk information of the food to be detected within the public opinion time range according to the public opinion data and the complaint reporting data.

5. The method for extracting food detection items according to claim 4, wherein the preset risk screening rules include a level evaluation rule and a level screening rule, and the screening of the food risk sequences according to the preset risk screening rules to obtain the risk food recommended for spot inspection includes:

evaluating the risk grade of the food risk sequence according to the grade evaluation rule to obtain the risk grade of the food to be detected;

and screening out the risk food recommended for the spot check based on the risk grade and the sequencing information in the food risk sequence according to the grade screening rule.

6. The method for extracting food detection items according to claim 5, wherein after the risk food is extracted from a preset food risk knowledge graph according to the proposed spot check, and corresponding risk associated information is screened out according to the risk associated information, the method further comprises:

acquiring factor association information of risk items and risk factors contained in the food risk knowledge graph;

inquiring the item risk factors corresponding to the food detection items according to the factor correlation information;

and generating a detection item list based on the risk food for suggesting the spot check, the food detection items and the corresponding item risk factors.

7. The method for extracting food detection items according to any one of claims 1 to 6, wherein before the receiving a request for extracting food detection items and analyzing at least one piece of spot check related information carried in the request for extracting food detection items, the method further comprises:

acquiring historical spot check data containing unqualified items in a pre-established historical food spot check database to obtain an unqualified spot check data set;

counting the unqualified times of the unqualified items of each food in the unqualified spot inspection data set, and generating the risk items of each food based on the unqualified times;

and acquiring the risk factors of the risk items from the existing knowledge base, and generating a food risk knowledge graph based on the food types, the risk items and the risk factors.

8. A food detection item extraction device, characterized in that the food detection item extraction device comprises:

the food detection system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for receiving a food detection item extraction request and analyzing at least one piece of selective examination related information carried in the food detection item extraction request, and the selective examination related information comprises selective examination time information and selective examination region information;

the to-be-detected range determining module is used for determining corresponding to-be-detected food according to the sampling time information and the sampling region information;

the identification module is used for sequentially inputting the food to be detected into a preset risk parameter identification model to identify food risk parameters so as to obtain the risk parameters of the food to be detected;

the sequencing module is used for sequencing the food to be detected according to the risk parameters to obtain a food risk sequence;

the screening module is used for screening the food risk sequence according to a preset risk screening rule to obtain the risk food recommended for spot inspection;

and the output module is used for extracting risk items and corresponding risk associated information from a preset food risk knowledge graph according to the risk food recommended for spot check, and screening out corresponding food detection items according to the risk associated information.

9. A food detection item extraction device, characterized in that the food detection item extraction device comprises: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invokes the instructions in the memory to cause the food test item extraction device to perform the steps of the food test item extraction method of any of claims 1-7.

10. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the steps of the food item detection extraction method according to any one of claims 1-7.