CN111125368A - Legal opinion book generation method based on target object - Google Patents
Legal opinion book generation method based on target object Download PDFInfo
- Publication number
- CN111125368A CN111125368A CN201911420919.5A CN201911420919A CN111125368A CN 111125368 A CN111125368 A CN 111125368A CN 201911420919 A CN201911420919 A CN 201911420919A CN 111125368 A CN111125368 A CN 111125368A
- Authority
- CN
- China
- Prior art keywords
- legal
- target object
- opinions
- generation method
- opinion book
- 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 44
- 239000013598 vector Substances 0.000 claims description 24
- 230000014509 gene expression Effects 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000008921 facial expression Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 230000008451 emotion Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of Internet, in particular to a legal opinion book generating method based on a target object, which comprises the following steps: s1 inputting legal questions and extracting keywords; s2 identifying the target object according to the keyword; s3 generating a query sentence according to the legal question and the target object; s4 searches the database for a predetermined legal opinion book matching the query sentence according to the query sentence, and outputs the legal opinion book. The method comprises the steps of identifying a target object by extracting keywords of legal problems, and generating a query sentence according to the target object and the legal problems; the legal opinions are generated according to specific legal information and by considering the characteristics of the requirements of the target object, so that the generated legal opinions are more targeted.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a legal opinion book generation method based on a target object.
Background
In the twenty-first century, people's legal awareness is gradually increasing. When the legal rights are damaged, most people can think of taking legal weapons to protect the life and property safety of themselves, and the demand for legal services is increasing day by day. The rapid development of the internet greatly improves the convenience degree of information acquisition of people. When legal services are needed, lawyers can only be consulted in the past, and most of the time is to inquire relevant information on the Internet. But for some groups of users, the users cannot be skilled in surfing the internet, and legal consultation information is obtained through the intelligent robot.
In this regard, CN107832281A discloses a legal document generation system based on an online counselor system, which comprises the following steps: applying for and obtaining a service code from a network operator, and establishing a network consultation platform; editing legal problems to be consulted into legal requirement information by a user through a terminal and sending the legal requirement information to the network consultation platform; the network consultation platform detects legal requirement information of the user, matches preset legal problems and solutions and displays the legal requirements and solutions to the user; the user selects a solution suitable for the user according to the displayed content; and matching the pre-stored coping strategies in the database according to the solution selected by the user, generating an editable legal document, and outputting the legal document to the user. The invention provides a flexible and convenient legal document generation mode, and a user selects a proper solution technical scheme through a prompt provided by an intelligent question-answer interaction mode; the problem of uneven distribution of talents in regions in the traditional legal service industry is solved through the Internet technology.
However, the number of legal problems in real life is huge, and the legal requirements of people are different. Different target objects (users) have different legal requirements, the required legal opinions are different, and different user culture levels and legal comprehension capabilities are different. The existing legal document generation system selects a proper solution through a prompt provided by an intelligent question-answer interaction mode instead of customizing the solution according to a target object.
Disclosure of Invention
The invention provides a legal opinion book generating system based on a target object, which customizes a solution according to the user and generates a legal opinion book; not only the characteristics of the user are considered, but also the requirements of the user are considered; the technical problem that the existing legal document generation system ignores the characteristics of the user is solved.
The basic scheme provided by the invention is a legal opinion book generation method based on a target object, which comprises the following steps: s1, extracting effective information in the interaction process; s2, acquiring the understanding level information of the target object according to the expression mode of the effective information; s3 generating a query sentence according to the legal question and the target object; s4 searches the database for a predetermined legal opinion book matching the query sentence according to the query sentence, and outputs the legal opinion book.
The working principle of the method is that the target object is identified by extracting the keywords of the legal problem, and the query sentence is generated according to the target object and the legal problem. The query sentence contains information of characteristics of common legal requirements of the target object and information of specific legal problems, so that the legal opinion book is generated in a targeted manner. The invention has the advantages that: the legal opinions are generated according to specific legal information and by considering the characteristics of the requirements of the target object, so that the generated legal opinions are more targeted.
The method and the device consider the dual information of the specific problem and the demand characteristic of the target object when generating the legal suggestion, and have pertinence and effectiveness compared with the prior art which only considers the specific problem and ignores the demand characteristic of the target object.
Further, step S1 specifically includes: s11 extracting information input by the user; s12 segmenting words, and segmenting word sequences into independent words; s13 removing stop words that have no actual meaning; s14 extracts keywords. Some keywords are long, so that the word sequence is successfully divided into independent words, and the effect of improving the automatic recognition meaning of the sentences by a computer can be achieved. The stop words without actual meanings are removed, so that the index amount can be reduced, the retrieval efficiency is improved, and the retrieval effect is improved.
Further, step S2 specifically includes: s21 randomly selecting K keywords as initial clustering centers; s22 assigning each keyword to its nearest cluster center; s23 recalculating the clustering centers; if the convergence is achieved, outputting a clustering result; if not, go to step S21; s24 matches the type of the target object according to the result of the clustering. Due to the fact that the categories of the keywords in the legal problem are various and different categories even intersect with each other, the type of the target object cannot be determined accurately. And clustering the keywords by adopting an algorithm, and merging similar keywords into the same category, which is favorable for improving the matching accuracy.
Further, step S3 specifically includes: s31 calling case templates of the database to generate case facts according to the keywords; s32, calling a corresponding criterion according to the type of the target object; s33 combines the case facts and the criteria to generate a query statement. Under the condition of no context, calling case templates in a database according to keywords can approximately outline the fact of cases; meanwhile, the efficiency and the accuracy of subsequent legal opinion book searching can be improved by combining the corresponding criteria of the type of the target object.
Further, step S4 specifically includes:
s41, extracting corresponding legal opinions from the database according to the query sentence; if only one corresponding legal opinion book exists, the legal opinion books are directly output; if N corresponding legal opinions exist, the step S42 is performed;
s42, obtaining a text vector A corresponding to the query statement, and obtaining text vectors B1, B2 and B3 … BN corresponding to each legal opinion book;
s43 calculates the text similarity Yi between the text vector a corresponding to the query sentence and the text vector Bi corresponding to each legal opinion book, where Yi is cos < a, Bi >, and i is 1, 2, or 3 … N;
s44, comparing the sizes of the N text similarity degrees Yi, and determining the maximum text similarity degree YM;
s45 outputs the legal opinions corresponding to the maximum text similarity YM.
Because of the profound nature of Chinese, a word with multiple meanings often occurs. When the corresponding legal opinions are extracted from the database according to the query sentence, a plurality of corresponding legal opinions may exist. Therefore, the legal opinions with the largest text similarity should be output.
The method further comprises a step S5 of estimating the probability of the winning, and specifically comprises the steps of S51 extracting a text vector C of the legal recommendation, S52 searching the corresponding judgment book of the typical case from the database and extracting a text vector D of the judgment book, S53 calculating the text similarity β of the text vector C and the text vector D to cos < C, D >, and S54 calculating the probability P of the winning to β x 100%, and predicting the possibility of the winning according to the generated legal recommendation, so that the target object has certain psychological expectation on the legal result of the winning or the losing.
Further, step S6 is included, the method evaluates the winning grade according to the winning probability; the method specifically comprises the following steps: s61, presetting a grade interval according to the winning probability; s62, determining the grade interval according to the winning probability p; s63 determines a winning rank. It is advantageous to give preliminary general legal advice in terms of the victory rank.
Further, step S7 is included to estimate the loss L caused by litigation risk. By estimating the loss, the method can effectively prompt the action to reduce the loss possibly brought by the risk of litigation.
Further, the method includes a step S8 of calculating an expected loss e (L), e (L) L × (1-P). The mathematical expectation is the result of random state averaging and can provide psychological expectation to people.
Further, step S9 is included, feedback; the method specifically comprises the following steps: s91 the target object judging whether or not the output legal opinions are satisfactory; s92, if the target object is satisfied with the outputted legal opinions, outputting the final legal opinions; if not, the target object supplements the question, and returns the post-problem legal question to step S1.
Drawings
FIG. 1 is a flowchart of an embodiment of a legal opinion book generation method based on target objects according to the present invention.
Detailed Description
The following is further detailed by the specific embodiments:
example 1
The embodiment of the legal opinion book generation method based on the target object is basically as shown in the attached figure 1, and comprises four steps of inputting legal questions and extracting key words, identifying the target object according to the key words, generating query sentences according to the legal questions and the target object, searching preset legal opinion books matched with the query sentences in a database according to the query sentences, and outputting the legal opinion books.
First, a legal question is entered and keywords are extracted. Various legal problems proposed by people are searched on the network, and after the legal problems are searched, word segmentation processing is carried out on the legal problems, and word sequences are segmented into independent words. Some keywords are long, so that the word sequence is successfully divided into independent words, and the effect of improving the automatic recognition meaning of the sentences by a computer can be achieved. And after the word segmentation is finished, removing stop words without actual meanings. The stop words without actual meanings are removed, so that the index amount can be reduced, the retrieval efficiency is improved, and the retrieval effect is improved. And when the stop words without meanings are taken out, extracting the keywords.
Then, a target object that presents a legal issue is identified based on the keywords. And classifying the legal problems by adopting a clustering algorithm, and then matching the types of the target objects according to the classification result. The method comprises the following specific steps: first, a keyword is input. And step two, randomly selecting K keywords as initial clustering centers. And thirdly, assigning each keyword word to the nearest cluster center. Fourthly, recalculating the clustering center; if the convergence is achieved, outputting a clustering result; if not, executing the second step. And fifthly, matching the type of the target object according to the clustering result. Due to the fact that the categories of the keywords in the legal problem are various and different categories even intersect with each other, the type of the target object cannot be determined accurately. And clustering the keywords by adopting an algorithm, and merging similar keywords into the same category, which is favorable for improving the matching accuracy.
Next, a query statement is generated based on the legal issue and the target object. The method comprises the following specific steps: firstly, calling a case template of a database to generate case facts according to keywords. Under the condition of no context, the fact that the case is approximately outlined by calling the case template in the database according to the keywords can provide a good basis for generating the legal opinions. And secondly, calling a corresponding criterion according to the type of the target object. Since different target objects have different cultural degrees and legal levels, the provided legal opinions should be treated differently, which requires that the legal opinions be generated by a certain criterion. For example, only the corresponding laws and regulations may be generated for the target object with high culture degree, and the corresponding popular and understandable interpretation and simple case may be generated for the target object with low culture degree in addition to the corresponding laws and regulations. And thirdly, combining case facts and criteria to generate a query statement. Therefore, the criteria corresponding to the type of the target object are considered, and the efficiency and the accuracy of subsequently searching the legal opinions can be improved.
And finally, searching a preset legal opinion book matched with the query statement in a database according to the query statement and outputting the legal opinion book. The method comprises the following specific steps: step one, extracting corresponding legal opinions from a database according to query sentences; if only one corresponding legal opinion book exists, the legal opinion books are directly output; if N corresponding legal opinions exist, the second step is carried out. And secondly, acquiring a text vector A corresponding to the query statement, and acquiring text vectors B1, B2 and B3 … BN corresponding to each legal opinion book. And thirdly, calculating the text similarity Yi, i which is cos < A, Bi > and i which is 1, 2 and 3 … N of the text vector A corresponding to the query sentence and the text vector Bi corresponding to each legal opinion book. And fourthly, comparing the N text similarity degrees Yi and determining the maximum text similarity degree YM. And fifthly, outputting the legal opinions corresponding to the maximum text similarity YM. Because of the profound nature of Chinese, a word with multiple meanings often occurs. When the corresponding legal opinions are extracted from the database according to the query sentence, a plurality of corresponding legal opinions may exist. Therefore, the legal opinions with the largest text similarity should be output.
Example 2
The only difference from example 1 is that:
the method comprises the following steps of firstly, extracting a text vector C of the legal proposal, secondly, searching a judgment book of a corresponding typical case from a database, and extracting a text vector D of the judgment book, thirdly, calculating the text similarity β between the text vector C and the text vector D as cos < C, D, fourthly, calculating the probability P of the winning proposal as β multiplied by 100%, predicting the probability of the winning proposal according to the generated legal proposal, so that a target object has certain psychological expectation on the legal result of the winning proposal or the losing proposal, then, evaluating the grade of the winning proposal according to the probability of the winning proposal generally, secondly, determining the grade section where the target object is located according to the probability P of the winning proposal, thirdly, determining the grade of the winning proposal according to the grade of the winning proposal, and being beneficial to the preliminarily given legal proposal.
Then, the loss L due to litigation risk is estimated. By estimating the loss, the method can effectively prompt the action to reduce the loss possibly brought by the risk of litigation. The expected loss e (L), e (L) ═ L × (1-P) is then calculated. The mathematical expectation is the result of random state averaging and can provide psychological expectation to people.
And finally, carrying out feedback. The method comprises the following specific steps: firstly, judging whether the output legal opinions are satisfied by a target object; secondly, if the target object is satisfied with the output legal opinions, outputting the final legal opinions; if not, the target object supplements the problem and re-inputs the legal problem after supplementing the problem.
Example 3
The only difference from example 2 is that: in the process of interacting with the user, in order to ensure the user experience, the system also comprises personification. The personification method specifically comprises the following steps: s01, collecting facial expression data of the user in the process of interacting with the user; s02, analyzing emotion information of the user, and judging whether the user needs comfort or not; s03, performing the operations of comfort and non-comfort; s04, after the first expression unit executes the comfort and non-comfort operation, collecting the next facial expression data of the user; s05, analyzing emotion information of the user, and judging whether the user really needs comfort or pretends to need comfort; s06, collecting facial expression data of the user after the user is assumed to be comforted; s07, the execution system has known that the user pretends to require comfort for normal operation.
In this embodiment, the personification adopts Face Reader, which is expression recognition software developed by Noldus. The software can analyze 6 basic facial expressions (happy, surprised, disgust, angry, fear, sadness), as well as blankness and slight libel; the gaze direction, head direction and character characteristics of the person may also be calculated.
When the user inputs legal problems, the Face Reader software synchronously collects the facial expressions of the user. The user is comforted when negative expressions of the user's face are captured. For example, when the fact that the face of the user leaks sadness and pain expressions is collected, the system judges that the emotion of the user is low and needs to be comforted, and encouraged words are played through voice.
And after the voice playing is finished, acquiring the facial expression of the user, and analyzing whether the target object really receives consolation or falsely receives consolation according to the facial expression. If the user's expression is "sad" before the comfort and "calm" after the comfort, then the system determines that the user is really receiving comfort; if the user's expression is "sad" before the comfort and "happy" after the comfort, the system determines that the user is pretending to accept the comfort. If the user is false to accept comfort, the utterance "please operate normally" is played by voice. And when the voice playing of 'please operate normally' is finished, the facial expression of the user is collected. If the user's expression is "calm" or "sad", playing the inspired words by voice; if the expression of the user is "happy," the word "please operate normally" is still played.
At the same time, the system also analyzes the personality traits of the user, and the inspired words are selected specifically according to the personality traits of the object. If the system analyzes that the user is in an optimistic character, then a fact-oriented speech is played, and if the fact-oriented speech is 'believing law, the problem can be successfully solved'; if the system analyzes that the user is in pessimistic character, then the emotion-oriented words are played, such as "better tomorrow". Therefore, the method can play a good role in mood placating for the user.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. The legal opinion book generating method based on the target object is characterized in that: the method comprises the following steps: s1, extracting effective information in the interaction process; s2, acquiring the understanding level information of the target object according to the expression mode of the effective information; s3 generating a query sentence according to the legal question and the target object; s4 searches the database for a predetermined legal opinion book matching the query sentence according to the query sentence, and outputs the legal opinion book.
2. The target object-based legal opinion book generation method of claim 1, wherein: step S1 specifically includes: s11 extracting information input by the user; s12 segmenting words, and segmenting word sequences into independent words; s13 removing stop words that have no actual meaning; s14 extracts keywords.
3. The target object-based legal opinion book generation method of claim 2, wherein: step S2 specifically includes: s21 randomly selecting K keywords as initial clustering centers; s22 assigning each keyword to its nearest cluster center; s23 recalculating the clustering centers; if the convergence is achieved, outputting a clustering result; if not, go to step S21; s24 matches the type of the target object according to the result of the clustering.
4. The target object-based legal opinion generation method of claim 3, wherein: step S3 specifically includes: s31 calling case templates of the database to generate case facts according to the keywords; s32, calling a corresponding criterion according to the type of the target object; s33 combines the case facts and the criteria to generate a query statement.
5. The target object-based legal opinion generation method of claim 4, wherein: step S4 specifically includes:
s41, extracting corresponding legal opinions from the database according to the query sentence; if only one corresponding legal opinion book exists, the legal opinion books are directly output; if N corresponding legal opinions exist, the step S42 is performed;
s42, obtaining a text vector A corresponding to the query statement, and obtaining text vectors B1, B2 and B3 … BN corresponding to each legal opinion book;
s43 calculates the text similarity Yi between the text vector a corresponding to the query sentence and the text vector Bi corresponding to each legal opinion book, where Yi is cos < a, Bi >, and i is 1, 2, or 3 … N;
s44, comparing the sizes of the N text similarity degrees Yi, and determining the maximum text similarity degree YM;
s45 outputs the legal opinions corresponding to the maximum text similarity YM.
6. The method for generating legal opinions based on target objects as claimed in claim 5, further comprising step S5, wherein the method comprises the steps of S51 extracting text vector C of legal advice, S52 searching corresponding typical case judgment from database and extracting text vector D of the judgment, S53 calculating text similarity β -cos < C, D > of text vector C and text vector D, and S54 calculating probability P- β x 100% of victory advice.
7. The target object-based legal opinion book generation method of claim 6, wherein: step S6, evaluating the winning grade according to the winning probability; the method specifically comprises the following steps: s61, presetting a grade interval according to the winning probability; s62, determining the grade interval according to the winning probability p; s63 determines a winning rank.
8. The target object-based legal opinion generation method of claim 7, wherein: further comprising a step S7 of estimating the loss L caused by the risk of litigation.
9. The target object-based legal opinion book generation method of claim 8, wherein: further comprising step S8, calculating an expected loss e (L), e (L) L × (1-P).
10. The target object-based legal opinion book generation method of claim 9, wherein: further comprising step S9, feedback; the method specifically comprises the following steps: s91 the target object judging whether or not the output legal opinions are satisfactory; s92, if the target object is satisfied with the outputted legal opinions, outputting the final legal opinions; if not, the target object supplements the question, and returns the post-problem legal question to step S1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911420919.5A CN111125368A (en) | 2019-12-31 | 2019-12-31 | Legal opinion book generation method based on target object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911420919.5A CN111125368A (en) | 2019-12-31 | 2019-12-31 | Legal opinion book generation method based on target object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111125368A true CN111125368A (en) | 2020-05-08 |
Family
ID=70507539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911420919.5A Pending CN111125368A (en) | 2019-12-31 | 2019-12-31 | Legal opinion book generation method based on target object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125368A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220710A (en) * | 2021-05-11 | 2021-08-06 | 北京百度网讯科技有限公司 | Data query method and device, electronic equipment and storage medium |
| CN114492446A (en) * | 2022-02-16 | 2022-05-13 | 平安科技（深圳）有限公司 | Legal document processing method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090863A (en) * | 2014-07-24 | 2014-10-08 | 高德良 | Intelligent legal instrument generating method and system |
| CN107291867A (en) * | 2017-06-13 | 2017-10-24 | 北京百度网讯科技有限公司 | Dialog process method, device, equipment and computer-readable recording medium based on artificial intelligence |
| CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
| CN109033336A (en) * | 2018-07-20 | 2018-12-18 | 吴怡 | Legal advice robot and business model based on artificial intelligence |
| CN109446303A (en) * | 2018-10-09 | 2019-03-08 | 深圳市三宝创新智能有限公司 | Robot interactive method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN110059193A (en) * | 2019-06-21 | 2019-07-26 | 南京擎盾信息科技有限公司 | Legal advice system based on law semanteme part and document big data statistical analysis |
-
2019
- 2019-12-31 CN CN201911420919.5A patent/CN111125368A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090863A (en) * | 2014-07-24 | 2014-10-08 | 高德良 | Intelligent legal instrument generating method and system |
| CN107291867A (en) * | 2017-06-13 | 2017-10-24 | 北京百度网讯科技有限公司 | Dialog process method, device, equipment and computer-readable recording medium based on artificial intelligence |
| CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
| CN109033336A (en) * | 2018-07-20 | 2018-12-18 | 吴怡 | Legal advice robot and business model based on artificial intelligence |
| CN109446303A (en) * | 2018-10-09 | 2019-03-08 | 深圳市三宝创新智能有限公司 | Robot interactive method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN110059193A (en) * | 2019-06-21 | 2019-07-26 | 南京擎盾信息科技有限公司 | Legal advice system based on law semanteme part and document big data statistical analysis |
Non-Patent Citations (1)
| Title |
|---|
| 李德毅: "《Web文本挖掘》", vol. 9787504681195, 中国科学技术出版社, pages: 169 - 172 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220710A (en) * | 2021-05-11 | 2021-08-06 | 北京百度网讯科技有限公司 | Data query method and device, electronic equipment and storage medium |
| CN113220710B (en) * | 2021-05-11 | 2024-06-04 | 北京百度网讯科技有限公司 | Data query method, device, electronic equipment and storage medium |
| CN114492446A (en) * | 2022-02-16 | 2022-05-13 | 平安科技（深圳）有限公司 | Legal document processing method and device, electronic equipment and storage medium |
| CN114492446B (en) * | 2022-02-16 | 2023-06-16 | 平安科技（深圳）有限公司 | Legal document processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800306B (en) | Intention analysis method, device, display terminal and computer readable storage medium | |
| CN113591902B (en) | Cross-modal understanding and generating method and device based on multi-modal pre-training model | |
| CN111125334B (en) | Search question-answering system based on pre-training | |
| KR102640564B1 (en) | Question and answer system training device and computer program therefor | |
| US6173261B1 (en) | Grammar fragment acquisition using syntactic and semantic clustering | |
| CN112800170A (en) | Question matching method and device and question reply method and device | |
| CN110175229B (en) | Method and system for on-line training based on natural language | |
| CN109299245B (en) | Method and device for recalling knowledge points | |
| CN112100354A (en) | Man-machine conversation method, device, equipment and storage medium | |
| US10586174B2 (en) | Methods and systems for finding and ranking entities in a domain specific system | |
| CN110266900B (en) | Method and device for identifying customer intention and customer service system | |
| CN111709223B (en) | Sentence vector generation method and device based on bert and electronic equipment | |
| CN110717021B (en) | Input text acquisition and related device in artificial intelligence interview | |
| CN114218375B (en) | Atlas-based dialogue guiding method, apparatus, equipment and medium | |
| CN112287090A (en) | Financial question asking back method and system based on knowledge graph | |
| CN113064980A (en) | Intelligent question and answer method and device, computer equipment and storage medium | |
| CN111858854A (en) | Question-answer matching method based on historical dialogue information and related device | |
| CN111429157A (en) | Method, device and equipment for evaluating and processing complaint work order and storage medium | |
| CN111125368A (en) | Legal opinion book generation method based on target object | |
| CN111159383A (en) | Legal opinion book generation system based on target object | |
| CN113051380A (en) | Information generation method and device, electronic equipment and storage medium | |
| CN113505606B (en) | Training information acquisition method and device, electronic equipment and storage medium | |
| TW202034207A (en) | Dialogue system using intention detection ensemble learning and method thereof | |
| CN112288584B (en) | Insurance report processing method and device, computer readable medium and electronic equipment | |
| CN116304046A (en) | Dialogue data processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |