CN110674970A - Enterprise legal risk early warning method, device, equipment and readable storage medium - Google Patents
Enterprise legal risk early warning method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN110674970A CN110674970A CN201910765791.XA CN201910765791A CN110674970A CN 110674970 A CN110674970 A CN 110674970A CN 201910765791 A CN201910765791 A CN 201910765791A CN 110674970 A CN110674970 A CN 110674970A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- data
- early warning
- legal
- risk early
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012549 training Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 42
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000003058 natural language processing Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000007812 deficiency Effects 0.000 abstract description 2
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an enterprise legal risk early warning method, a device, equipment and a readable storage medium, wherein the method comprises the following steps: establishing an enterprise legal affair question bank according to the referee data; constructing an enterprise portrait system according to enterprise data; constructing an enterprise public opinion information map according to the enterprise public opinion data; and training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result. The embodiment of the invention can realize all dimensional information of an enterprise in the using process, capture the whole amount and automatically acquire legal risk information related to the enterprise possibly; potential legal risks which may exist can be intelligently excavated, and the deficiency of artificial subjective evaluation is supplemented for the objective evaluation of the overall risk; modeling can be performed aiming at all industries, and legal risks possibly encountered by enterprises can be deeply excavated.
Description
Technical Field
The invention relates to the technical field of enterprise legal risk early warning intelligent processing based on big data, in particular to an enterprise legal risk early warning method, device, equipment and readable storage medium.
Background
At present, for legal work of an enterprise, staff often collect contents possibly having legal risk points in a manual collection mode, and then judge one by one, and related legal classifications can be classified according to the following two dimensions under a general condition:
firstly, the method comprises the following steps: other companies, groups, individuals, etc., and corporate principals may present legal risks and problems;
secondly, the method comprises the following steps: at this stage, the company may encounter legal risks and problems.
Above-mentioned working method and work content because the information source is artifical screening, lead to whole information coverage low, the dimension is less to individual subjectivity is big, leaves over key information easily, often leads to final evaluation timeliness of legal risk low and the result is not accurate enough.
Based on the situation, it is necessary to design a legal risk early warning system with artificial intelligence capability and automation capability to solve the above problems.
Disclosure of Invention
The embodiment of the invention aims to provide an enterprise legal risk early warning method, device and equipment and a readable storage medium. In the use process, the embodiment of the invention can predict the enterprise legal affair risk by constructing an enterprise legal affair question bank and an enterprise portrait, constructing a map according to public opinion information and deeply learning a model.
In order to solve the technical problem, the embodiment of the invention adopts the following technical scheme:
the enterprise legal risk early warning method comprises the following steps:
establishing an enterprise legal affair question bank according to the referee data;
constructing an enterprise portrait system according to enterprise data;
constructing an enterprise public opinion information map according to the enterprise public opinion data;
and training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
Optionally, the constructing an enterprise legal issue database according to the referee data includes: and carrying out industry classification according to the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data and on the basis of the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data, and constructing an enterprise legal affairs problem library.
Optionally, the constructing an enterprise representation system according to enterprise data includes: and constructing an enterprise representation system according to the business data and/or the industrial and commercial data and/or the tax data and/or the intellectual property data of each enterprise.
Optionally, the constructing of the enterprise public opinion information map according to the enterprise public opinion data includes: and constructing the public opinion information map of the enterprise according to the Internet public data and/or publication public data of each enterprise.
Optionally, the process of constructing the enterprise public opinion information map according to the enterprise public opinion data is as follows:
text mining is carried out on Internet public data and publication public data by using a natural language processing method, and names of individuals, units and/or other social organizations in the text are extracted as entities in a map;
whether the same data appear among the entities is defined as whether the entities are related, and the probability of the same data appearing is used as the weight of the relation, so that the entity relation extraction is realized;
generating a feature vector for each of the entities; and if necessary, judging the similarity degree between the entities by comparing the Euclidean distances between the characteristic vectors.
Optionally, the method for training the enterprise legal affair risk early warning model according to the enterprise legal affair question bank, the enterprise portrait system and the enterprise public opinion information map, and generating a risk early warning result includes: and modeling the data of at least one enterprise similar to the target enterprise within a preset time by using a deep learning algorithm according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map, and predicting the legal risk of the target enterprise.
Optionally, the enterprise legal affair risk early warning model is trained according to the enterprise legal affair question bank, the enterprise portrait system and the enterprise public opinion information map, and the process of generating the risk early warning result is as follows:
an algorithm input stage, comprising: inputting a feature vector sequence with the length of m as an input feature of an algorithm;
an algorithm training phase comprising: taking the two-dimensional matrix sequence data of m x n as training data of an algorithm, extracting features of the sequence data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and reducing the dimensions of the k-dimensional feature vector through a deep neural network to generate a low-dimensional feature vector; then calculating the probability of the sequence data belonging to each category, finally comparing the probability distribution output by the algorithm with the real probability distribution, and updating parameters by reverse conduction iteration of errors;
an algorithmic prediction phase comprising: taking a sequence data sequence of the latest n days of an enterprise and a data feature vector of each day as prediction data of an input model, extracting features of the prediction data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and generating a low-dimensional feature vector after the k-dimensional feature vector is subjected to dimension reduction through a deep neural network; and then calculating the probability of possibly facing each legal risk, wherein the legal risk category with the highest probability is used as a risk early warning result output by the model.
The embodiment of the invention also provides an enterprise legal risk early warning device, which comprises:
the enterprise legal question bank generating module is used for constructing an enterprise legal question bank according to the judge data;
the enterprise portrait system generation module is used for constructing an enterprise portrait system according to enterprise data;
the enterprise public opinion information map generation module is used for constructing an enterprise public opinion information map according to enterprise public opinion data;
and the enterprise legal risk early warning model training module is used for training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
The embodiment of the invention also provides enterprise legal risk early warning equipment, which comprises:
a memory for storing a computer program;
and the processor is used for realizing the steps of the enterprise legal risk early warning method when the computer program is executed.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the enterprise legal risk early warning method are realized.
The embodiment of the invention provides an enterprise legal risk early warning method, device and equipment and a readable storage medium. The method can realize all-dimensional information of the enterprise, capture the whole quantity and automatically acquire legal risk information possibly related to the enterprise; potential legal risks which may exist can be intelligently excavated, and the deficiency of artificial subjective evaluation is supplemented for the objective evaluation of the overall risk; modeling can be performed aiming at all industries, and legal risks possibly encountered by enterprises can be deeply excavated.
Drawings
In order to more clearly illustrate the technical solution in the present embodiment, the drawings used in the prior art and the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for a person skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an enterprise legal risk early warning method according to an embodiment of the present invention.
Fig. 2 is a schematic algorithm flow diagram of an enterprise legal risk early warning method according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an enterprise legal risk early warning device according to an embodiment of the present invention.
Detailed Description
All of the features disclosed in this specification, or all of the steps in any method or process so disclosed, may be combined in any combination, except combinations of features and/or steps that are mutually exclusive.
Any feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
The following detailed description of embodiments of the invention refers to the accompanying drawings and examples.
Referring to fig. 1, fig. 1 is a schematic flow chart of an enterprise legal risk early warning method according to an embodiment of the present invention.
The method comprises the following steps:
s11: and establishing an enterprise legal affairs question bank according to the referee data.
Specifically, the method for constructing the enterprise legal affairs question bank according to the referee data comprises the following steps: and carrying out industry classification according to the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data and on the basis of the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data, and constructing an enterprise legal affairs problem library.
The data source is the official or official document information of the administrative officials, judicial officials or all mediation institutions for nearly ten years.
In order to accurately or comprehensively cover the referee data information, all of the administrative referee authorities, judicial referee authorities, or mediation mechanisms may be selected, or one or more of them may be selected as necessary. And, the time of disclosure of the official or mediation document information may be selected to be nearly ten years or earlier, or less than ten years.
S12: and constructing an enterprise portrait system according to the enterprise data.
Specifically, the method for constructing the enterprise representation system according to the enterprise data comprises the following steps: and constructing an enterprise representation system according to the business data and/or the industrial and commercial data and/or the tax data and/or the intellectual property data of each enterprise.
It should be noted that, in order to accurately or comprehensively cover the enterprise data information, all data information in the enterprise business data, the industrial and commercial data, the tax data, or the intellectual property data may be selected, or part of the data information may be selected as needed.
S13: and constructing an enterprise public opinion information map according to the enterprise public opinion data.
Specifically, please refer to fig. 2, where fig. 2 is a schematic diagram of an algorithm flow of an enterprise legal risk early warning method according to an embodiment of the present invention. The method for constructing the enterprise public opinion information map according to the enterprise public opinion data comprises the following steps: and constructing the public opinion information map of the enterprise according to the Internet public data and/or publication public data of each enterprise.
It should be noted that the internet public data of the enterprise includes, but is not limited to, the following data: wechat, microblog, Chinese referee's paperwork, no case of a suit, exposed enterprise information.
Publication published data includes, but is not limited to, the following: newspapers, magazines, and other traditional media-exposed enterprise information.
Specifically, on one hand, the establishment of the enterprise public opinion information map according to the enterprise public opinion data is to search the enterprise most similar to the enterprise situation according to the association when training the legal risk early warning model for a specific company.
The construction method comprises the following steps:
the method comprises the steps of performing text mining on internet and media text information in the last 5 years by using a natural language processing method, extracting names of individuals, units or other social organizations in the text as entities in a map, defining whether enterprise data co-occur or not as related, and using probability of co-occurrence as related weight. And the entity relation extraction is realized, and the algorithm comprises dependency grammar analysis, deep learning entity relation extraction and the like. And (3) generating a characteristic vector for each entity by using a graph mining algorithm (such as node2vec), and judging the similarity degree between the entities by comparing Euclidean distances between the characteristic vectors.
S14: and training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
Specifically, the enterprise legal risk early warning model is trained according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map, a risk early warning result is generated, and the association among the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map is established through an artificial intelligence algorithm, so that the enterprise legal risk early warning model is established.
Wherein the algorithm is based on enterprise-related data, including structured and unstructured data. And modeling the data of n (n is a natural number which is more than or equal to 1) enterprises which are most similar to the enterprise in a period of time by using a deep learning algorithm, and predicting the legal risk which the enterprise is possibly involved at present. The most similar n enterprises can be found through enterprise public opinion information maps.
More specifically, the enterprise legal risk early warning model is trained according to an enterprise legal question bank, an enterprise portrait system and an enterprise public opinion information map, and the process of generating a risk early warning result is as follows:
s141: an algorithm input stage, comprising: a feature vector sequence with the length of m (m is a natural number which is more than or equal to 1) is used as an input feature of the algorithm for inputting.
Specifically, the input features of the algorithm are feature vector sequences with the length of m, and the feature vector sequences are enterprise information data of each day for m consecutive days. The method for generating the characteristics of the daily enterprise information data comprises the following steps:
daily data features are features where structured features are concatenated with unstructured features. The structured features include business dimension, tax dimension, patent dimension information. The features of each dimension include discrete data features, continuous data features, and category features. The discrete data features and the continuous data features are normalized and then directly used as features, and the category features are subjected to onehot coding and then used as features. The unstructured features refer to text one-dimensional vectors obtained through a natural language processing algorithm. The text includes all internet and traditional media related to the business on that day. Extracting one-dimensional text vectors from text may use the algorithm of content 2vec, w2v, etc. in natural language processing. The dimensions of the structured features and the unstructured features may be adjusted according to the effect of the algorithm.
The Onehot encoding method is to convert all n-class features into vectors containing n 0 and 1, and each vector corresponds to a class name. It should be noted that the normalization method may be linear normalization.
S142: an algorithm training phase comprising: taking the two-dimensional matrix sequence data of m x n as training data of an algorithm, extracting features of the sequence data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and reducing the dimensions of the k-dimensional feature vector through a deep neural network to generate a low-dimensional feature vector; and then calculating the probability of the sequence data belonging to each category, finally comparing the probability distribution output by the algorithm with the real probability distribution, and updating parameters by reverse conduction iteration of errors.
Specifically, the training data of the algorithm is two-dimensional matrix sequence data of m × n, m is the length of the sequence data, i.e., the number of days, and n is the dimension of each piece of data in the sequence data, i.e., the dimension of the data per day. The feature of the sequence data is extracted through cnn (convolutional neural network), and the size of a convolutional kernel of the convolutional neural network is adjusted according to the sizes of m and n. And (3) generating a k-dimensional feature vector after the features of the data are extracted by cnn, and generating a low-dimensional feature vector after the dimension of the k-dimensional feature vector is reduced by dnn (a deep neural network). Finally, the probability that the data belongs to each category is calculated using the softmax function. And finally, comparing the probability distribution output by the algorithm with the real probability distribution, and conducting error backward to iterate and update parameters.
S143: an algorithmic prediction phase comprising: taking a sequence data sequence of the latest n days of an enterprise and a data feature vector of each day as prediction data of an input model, extracting features of the prediction data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and generating a low-dimensional feature vector after the k-dimensional feature vector is subjected to dimension reduction through a deep neural network; and then calculating the probability of possibly facing each legal risk, wherein the legal risk category with the highest probability is used as a risk early warning result output by the model.
It should be noted that, by using the algorithm described in the embodiment of the present application, the legal risk that the enterprise is most likely to face at present can be predicted. The data input into the model is a sequence data sequence of the last n days of the enterprise, and the data feature vector of each day is m-dimensional data spliced by structured data and unstructured data. The mapping from structured and unstructured data to daily data feature vectors needs to be the same as in the training phase. Inputting the sequence data into cnn to extract features and inputting dnn to reduce dimensions. And calculating the characteristic vector after dimensionality reduction through a softmax function to obtain the probability of possibly facing each legal risk at present, wherein the legal risk category with the highest probability is used as a risk early warning result of final judgment of the model.
S144: according to the classified output of the models, enterprise legal risk early warning is made;
it should be noted that the output of the enterprise legal risk early warning model or the output of the algorithm is the probability that the enterprise currently faces each legal risk, and the legal risk category with the highest probability is determined as the type that the model judges that the enterprise is likely to be related to the legal risk currently.
Of course, the embodiment of the present invention is not limited to the method for early warning the corporate law risk of the enterprise, and may also be implemented by other methods. The embodiment of the present invention is not limited to specific methods.
On the basis of the above embodiments, the embodiments of the present invention correspondingly provide an enterprise legal risk early warning device, which is specifically referred to fig. 3. The device includes:
the enterprise legal question bank generating module is used for constructing an enterprise legal question bank according to the judge data;
the enterprise portrait system generation module is used for constructing an enterprise portrait system according to enterprise data;
the enterprise public opinion information map generation module is used for constructing an enterprise public opinion information map according to enterprise public opinion data;
and the enterprise legal risk early warning model training module is used for training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
It should be noted that the embodiment of the present invention has the same beneficial effects as the enterprise legal risk early warning method in the foregoing embodiment, and for the specific introduction of the enterprise legal risk early warning method related in the embodiment of the present invention, refer to the foregoing embodiment, which is not described herein again.
On the basis of the above embodiment, an embodiment of the present invention further provides an enterprise legal risk early warning device, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the enterprise legal risk early warning method when the computer program is executed.
It should be noted that the embodiment of the present invention has the same beneficial effects as the enterprise legal risk early warning method in the foregoing embodiment, and for the specific introduction of the enterprise legal risk early warning method related in the embodiment of the present invention, refer to the foregoing embodiment, which is not described herein again.
On the basis of the foregoing embodiments, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the enterprise legal risk early warning method are implemented.
It should be noted that the embodiment of the present invention has the same beneficial effects as the enterprise legal risk early warning method in the above embodiment, and for the specific introduction of the enterprise legal risk early warning method related in the above embodiment of the present invention, please refer to the above embodiment, which is not described herein again.
It is further noted that, in the present specification, relational terms such as first and second, and the like are 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.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An enterprise legal risk early warning method is characterized by comprising the following steps:
establishing an enterprise legal affair question bank according to the referee data;
constructing an enterprise portrait system according to enterprise data;
constructing an enterprise public opinion information map according to the enterprise public opinion data;
and training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
2. The enterprise legal risk early warning method according to claim 1, wherein the constructing an enterprise legal problem library according to referee data comprises: and carrying out industry classification according to the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data and on the basis of the judicial data and/or the administrative referee data and/or the mediation data and/or the resolution data, and constructing an enterprise legal affairs problem library.
3. The enterprise legal risk early warning method of claim 1, wherein the constructing an enterprise representation system from enterprise data comprises: and constructing an enterprise representation system according to the business data and/or the industrial and commercial data and/or the tax data and/or the intellectual property data of each enterprise.
4. The enterprise legal risk early warning method of claim 1, wherein the constructing an enterprise public opinion information graph according to enterprise public opinion data comprises: and constructing the public opinion information map of the enterprise according to the Internet public data and/or publication public data of each enterprise.
5. The enterprise legal risk early warning method according to claim 1 or 4, wherein the process of constructing the enterprise public opinion information map according to the enterprise public opinion data comprises:
text mining is carried out on Internet public data and publication public data by using a natural language processing method, and names of individuals, units and/or other social organizations in the text are extracted as entities in a map;
whether the same data appear among the entities is defined as whether the entities are related, and the probability of the same data appearing is used as the weight of the relation, so that the entity relation extraction is realized;
generating a feature vector for each of the entities; and if necessary, judging the similarity degree between the entities by comparing the Euclidean distances between the characteristic vectors.
6. The enterprise legal risk early warning method of claim 1, wherein the training of the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information graph, and the generating of the risk early warning result comprises: and modeling the data of at least one enterprise similar to the target enterprise within a preset time by using a deep learning algorithm according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map, and predicting the legal risk of the target enterprise.
7. The enterprise legal risk early warning method according to claim 1 or 6, wherein the enterprise legal risk early warning model is trained according to an enterprise legal question bank, an enterprise portrait system and an enterprise public opinion information map, and the process of generating the risk early warning result is as follows:
an algorithm input stage, comprising: inputting a feature vector sequence with the length of m as an input feature of an algorithm;
an algorithm training phase comprising: taking the two-dimensional matrix sequence data of m x n as training data of an algorithm, extracting features of the sequence data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and reducing the dimensions of the k-dimensional feature vector through a deep neural network to generate a low-dimensional feature vector; then calculating the probability of the sequence data belonging to each category, finally comparing the probability distribution output by the algorithm with the real probability distribution, and updating parameters by reverse conduction iteration of errors;
an algorithmic prediction phase comprising: taking a sequence data sequence of the latest n days of an enterprise and a data feature vector of each day as prediction data of an input model, extracting features of the prediction data through a convolutional neural network, extracting the features through the convolutional neural network, and then generating a k-dimensional feature vector, and generating a low-dimensional feature vector after the k-dimensional feature vector is subjected to dimension reduction through a deep neural network; and then calculating the probability of possibly facing each legal risk, wherein the legal risk category with the highest probability is used as a risk early warning result output by the model.
8. An enterprise legal risk early warning device, characterized by includes:
the enterprise legal question bank generating module is used for constructing an enterprise legal question bank according to the judge data;
the enterprise portrait system generation module is used for constructing an enterprise portrait system according to enterprise data;
the enterprise public opinion information map generation module is used for constructing an enterprise public opinion information map according to enterprise public opinion data;
and the enterprise legal risk early warning model training module is used for training the enterprise legal risk early warning model according to the enterprise legal question bank, the enterprise portrait system and the enterprise public opinion information map to generate a risk early warning result.
9. An enterprise legal risk early warning device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the enterprise legal risk warning method according to any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, implements the steps of the enterprise legal risk warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765791.XA CN110674970A (en) | 2019-08-19 | 2019-08-19 | Enterprise legal risk early warning method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765791.XA CN110674970A (en) | 2019-08-19 | 2019-08-19 | Enterprise legal risk early warning method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110674970A true CN110674970A (en) | 2020-01-10 |
Family
ID=69075384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910765791.XA Pending CN110674970A (en) | 2019-08-19 | 2019-08-19 | Enterprise legal risk early warning method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674970A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553563A (en) * | 2020-04-07 | 2020-08-18 | 国网电子商务有限公司 | Method and device for determining enterprise fraud risk |
| CN111915154A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Enterprise comprehensive risk early warning level determination method and device |
| CN111967802A (en) * | 2020-09-25 | 2020-11-20 | 杭州安恒信息安全技术有限公司 | Enterprise financial risk quantitative analysis and early warning method, device and equipment |
| CN112132489A (en) * | 2020-10-13 | 2020-12-25 | 深圳前海微众银行股份有限公司 | Method, device and equipment for early warning processing of complaints and computer storage medium |
| CN112651573A (en) * | 2020-12-31 | 2021-04-13 | 上海竞动科技有限公司 | Risk prediction method and device based on deep learning |
| CN113160000A (en) * | 2021-04-22 | 2021-07-23 | 广州广电运通信息科技有限公司 | Legal information analysis method, system, device and storage medium |
| CN113283795A (en) * | 2021-06-11 | 2021-08-20 | 同盾科技有限公司 | Data processing method and device based on two-classification model, medium and equipment |
| CN113435762A (en) * | 2020-05-06 | 2021-09-24 | 支付宝(杭州)信息技术有限公司 | Enterprise risk identification method, device and equipment |
| CN115269879A (en) * | 2022-09-05 | 2022-11-01 | 北京百度网讯科技有限公司 | Knowledge structure data generation method, data search method and risk warning method |
| CN116862243A (en) * | 2023-08-29 | 2023-10-10 | 北京融信数联科技有限公司 | Enterprise risk analysis prediction method, system and medium based on neural network |
| CN116934098A (en) * | 2023-09-14 | 2023-10-24 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | Risk quantitative evaluation method for technical trade measures |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451710A (en) * | 2017-04-27 | 2017-12-08 | 北京鼎泰智源科技有限公司 | A kind of Information Risk grade five-category method and system |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN109523153A (en) * | 2018-11-12 | 2019-03-26 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise |
| CN109657918A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and the computer equipment of association assessment object |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
| CN109858762A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | A kind of business risk prediction technique and device |
-
2019
- 2019-08-19 CN CN201910765791.XA patent/CN110674970A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451710A (en) * | 2017-04-27 | 2017-12-08 | 北京鼎泰智源科技有限公司 | A kind of Information Risk grade five-category method and system |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109523153A (en) * | 2018-11-12 | 2019-03-26 | 平安科技（深圳）有限公司 | Acquisition methods, device, computer equipment and the storage medium of illegal fund collection enterprise |
| CN109657918A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Method for prewarning risk, device and the computer equipment of association assessment object |
| CN109858762A (en) * | 2018-12-29 | 2019-06-07 | 重庆誉存大数据科技有限公司 | A kind of business risk prediction technique and device |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553563A (en) * | 2020-04-07 | 2020-08-18 | 国网电子商务有限公司 | Method and device for determining enterprise fraud risk |
| CN113435762B (en) * | 2020-05-06 | 2023-08-08 | 支付宝(杭州)信息技术有限公司 | Enterprise risk identification method, device and equipment |
| CN113435762A (en) * | 2020-05-06 | 2021-09-24 | 支付宝(杭州)信息技术有限公司 | Enterprise risk identification method, device and equipment |
| CN111915154A (en) * | 2020-07-13 | 2020-11-10 | 上海冰鉴信息科技有限公司 | Enterprise comprehensive risk early warning level determination method and device |
| CN111915154B (en) * | 2020-07-13 | 2022-01-04 | 上海冰鉴信息科技有限公司 | Enterprise comprehensive risk early warning level determination method and device |
| CN111967802A (en) * | 2020-09-25 | 2020-11-20 | 杭州安恒信息安全技术有限公司 | Enterprise financial risk quantitative analysis and early warning method, device and equipment |
| CN112132489A (en) * | 2020-10-13 | 2020-12-25 | 深圳前海微众银行股份有限公司 | Method, device and equipment for early warning processing of complaints and computer storage medium |
| CN112651573A (en) * | 2020-12-31 | 2021-04-13 | 上海竞动科技有限公司 | Risk prediction method and device based on deep learning |
| CN113160000A (en) * | 2021-04-22 | 2021-07-23 | 广州广电运通信息科技有限公司 | Legal information analysis method, system, device and storage medium |
| CN113283795A (en) * | 2021-06-11 | 2021-08-20 | 同盾科技有限公司 | Data processing method and device based on two-classification model, medium and equipment |
| CN115269879A (en) * | 2022-09-05 | 2022-11-01 | 北京百度网讯科技有限公司 | Knowledge structure data generation method, data search method and risk warning method |
| CN116862243A (en) * | 2023-08-29 | 2023-10-10 | 北京融信数联科技有限公司 | Enterprise risk analysis prediction method, system and medium based on neural network |
| CN116862243B (en) * | 2023-08-29 | 2024-06-07 | 北京融信数联科技有限公司 | Enterprise risk analysis prediction method, system and medium based on neural network |
| CN116934098A (en) * | 2023-09-14 | 2023-10-24 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | Risk quantitative evaluation method for technical trade measures |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674970A (en) | Enterprise legal risk early warning method, device, equipment and readable storage medium | |
| Hedrick et al. | Digitization and the future of natural history collections | |
| CN111382272B (en) | Electronic medical record ICD automatic coding method based on knowledge graph | |
| CN104318340B (en) | Information visualization methods and intelligent visible analysis system based on text resume information | |
| Lei et al. | Patent analytics based on feature vector space model: A case of IoT | |
| CN110597870A (en) | Enterprise relation mining method | |
| CN113657993B (en) | Credit risk identification method, apparatus, device and storage medium | |
| CN112182246A (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| CN114647741A (en) | Process automatic decision and reasoning method, device, computer equipment and storage medium | |
| CN113742733B (en) | Method and device for extracting trigger words of reading and understanding vulnerability event and identifying vulnerability type | |
| CN109740642A (en) | Invoice category recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN109033087B (en) | Method for calculating text semantic distance, deduplication method, clustering method and device | |
| Sugiharti et al. | Predictive evaluation of performance of computer science students of unnes using data mining based on naÏve bayes classifier (NBC) algorithm | |
| CN113434688B (en) | Data processing method and device for public opinion classification model training | |
| CN111581193A (en) | Data processing method, device, computer system and storage medium | |
| CN110222192A (en) | Corpus method for building up and device | |
| CN112100398A (en) | Patent blank prediction method and system | |
| CN114491084B (en) | Self-encoder-based relation network information mining method, device and equipment | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN117151659B (en) | Ecological restoration engineering full life cycle tracing method based on large language model | |
| CN113157757A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN113220885A (en) | Text processing method and system | |
| Aly et al. | Machine Learning Algorithms and Auditor’s Assessments of the Risks Material Misstatement: Evidence from the Restatement of Listed London Companies | |
| CN116226404A (en) | Knowledge graph construction method and knowledge graph system for intestinal-brain axis | |
| CN116452353A (en) | Financial data management method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |