CN115860769A - Hazardous waste tracing method based on matching degree and cross entropy - Google Patents
Hazardous waste tracing method based on matching degree and cross entropy Download PDFInfo
- Publication number
- CN115860769A CN115860769A CN202310139981.7A CN202310139981A CN115860769A CN 115860769 A CN115860769 A CN 115860769A CN 202310139981 A CN202310139981 A CN 202310139981A CN 115860769 A CN115860769 A CN 115860769A
- Authority
- CN
- China
- Prior art keywords
- waste
- index
- similarity
- indexes
- calculating
- 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.)
- Granted
Links
- 239000002920 hazardous waste Substances 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000002699 waste material Substances 0.000 claims abstract description 127
- 238000004364 calculation method Methods 0.000 claims abstract description 48
- 238000009826 distribution Methods 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000005389 magnetism Effects 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 2
- 238000005094 computer simulation Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000010365 information processing Effects 0.000 abstract description 2
- 229910052782 aluminium Inorganic materials 0.000 description 14
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 14
- 239000002910 solid waste Substances 0.000 description 8
- 239000000126 substance Substances 0.000 description 4
- KRHYYFGTRYWZRS-UHFFFAOYSA-M Fluoride anion Chemical compound [F-] KRHYYFGTRYWZRS-UHFFFAOYSA-M 0.000 description 3
- PMHQVHHXPFUNSP-UHFFFAOYSA-M copper(1+);methylsulfanylmethane;bromide Chemical compound Br[Cu].CSC PMHQVHHXPFUNSP-UHFFFAOYSA-M 0.000 description 3
- 238000003723 Smelting Methods 0.000 description 2
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 1
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004821 distillation Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000012452 mother liquor Substances 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- TWNQGVIAIRXVLR-UHFFFAOYSA-N oxo(oxoalumanyloxy)alumane Chemical compound O=[Al]O[Al]=O TWNQGVIAIRXVLR-UHFFFAOYSA-N 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000010888 waste organic solvent Substances 0.000 description 1
Images
Classifications
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W90/00—Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of data information processing, and particularly relates to a dangerous waste tracing method based on matching degree and cross entropy, which comprises the following steps: s1, constructing a dangerous waste fingerprint characteristic database, wherein the database contains characteristic information of dangerous waste; s2, a user inputs a corresponding retrieval index, and the database matches corresponding characteristic information according to the input retrieval index; s3, after matching, similarity calculation is carried out according to the number of input retrieval indexes; when the number N of the retrieval indexes is 1, calculating the similarity by adopting a single index calculation model; when N is more than or equal to 2, calculating the similarity by adopting a multi-index calculation model; and S4, displaying the tracing result according to the calculated similarity. The method can not only give quantitative matching results, but also reduce the calculated amount, improve the matching efficiency and increase the accuracy of database matching; the method is beneficial to the rapid identification of the waste, realizes the rapid tracing of the hazardous waste, and further assists the subsequent decision.
Description
Technical Field
The invention belongs to the technical field of data information processing, and particularly relates to a dangerous waste tracing method based on matching degree and cross entropy.
Background
With the rapid development of society, the amount of waste and garbage brought by the society is increasing day by day, especially the amount of dangerous waste generated in industrial production is as high as 3 hundred million and more tons every year around the world. The hazardous waste generally has one or more hazardous characteristics of corrosivity, toxicity, inflammability, reactivity or infectivity, etc., waste organic solvents, distillation waste liquids, etc. generated in the chemical field, mother liquor, waste salts, etc. generated in the pesticide field, scum, oily sludge, etc. generated in the petroleum field, dust, smelting waste residues, etc. generated in the non-ferrous metal smelting field. The hazardous wastes not only are harmful to the health of people, but also cause long-term damage to the environment, so that the reasonable disposal and scientific management of the hazardous wastes are extremely important.
In the event of frequent solid waste dumping in recent years, particularly dangerous waste dumping, the rapid and accurate tracing and characteristic identification of the solid waste are great problems for the penalty identification and safe disposal of the event. However, the lack of rapid qualitative and accurate identification techniques for matching hazardous waste generating sources and generating characteristics greatly impedes the timely introduction of such focused dumping event comprehensive management schemes. Meanwhile, when the hazardous waste utilization and disposal unit receives the hazardous waste, due to the fact that the hazardous waste type accurate identification capacity is not enough, production safety accidents are easily caused, and risks of the hazardous waste disposal are easily caused. Therefore, the traceability technology and method for establishing the database and developing the unidentified solid wastes have great significance for hitting solid wastes to dump, maintaining the ecological environment safety and preventing and controlling the risks in the solid waste utilization and disposal process.
In addition, the technology for fine management of hazardous waste is weak, and therefore, it is urgently needed to provide a method for tracing the source of hazardous waste, which can obtain the estimated type and estimated characteristics of hazardous waste by using the relevant information of unknown waste in combination with a system for tracing the source of hazardous waste.
Disclosure of Invention
In order to solve the technical problem of difficulty in tracing the source of the hazardous waste in the prior art, the invention provides a hazardous waste tracing method based on matching degree and cross entropy.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a dangerous waste tracing method based on matching degree and cross entropy comprises the following steps:
s1, constructing a dangerous waste fingerprint characteristic database, wherein the database contains characteristic information of dangerous waste;
s2, a user inputs a corresponding retrieval index, and the database matches corresponding characteristic information according to the input retrieval index;
s3, after matching, similarity calculation is carried out according to the number of input retrieval indexes; when the number N of the retrieval indexes is 1, calculating the similarity by adopting a single index calculation model; when N is more than or equal to 2, calculating the similarity by adopting a multi-index calculation model;
and S4, displaying the tracing result according to the calculated similarity.
Further, the database comprises a plurality of rows of information and a plurality of columns of information, wherein each row represents a hazardous waste and each column represents a characteristic information.
Further, the characteristic information comprises industry classification, waste category, physical form, shape, magnetism, smell, color, apparent appearance, substance composition, characteristic index and numerical index.
Further, the single index calculation model is as follows:
wherein ,
And the similarity of the unknown waste and the known waste in the database is represented, and t represents the matching degree between the retrieval index used for inputting and the matched characteristic information.
Furthermore, the method for calculating the matching degree t comprises the following steps:
the k calculation method comprises the following steps:
the search index input by the user is set to
And the matched index is->
Then, then
，
。
Further, the calculating the similarity by using the multi-index calculation model comprises the following steps:
s301, judging the type of a retrieval index input by a user, and classifying according to a text type index and a numerical type index;
s302, setting the number of text type indexes to be N1 and the number of numerical type indexes to be N2; when N1 is 1, calculating the similarity of the text type index by adopting the single index calculation model, when N1 is more than or equal to 2, calculating the similarity of the text type index by adopting a cross entropy calculation model, and finally obtaining the similarity corresponding to the text type index
(ii) a When N2 is 1, the single-index calculation model meter is adopted for the numerical indexCalculating the similarity, when N2 is more than or equal to 2, calculating the similarity of the numerical index by adopting a cross entropy calculation model, and finally obtaining the similarity based on the numerical index>
；
S303, selecting similarity
and
The larger of these values is taken as the similarity of the unknown waste to the matching known waste.
Further, when the index is a plurality of numerical indexes, the numerical indexes of the input unknown waste are formed into a set Y = (Y) 1 ,y 2 , y 3 …y n ) The indexes of the known waste matched are formed into a set X = (X) 1 ,x 2 , x 3 …x n ) The probability distribution of the two data sets is calculated as q (y) = (q) separately 1 ,q 2 , q 3 …q n ) And p (x) = (p) 1 ,p 2 , p 3 …p n )，
Calculating the cross-entropy probability of unknown waste and known waste as
：
Wherein: i =1,2 … … n;
the calculation probability of the known waste index distribution entropy is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
furthermore, when the index is a plurality of text-type indexes, the text-type indexes are assigned,
forming a set B = (B) by using assigned text type indexes of unknown wastes 1 ,b 2 , b 3 …b n ) And performing assignment conversion on the matched indexes of the known wastes to form a set A = (a) 1 ,a 2 , a 3 …a n ) The probability distributions of the two data sets are calculated as r (b) = (r) respectively 1 ,r 2 , r 3 …r n ) And s (a) =(s) 1 ,s 2 , s 3 …s n )，
Calculating the cross-entropy probability of unknown waste and known waste as
：
Wherein: i =1,2 … … n;
the calculation probability of the known waste index distribution entropy is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
compared with the prior art, the invention has the following beneficial effects:
according to the method, a reasonable hazardous waste database is constructed, the database contains various characteristic information of hazardous waste, a user inputs corresponding retrieval conditions, and the database matches different models according to the retrieval indexes to calculate the similarity, so that not only can a quantitative matching result be given, but also the calculated amount can be reduced, the matching efficiency can be improved, and the database matching accuracy can be increased; the method is beneficial to the rapid identification of the waste, realizes the rapid tracing of the hazardous waste, and further assists the subsequent decision.
The method characterizes the matching result of the unknown waste and the waste database through the similarity, and is visual and effective.
Drawings
Fig. 1 is a schematic view of a tracing process according to the present invention.
Detailed Description
The technical solutions of the present invention will be described in detail with reference to the accompanying drawings, and it is obvious that the described embodiments are not all embodiments of the present invention, and all other embodiments obtained by those skilled in the art without any inventive work belong to the protection scope of the present invention.
The invention provides a dangerous waste tracing method based on matching degree and cross entropy, which comprises the following steps:
s1, constructing a dangerous waste fingerprint characteristic database, wherein the database contains characteristic information of dangerous waste; 1554 rows of information and 193 columns of information are included in the database, wherein each row represents one type of hazardous waste, namely 1554 types of hazardous waste are included in the database, and each column represents one piece of characteristic information. The characteristic information comprises industry classification, waste category, physical form, shape, magnetism, smell, color, apparent morphology, substance composition, characteristic index and numerical index. The numerical indexes comprise heavy metal content and the like, and the characteristic information further comprises a data source, a waste type, a solid waste name, a production link, waste description and the like.
S2, a user inputs a corresponding retrieval index, and the database matches corresponding characteristic information according to the input retrieval index;
the user can directly input the corresponding dangerous waste name, the dangerous waste name string is matched with the dangerous waste name in the database, the string with the most overlapped string is the retrieval result, and the retrieval result is displayed on the front-end page for the user to refer to.
When the name and the type of the dangerous waste are uncertain, the easily-obtained characteristic information of the dangerous waste can be obtained by utilizing the prior art and is used as a retrieval index for retrieval so as to estimate the most possible name and the type of the dangerous waste.
S3, after matching, similarity calculation is carried out according to the number of input retrieval indexes; when the number N of the retrieval indexes is 1, calculating the similarity by adopting a single index calculation model; when N is more than or equal to 2, calculating the similarity by adopting a multi-index calculation model; fig. 1 is a schematic flow chart of similarity calculation.
The single index calculation model is as follows:
wherein ,
and the similarity of the unknown waste and the known waste in the database is represented, and t represents the matching degree between the retrieval index used for inputting and the matched characteristic information.
The calculation method of the matching degree t comprises the following steps:
the k calculation method comprises the following steps:
the search index input by the user is set to
And the matched index is->
Then, then
，
。
If the input single index belongs to a text index, the single index cannot be directly used for similarity calculation, so that assignment conversion needs to be performed on the text index, when the text type is physical form, magnetism, smell and color, assignment conversion is performed according to table 1, and similarity calculation is performed after assignment conversion. The color indexes in table 1 may be added with assigned data of other different colors according to actual needs, which is not described herein.
TABLE 1 text type index assignment table
The similarity calculation by adopting the multi-index calculation model comprises the following steps:
s301, judging the type of a retrieval index input by a user, and classifying according to a text type index and a numerical type index;
s302, setting the number of text type indexes to be N1 and the number of numerical type indexes to be N2; when N1 is 1, calculating similarity of text type indexes by adopting the single index calculation modelAnd when N1 is more than or equal to 2, calculating the similarity of the text type indexes by adopting a cross entropy calculation model, and finally obtaining the similarity corresponding to the text type indexes
(ii) a When N2 is 1, calculating the similarity of the logarithmic value type index by adopting the single index calculation model, when N2 is more than or equal to 2, calculating the similarity of the logarithmic value type index by adopting a cross entropy calculation model, and finally obtaining the similarity (based on the strength and the strength) corresponding to the logarithmic value type index>
；
S303, selecting similarity
and
The larger of these values is taken as the similarity of the unknown waste to the matching known waste.
Further, when the index is a plurality of numerical indexes, the input numerical indexes of the unknown waste are formed into a set Y = (Y) 1 ,y 2 , y 3 …y n ) The indexes of the known waste matched are formed into a set X = (X) 1 ,x 2 , x 3 …x n ) The probability distribution of the two data sets is calculated as q (y) = (q) separately 1 ,q 2 , q 3 …q n ) And p (x) = (p) 1 ,p 2 , p 3 …p n )，
Calculating the cross-entropy probability of unknown waste and known waste as
：
Wherein: i =1,2 … … n;
the calculation probability of the distribution entropy of the known waste index is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
it should be noted that, in the process of matching the numerical indicators, different known wastes may be matched, where the known waste indicator dataset refers to a dataset of corresponding indicators of the same known waste, different similarities may be calculated for different matched known wastes, and finally a maximum value is selected to display a similarity result, and meanwhile, the similarity of each matched known waste may also be called.
Furthermore, when the retrieval index is a plurality of text type indexes, the text type indexes are assigned according to the table 1, and the text type indexes of the unknown waste after assignment form a set B = (B) 1 ,b 2 , b 3 …b n ) And assigning and converting indexes of the matched known wastes to form a set A = (a) 1 ,a 2 , a 3 …a n ) The probability distributions of the two data sets are calculated as r (b) = (r) respectively 1 ,r 2 , r 3 …r n ) And s (a) =(s) 1 ,s 2 , s 3 …s n )，
Calculating the cross-entropy probability of unknown waste and known waste as
：/>
Wherein: i =1,2 … … n;
the calculation probability of the known waste index distribution entropy is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
similarly, in the process of matching the text type indexes, different known wastes may be matched, the known waste index dataset refers to a dataset of corresponding indexes of the same known waste, for the different matched known wastes, different similarities can be calculated, and finally, the maximum value is selected to display the similarity result, and meanwhile, the similarity of each matched known waste can also be called.
The final similarity can be obtained according to the feature information and the similarity, and the rest feature information does not participate in the similarity calculation and is only used as information data.
And S4, displaying the tracing result according to the calculated similarity. Of course, the maximum value of the similarity can be selected to display the most possible waste information, and the tracing results can also be displayed according to the sequence of the similarity from large to small. The dangerous waste corresponding to the maximum similarity is the dangerous waste category to which the unknown waste most possibly belongs, and the possibility is gradually reduced along with the reduction of the similarity.
Examples
Taking aluminum ash as an example, the process of applying the hazardous waste tracing method in tracing unknown waste or similarity analysis is analyzed.
Basic characteristics of the aluminum ash: aluminum ash has an offensive odor (ammonia gas) and contains certain amounts of alumina, aluminum nitride and fluoride. Assuming that the indexes can represent the basic characteristics of the aluminum ash, namely pungent odor, the aluminum oxide, the aluminum nitride and the fluoride and the content distribution thereof are the fingerprint characteristics of the aluminum ash, and an aluminum ash fingerprint characteristic database is formed.
When only one index of unknown waste is known, such as pungent odor, the "pungent odor" in the aluminum ash database is the fingerprint feature of the aluminum ash, therefore,
=1; unknown waste likewise has an irritating odor, i.e. <' > i>
=1. Accordingly, is present>
，
Therefore, f (t) =1. That is, under the matching analysis condition of the index "pungent odor", the similarity of the unknown waste to the known waste is 100%.
When more than one unknown waste index is obtained, such as numerical indices of alumina content, aluminum nitride content and fluoride content, as shown in table 2, 50%, 40%, 9% and 2%, respectively, i.e., the set of unknown waste indices Y = (0.5,0.4, 0.09, 0.02), the main material content is normalized to construct the unknown waste index probability distribution q = (0.495,0.396, 0.089, 0.020).
According to the known aluminum ash fingerprint feature database, a known index set X = (0.56, 0.38, 0.10 and 0.03) is constructed by using the content mean value of the main substances of the aluminum ash, and the known index set of the aluminum ash is converted into a probability distribution p = (0.526, 0.356, 0.091 and 0.027) as shown in the following table.
Calculating the cross entropy of the probability distribution of the unknown waste index and the probability distribution of the known index, wherein H (p, q) =1.04, meanwhile, calculating the entropy of the probability distribution of the known aluminum ash index to be H (X) 1.01, and respectively calculating according to the relation between the information quantity and the probability
and
Calculating the degree of similarity between two wastes>
The content was 97.20%. The similarity of the unknown waste and the known waste (aluminum ash) reaches 97.20 percent; in addition, due to the fact that the similarity between the two wastes is high and the fact that the unknown wastes possibly come from the known wastes (aluminum ash) is indicated, the traceability work of the unknown wastes can be realized under the condition that the basic fingerprint database is sufficient.
Table 2 example of calculation of similarity of two waste numerical indicators based on cross entropy
When more than one unknown waste index is obtained, such as a plurality of text indexes: and color, smell, physical form and the like are assigned correspondingly according to the assignment condition of the text indexes in the database, and the similarity is calculated according to a multi-index cross entropy-based tracing method.
For example, the unknown waste is a solid waste with yellow color and pungent odor, and the matched known waste is a solid waste with gray color and pungent odor, and the calculation results are shown in table 3 according to the calculation method provided by the invention.
Table 3 example of calculation of similarity of text-based indicators for two wastes based on cross entropy
The similarity of the two wastes is calculated by cross entropy of the data distribution formed by assigning the texts, and according to the above example, the similarity of A and B is found to be 86.54%. It shows that the similarity probability of the unknown waste and the known waste is 86.54% under the conditions of gray color, smell and physical form, pungent smell and solid state respectively.
Although the present invention has been described in detail with reference to examples, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the scope of the present invention.
Claims (8)
1. A dangerous waste tracing method based on matching degree and cross entropy is characterized by comprising the following steps:
s1, constructing a dangerous waste fingerprint characteristic database, wherein the database contains characteristic information of dangerous waste;
s2, a user inputs a corresponding retrieval index, and the database matches corresponding characteristic information according to the input retrieval index;
s3, after matching, similarity calculation is carried out according to the number of input retrieval indexes; when the number N of the retrieval indexes is 1, calculating the similarity by adopting a single index calculation model; when N is more than or equal to 2, calculating the similarity by adopting a multi-index calculation model;
and S4, displaying the tracing result according to the calculated similarity.
2. The hazardous waste tracing method of claim 1, wherein the database comprises a plurality of rows of information and a plurality of columns of information, wherein each row represents a hazardous waste and each column represents a characteristic information.
3. The hazardous waste tracing method of claim 2, wherein the characteristic information comprises industry classification, waste category, physical form, shape, magnetism, smell, color, apparent morphology, material composition, characteristic index, numerical index.
4. The hazardous waste tracing method of claim 1, wherein the single index calculation model is:
wherein ,
representing the similarity of the unknown waste and the known waste in the database, and t representing the matching degree between the retrieval index used for inputting and the matched characteristic information.
5. The hazardous waste traceability method of claim 4, wherein the matching degree t is calculated by:
the k calculation method comprises the following steps:
the search index input by the user is set to
And the matched index is->
Then, then
，
。
6. The hazardous waste traceability method of claim 1, wherein the calculating the similarity using the multi-index computational model comprises:
s301, judging the type of a retrieval index input by a user, and classifying according to a text type index and a numerical type index;
s302, setting the number of text type indexes to be N1 and the number of numerical type indexes to be N2; when N1 is 1, calculating the similarity of the text type index by adopting the single index calculation model, when N1 is more than or equal to 2, calculating the similarity of the text type index by adopting a cross entropy calculation model, and finally obtaining the similarity corresponding to the text type index
(ii) a When N2 is 1, calculating the similarity of the logarithmic value type index by adopting the single index calculation model, when N2 is more than or equal to 2, calculating the similarity of the logarithmic value type index by adopting a cross entropy calculation model, and finally obtaining the similarity (based on the strength and the strength) corresponding to the logarithmic value type index>
；
S303, selecting similarity
and
The larger of these values is taken as the similarity of the unknown waste to the matching known waste.
7. The hazardous waste tracing method of claim 6, wherein the retrieval index is a plurality of indicesWhen the numerical indexes are input, the numerical indexes of the unknown waste are formed into a set Y = (Y) 1 ,y 2 , y 3 …y n ) The indexes of the matched known wastes form a set X = (X) 1 ,x 2 , x 3 …x n ) The probability distribution of the two data sets is calculated as q (y) = (q) separately 1 ,q 2 , q 3 …q n ) And p (x) = (p) 1 ,p 2 , p 3 …p n )，
Calculating the cross-entropy probability of unknown waste and known waste as
：/>
Wherein: i =1,2 … … n;
the calculation probability of the known waste index distribution entropy is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
8. the hazardous waste traceability method of claim 6, wherein when the retrieval index is a plurality of text-based indices, the text-based indices are assigned values,
forming a set B = (B) by using assigned text type indexes of unknown wastes 1 ,b 2 , b 3 …b n ) And performing assignment conversion on the matched indexes of the known wastes to form a set A = (a) 1 ,a 2 , a 3 …a n ) The probability distributions of the two data sets are calculated as r (b) = (r) respectively 1 ,r 2 , r 3 …r n ) And s (a) =(s) 1 ,s 2 , s 3 …s n )，
Calculating the cross-entropy probability of the unknown waste and the known waste as
：
Wherein: i =1,2 … … n;
the calculation probability of the distribution entropy of the known waste index is
：
Then, the similarity of the unknown waste to the known waste
Comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139981.7A CN115860769B (en) | 2023-02-21 | 2023-02-21 | Dangerous waste tracing method based on matching degree and cross entropy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139981.7A CN115860769B (en) | 2023-02-21 | 2023-02-21 | Dangerous waste tracing method based on matching degree and cross entropy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115860769A true CN115860769A (en) | 2023-03-28 |
| CN115860769B CN115860769B (en) | 2023-05-05 |
Family
ID=85658525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310139981.7A Active CN115860769B (en) | 2023-02-21 | 2023-02-21 | Dangerous waste tracing method based on matching degree and cross entropy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860769B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000155681A (en) * | 1998-11-24 | 2000-06-06 | Fujitsu Ltd | Predicting device performing prediction based on analogous example and method |
| CN111291069A (en) * | 2018-12-07 | 2020-06-16 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
| CN113361263A (en) * | 2021-06-04 | 2021-09-07 | 中国人民解放军战略支援部队信息工程大学 | Character entity attribute alignment method and system based on attribute value distribution |
| CN115776401A (en) * | 2022-11-23 | 2023-03-10 | 中国人民解放军国防科技大学 | Method and device for tracing network attack event based on few-sample learning |
-
2023
- 2023-02-21 CN CN202310139981.7A patent/CN115860769B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000155681A (en) * | 1998-11-24 | 2000-06-06 | Fujitsu Ltd | Predicting device performing prediction based on analogous example and method |
| CN111291069A (en) * | 2018-12-07 | 2020-06-16 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
| CN113361263A (en) * | 2021-06-04 | 2021-09-07 | 中国人民解放军战略支援部队信息工程大学 | Character entity attribute alignment method and system based on attribute value distribution |
| CN115776401A (en) * | 2022-11-23 | 2023-03-10 | 中国人民解放军国防科技大学 | Method and device for tracing network attack event based on few-sample learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115860769B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110471948B (en) | Intelligent customs clearance commodity classification method based on historical data mining | |
| Tixier et al. | Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports | |
| Karakaya et al. | Social sciences and the mining sector: Some insights into recent research trends | |
| Stefanović et al. | A comparison of the analytic hierarchy process and the analysis and synthesis of parameters under information deficiency method for assessing the sustainability of waste management scenarios | |
| CN111950932A (en) | Multi-source information fusion-based comprehensive quality portrait method for small and medium-sized micro enterprises | |
| Vegera et al. | Information support of the circular economy: the objects of accounting at recycling technological cycle stages of industrial waste | |
| Wernick et al. | Industrial ecology: Some directions for research | |
| CN111950922B (en) | Equipment economic data evaluation method based on multi-source data interaction analysis | |
| Cecere et al. | Drivers of knowledge accumulation in electronic waste management: An analysis of publication data | |
| CN111400446A (en) | Standard text duplicate checking method and system | |
| Khan et al. | Mapping and visualizing of research output on waste management and green technology: a bibliometric review of literature | |
| Lancho-Barrantes et al. | The iceberg hypothesis revisited | |
| Aitimbetova et al. | Environmental Assessment of Solid Waste Pollution of Urban Areas (on the example of Shymkent, Republic of Kazakhstan) | |
| CN116089825B (en) | Solid waste fingerprint feature extraction method based on statistical entropy | |
| CN115860769B (en) | Dangerous waste tracing method based on matching degree and cross entropy | |
| CN115392939B (en) | Hazardous waste tracing method based on retrieval comparison and matching degree calculation | |
| CN116029262A (en) | Legal and legal code generation method, database construction method and device | |
| CN113570250B (en) | Multi-objective comprehensive evaluation method for full life cycle of transformer temperature measuring device | |
| CN115563292A (en) | Dangerous waste directory knowledge graph establishing method and device | |
| Salem et al. | An integrated approach to assess manufacturing greenness level | |
| Derevyanov et al. | Application of data envelopment analysis for multi-criteria evaluation of system for technogenic waste recycling in oil refining industry | |
| JP3227965B2 (en) | Workability evaluation method and workability evaluation device | |
| CN113127647A (en) | Big data analysis-based process knowledge base construction method | |
| Zainon et al. | The Assessment of Waste Segregation Exercise Among Malaysian Contractors: A Descriptive Analysis | |
| Yang et al. | Similarity model by matching and cross entropy-driven methods to support tracing source of unknown waste |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |