CN109739950B - Method and device for screening applicable legal provision - Google Patents
Method and device for screening applicable legal provision Download PDFInfo
- Publication number
- CN109739950B CN109739950B CN201811589269.2A CN201811589269A CN109739950B CN 109739950 B CN109739950 B CN 109739950B CN 201811589269 A CN201811589269 A CN 201811589269A CN 109739950 B CN109739950 B CN 109739950B
- Authority
- CN
- China
- Prior art keywords
- legal
- analyzed
- case description
- description text
- noise
- 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.)
- Active
Links
Images
Landscapes
- Machine Translation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for screening applicable legal provisions, wherein, noise in case description texts to be analyzed is filtered; then, determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered; and finally, screening applicable legal provisions for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the composition requirement conformance condition, the law violation condition and the liability condition matched with each legal provision. The constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept. The technical scheme meets the purpose of reasoning and applying from case description to legal provisions, can determine the corresponding legal concepts based on the case description text to be analyzed, and then screens the applicable legal provisions based on the determined legal concepts, thereby solving the defect that the screened legal provisions in the prior art are not accurate enough.
Description
Technical Field
The invention relates to the field of laws and calculation, in particular to a method and a device for screening applicable legal provisions.
Background
Currently, the laws are of a wide variety, with each legal provision being of a large number. In the case auditing process, suitable legal provisions need to be screened from a great number of legal provisions, and the defects of low efficiency and large workload exist.
In the prior art, the functions of searching legal provisions and searching target legal provisions based on text similarity or keywords are realized. However, the legal provision screening with only the search function cannot satisfy the purpose of applying from case description to legal provision reasoning, and there is a logical lack of function. The method for retrieving the target legal provision based on the similarity of the keywords or the texts cannot understand the legal concept in the case description text, and when the description text has character deviation, the applicable provision is wrongly deduced due to the problem of the case description text, namely, the legal theory is not used as a support, so that logic errors are easy to occur.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a method and a device for screening applicable legal provisions, which overcome the defect that the applicable legal provisions cannot be screened for case description texts to be analyzed.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for screening applicable legal provisions, including:
filtering noise in case description texts to be analyzed;
determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered;
screening applicable legal provisions for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the constituent requirement conformance conditions, the illegal conditions and the liability conditions matched with each legal provision; wherein, the constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept.
In a possible implementation manner, the filtering out noise in the case description text to be analyzed includes:
filtering noise from the case description text to be analyzed by using a preset noise database; wherein the noise database comprises at least one noisy text.
In one possible embodiment, the method of screening applicable legal provisions further comprises the step of building the noise database:
acquiring a plurality of case description texts of each preset type of cases in a plurality of preset types of cases;
for each preset type case, performing word segmentation processing on each case description text corresponding to the preset type case to obtain word segmentation phrases corresponding to the preset type case; wherein, the word-dividing phrase at least comprises a vocabulary;
and calculating the intersection of word segmentation phrases corresponding to the multiple preset types of cases to obtain the noise database.
In a possible implementation manner, the determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after the noise is filtered out includes:
performing word segmentation processing on the case description text to be analyzed after the noise is filtered out to obtain a plurality of words of the case description text to be analyzed after the noise is filtered out;
determining legal concepts corresponding to each vocabulary of the case description text to be analyzed after noise is filtered based on the deep neural network model; the deep neural network model comprises a plurality of vocabularies and legal concepts corresponding to each vocabulary.
In one possible embodiment, the method for screening applicable legal provisions further includes the step of building the deep neural network model:
acquiring a plurality of case description texts belonging to the same preset type of case as the case description text to be analyzed to obtain a plurality of sample case description texts;
acquiring legal concepts corresponding to each vocabulary in each sample case description text;
and establishing a corresponding relation between each vocabulary in each sample case description text and the corresponding legal concept.
In one possible embodiment, the method of screening for applicable legal provisions further comprises:
when there are a plurality of words corresponding to the same legal concept, the words corresponding to the legal concept are sorted based on the word frequency of each word.
In one possible embodiment, the method of screening for applicable legal provisions further comprises:
and setting corresponding codes for each vocabulary in each sample case description text.
In one possible implementation, the activation function of the deep neural network model is a Sigmoid function:
f(x)＝(wx-θ)
in the formula, w represents a link weight value of a previous neuron and a next neuron, theta represents an activation threshold value, x represents a vocabulary in the case description text to be analyzed, and f (x) is a legal concept corresponding to the vocabulary in the case description text to be analyzed.
In a possible implementation manner, in the case that the constituent requirement conformity condition includes a plurality of legal concepts, the legal concepts have a first preset logical relationship therebetween;
under the condition that the law violation condition comprises a plurality of legal concepts, each legal concept has a second preset logical relationship;
in the case that the liability condition comprises a plurality of legal concepts, each legal concept has a third preset logical relationship.
In a second aspect, an embodiment of the present application provides an apparatus for screening applicable legal provisions, including:
the drying module is used for filtering noise in the case description text to be analyzed;
the concept determining module is used for determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered;
the clause screening module is used for screening applicable legal clauses for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and composition requirement conformity conditions, illegal conditions and liability conditions matched with each legal clause; wherein, the constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept.
(III) advantageous effects
The embodiment of the invention provides a method and a device for screening applicable legal provisions. The method has the following beneficial effects:
the embodiment of the invention firstly filters the noise in the case description text to be analyzed; then, determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered; and finally, screening applicable legal provisions for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the composition requirement conformance condition, the law violation condition and the liability condition matched with each legal provision. The constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept. The technical scheme meets the purpose of reasoning application from case description to legal provision, can determine the corresponding legal concept based on the case description text to be analyzed, and then screens the applicable legal provision based on the determined legal concept, thereby solving the defect that the screening of the legal provision in the prior art is not accurate enough.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 schematically illustrates a flow chart of a method of screening applicable legal provisions, in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart schematically illustrating the modeling of a deep neural network according to another embodiment of the present invention;
FIG. 3 is a block diagram schematically illustrating an apparatus for screening applicable legal provisions according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the embodiment of the present application provides a method for screening applicable legal provisions, which satisfies the purpose of applying from case description to legal provision reasoning, can determine corresponding legal concepts based on a case description text to be analyzed, and then screen applicable legal provisions based on the determined legal concepts, thereby solving the defect in the prior art that the screened legal provisions are not accurate enough. Specifically, the method for screening applicable legal provisions comprises the following steps:
and S110, filtering noise in the case description text to be analyzed.
Here, the following steps are specifically used to filter out noise: filtering noise from the case description text to be analyzed by using a preset noise database; wherein the noise database comprises at least one noisy text.
In particular implementation, the noise database may be established by:
s1101, obtaining a plurality of case description texts of each preset type of cases in the plurality of preset types of cases.
The preset cases are administrative cases, criminal cases, civil cases or business cases and the like.
S1102, aiming at each preset type case, performing word segmentation processing on each case description text corresponding to the preset type case to obtain word segmentation phrases corresponding to the preset type case; wherein, the word-dividing phrase at least comprises a vocabulary.
The word-separating phrase is a word set.
S1103, calculating the intersection of word segmentation phrases corresponding to the multiple preset cases to obtain the noise database.
And S120, determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after the noise is filtered.
In particular implementation, the legal concepts corresponding to each word can be determined by the following steps:
s1201, performing word segmentation processing on the case description text to be analyzed after the noise is filtered out to obtain a plurality of words of the case description text to be analyzed after the noise is filtered out.
A1202, determining legal concepts corresponding to each vocabulary of the case description text to be analyzed after noise is filtered based on a deep neural network model; the deep neural network model comprises a plurality of vocabularies and legal concepts corresponding to each vocabulary.
This step enables mapping from vocabulary to legal concepts.
S130, screening applicable legal provisions for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the constituent requirement conformance conditions, the illegal conditions and the liability conditions matched with each legal provision; wherein, the constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept.
As shown in fig. 2, in some embodiments, the method for screening applicable legal provisions further includes the step of establishing the deep neural network model:
s210, obtaining a plurality of case description texts belonging to the same preset type of cases as the case description text to be analyzed, and obtaining a plurality of sample case description texts.
And S220, acquiring legal concepts corresponding to each vocabulary in each sample case description text.
Before this step is performed, a process of segmenting each sample case description text into words needs to be performed.
And S230, establishing a corresponding relation between each vocabulary in each sample case description text and the corresponding legal concept.
According to the legal theory corresponding to the case of which the case description text to be analyzed belongs to the same preset type, the sentences in the corresponding case description text are marked out, and the segmented words are matched with the listed corresponding legal concepts one by one.
In a specific implementation, a corresponding code may be set for each vocabulary in each sample case description text. The legal concepts and corresponding description words are combined into an array, such as: "intentional" -the vocabulary describing "intentional", the coding set:
U＝(11,12,13,1x,......)
u is the x value of the training data and the test data, and belongs to the legal concept descriptor, wherein y is 0/1, the x value belongs to the legal concept descriptor, and is 1, otherwise, the x value is 0.
In the specific implementation, when a plurality of words corresponding to the same legal concept are provided, the words corresponding to the legal concept are sorted based on the word frequency of each word.
The activation function of the deep neural network model is a Sigmoid function:
f(x)＝(wx-θ)
in the formula, w represents a link weight value of a previous neuron and a next neuron, theta represents an activation threshold value, x represents a vocabulary in the case description text to be analyzed, and f (x) is a legal concept corresponding to the vocabulary in the case description text to be analyzed.
The deep neural network is a 7-layer BP application network. The neural network is trained by using training data and tested by using test data, and the accuracy of the applied network determined by testing on legal concepts exceeds 98%.
In some embodiments, in a case where the constituent requirement conformity condition includes a plurality of legal concepts, there is a first preset logical relationship between the respective legal concepts.
And in the case that the law violation condition comprises a plurality of legal concepts, the legal concepts have a second preset logical relationship.
In the case that the liability condition comprises a plurality of legal concepts, each legal concept has a third preset logical relationship.
The preset logical relationship may refer to, for example, an or, and, or the like relationship between two legal concepts. For example, legal concept a is met, and legal concept b. The illegal conditions and the responsible conditions are judged by a similar method. If the logical operations of the three conditions are all judged to be yes, a similar conclusion is generated: "this case description applies to xx items xx criminal names".
In the above embodiment, the noise database is calculated by using the case situation description text participle and vocabulary set intersection solving methods of different types. And the case situation text and the corresponding legal concepts are changed into a digital set by adopting the one-to-one correspondence of the legal concepts and the vocabularies and the coding arrangement. The above embodiment designs the logical operation rule according to the law theory to judge the applicable law provisions of case situation.
The embodiment perfects the defect that the conventional legal provision retrieval lacks functions suitable for cases description, legal concept abstract analysis and legal provision reasoning. The defect that the conventional legal provision reasoning applicable method lacks of legal theory support is overcome. By adopting the deep neural network technology, the defects of low efficiency and high error rate in the traditional keyword retrieval matching method are improved.
The embodiment discloses an artificial intelligence method for law concept understanding and law provision application based on Chinese natural language processing technology, deep neural network technology and law theory, and achieves the purposes of case description, law concept understanding, law provision automatic reasoning and application.
As shown in fig. 3, the embodiment of the present application further discloses an apparatus for screening applicable legal provisions, which includes:
the drying module 301 is used for filtering out noise in case description texts to be analyzed;
a concept determining module 302, configured to determine legal concepts corresponding to each vocabulary in the scenario description text to be analyzed after the noise is filtered;
the clause screening module 303 is used for screening applicable legal clauses for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the constituent requirement conformance conditions, the illegal conditions and the liability conditions matched with each legal clause; wherein, the constituent requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept.
Each step in the method of the embodiment of the present invention corresponds to a step in the process of screening the applicable legal provision by the apparatus of the embodiment of the present invention, and each step in the process of screening the applicable legal provision by the apparatus of the embodiment of the present invention is included in the method of the embodiment of the present invention, and therefore, repeated parts are not described herein again.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; 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 (6)
1. A method for screening applicable criminal case law provisions, comprising:
filtering noise in case description texts to be analyzed;
determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered;
screening applicable legal provisions for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and the constituent requirement conformance conditions, the illegal conditions and the liability conditions matched with each legal provision; wherein, the formation requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept; the filtering of noise in case description text to be analyzed includes:
filtering noise from the case description text to be analyzed by using a preset noise database; wherein the noise database comprises at least one noise text;
further comprising the step of building said noise database:
acquiring a plurality of case description texts of each preset type of cases in a plurality of preset types of cases;
for each preset type case, performing word segmentation processing on each case description text corresponding to the preset type case to obtain word segmentation phrases corresponding to the preset type case; wherein, the word-dividing phrase at least comprises a vocabulary;
calculating the intersection of word segmentation phrases corresponding to the multiple preset types of cases to obtain the noise database;
under the condition that the constituent requirement conformity condition comprises a plurality of legal concepts, a first preset logical relationship exists between the legal concepts;
under the condition that the law violation condition comprises a plurality of legal concepts, each legal concept has a second preset logical relationship;
in the case that the liability condition comprises a plurality of legal concepts, each legal concept has a third preset logical relationship;
the determining the legal concept corresponding to each vocabulary in the case description text to be analyzed after the noise is filtered comprises the following steps:
performing word segmentation processing on the case description text to be analyzed after the noise is filtered out to obtain a plurality of words of the case description text to be analyzed after the noise is filtered out;
determining legal concepts corresponding to each vocabulary of the case description text to be analyzed after noise is filtered based on the deep neural network model; the deep neural network model comprises a plurality of vocabularies and legal concepts corresponding to each vocabulary.
2. The method of claim 1, further comprising the step of building the deep neural network model by:
acquiring a plurality of case description texts belonging to the same preset type of case as the case description text to be analyzed to obtain a plurality of sample case description texts;
acquiring legal concepts corresponding to each vocabulary in each sample case description text;
and establishing a corresponding relation between each vocabulary in each sample case description text and the corresponding legal concept.
3. The method of claim 1, further comprising:
when there are a plurality of words corresponding to the same legal concept, the words corresponding to the legal concept are sorted based on the word frequency of each word.
4. The method of claim 3, further comprising:
and setting corresponding codes for each vocabulary in each sample case description text.
5. The method of claim 4, wherein the deep neural network model has an activation function Sigmoid function:
f(x)＝(wx-θ)
in the formula, w represents a link weight value of a previous neuron and a next neuron, theta represents an activation threshold value, x represents a vocabulary in the case description text to be analyzed, and f (x) is a legal concept corresponding to the vocabulary in the case description text to be analyzed.
6. A device for screening applicable criminal case law provisions, comprising:
the drying module is used for filtering noise in the case description text to be analyzed;
the concept determining module is used for determining legal concepts corresponding to each vocabulary in the case description text to be analyzed after noise is filtered;
the clause screening module is used for screening applicable legal clauses for the case description text to be analyzed based on a plurality of legal concepts corresponding to the case description text to be analyzed and composition requirement conformity conditions, illegal conditions and liability conditions matched with each legal clause; wherein, the formation requirement conformity condition, the unlawful condition and the liability condition at least comprise one legal concept;
when the noise in the case description text to be analyzed is filtered out by the dryness removal module, the dryness removal module comprises the following steps:
filtering noise from the case description text to be analyzed by using a preset noise database; wherein the noise database comprises at least one noise text;
the above apparatus is further configured to build a noise database:
acquiring a plurality of case description texts of each preset type of cases in a plurality of preset types of cases;
for each preset type case, performing word segmentation processing on each case description text corresponding to the preset type case to obtain word segmentation phrases corresponding to the preset type case; wherein, the word-dividing phrase at least comprises a vocabulary;
calculating the intersection of word segmentation phrases corresponding to the multiple preset types of cases to obtain the noise database;
under the condition that the constituent requirement conformity condition comprises a plurality of legal concepts, a first preset logical relationship exists between the legal concepts;
under the condition that the law violation condition comprises a plurality of legal concepts, each legal concept has a second preset logical relationship;
in the case that the liability condition comprises a plurality of legal concepts, each legal concept has a third preset logical relationship;
the determining the legal concept corresponding to each vocabulary in the case description text to be analyzed after the noise is filtered comprises the following steps:
performing word segmentation processing on the case description text to be analyzed after the noise is filtered out to obtain a plurality of words of the case description text to be analyzed after the noise is filtered out;
determining legal concepts corresponding to each vocabulary of the case description text to be analyzed after noise is filtered based on the deep neural network model; the deep neural network model comprises a plurality of vocabularies and legal concepts corresponding to each vocabulary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589269.2A CN109739950B (en) | 2018-12-25 | 2018-12-25 | Method and device for screening applicable legal provision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589269.2A CN109739950B (en) | 2018-12-25 | 2018-12-25 | Method and device for screening applicable legal provision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109739950A CN109739950A (en) | 2019-05-10 |
| CN109739950B true CN109739950B (en) | 2020-03-31 |
Family
ID=66359786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811589269.2A Active CN109739950B (en) | 2018-12-25 | 2018-12-25 | Method and device for screening applicable legal provision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109739950B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524043A (en) * | 2020-04-24 | 2020-08-11 | 南京擎盾信息科技有限公司 | Method and device for automatically generating litigation risk assessment questionnaire |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4713870B2 (en) * | 2004-10-13 | 2011-06-29 | ヒューレット−パッカード デベロップメント カンパニー エル．ピー． | Document classification apparatus, method, and program |
| CN107798033B (en) * | 2017-03-01 | 2021-07-02 | 中南大学 | Case text classification method in public security field |
| CN107229693B (en) * | 2017-05-22 | 2018-05-01 | 哈工大大数据产业有限公司 | The method and system of big data system configuration parameter tuning based on deep learning |
| CN107622182B (en) * | 2017-08-04 | 2020-10-09 | 中南大学 | Method and system for predicting local structural features of protein |
| CN107818138B (en) * | 2017-09-28 | 2020-05-19 | 银江股份有限公司 | Case law regulation recommendation method and system |
| CN108763484A (en) * | 2018-05-25 | 2018-11-06 | 南京大学 | A kind of law article recommendation method based on LDA topic models |
-
2018
- 2018-12-25 CN CN201811589269.2A patent/CN109739950B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109739950A (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256074B (en) | Verification processing method and device, electronic equipment and storage medium | |
| CN109726120B (en) | Software defect confirmation method based on machine learning | |
| CN109783639B (en) | Mediated case intelligent dispatching method and system based on feature extraction | |
| CN110597735A (en) | Software defect prediction method for open-source software defect feature deep learning | |
| CN106156083A (en) | A kind of domain knowledge processing method and processing device | |
| CN110689368B (en) | Method for designing advertisement click rate prediction system in mobile application | |
| CN107180084A (en) | Word library updating method and device | |
| CN111210842A (en) | Voice quality inspection method, device, terminal and computer readable storage medium | |
| CN109598307A (en) | Data screening method, apparatus, server and storage medium | |
| CN112199602B (en) | Post recommendation method, recommendation platform and server | |
| CN103246655A (en) | Text categorizing method, device and system | |
| JP7128919B2 (en) | Skill term evaluation method and device, electronic device, computer readable medium | |
| CN106528527A (en) | Identification method and identification system for out of vocabularies | |
| CN113590764A (en) | Training sample construction method and device, electronic equipment and storage medium | |
| CN111045902A (en) | Pressure testing method and device for server | |
| CN111338692A (en) | Vulnerability classification method and device based on vulnerability codes and electronic equipment | |
| CN111860981A (en) | Enterprise national industry category prediction method and system based on LSTM deep learning | |
| CN111680506A (en) | External key mapping method and device of database table, electronic equipment and storage medium | |
| CN113742733A (en) | Reading understanding vulnerability event trigger word extraction and vulnerability type identification method and device | |
| CN110413997B (en) | New word discovery method, system and readable storage medium for power industry | |
| CN109739950B (en) | Method and device for screening applicable legal provision | |
| CN111190973A (en) | Method, device, equipment and storage medium for classifying statement forms | |
| CN107480126B (en) | Intelligent identification method for engineering material category | |
| CN111898034A (en) | News content pushing method and device, storage medium and computer equipment | |
| CN117390198A (en) | Method, device, equipment and medium for constructing scientific and technological knowledge graph in electric power field |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220415 Address after: 266000 room 504, floor 5, building a, Shinan Software Park, No. 288, Ningxia road, Shinan District, Qingdao, Shandong Province Patentee after: Shandong Xinfa Technology Co.,Ltd. Address before: 102299 No. 27, Fuxue Road, Changping District, Beijing Patentee before: CHINA University OF POLITICAL SCIENCE AND LAW |
|
| TR01 | Transfer of patent right |