CN111339379A - Electronic evidence analysis system - Google Patents
Electronic evidence analysis system Download PDFInfo
- Publication number
- CN111339379A CN111339379A CN202010132133.XA CN202010132133A CN111339379A CN 111339379 A CN111339379 A CN 111339379A CN 202010132133 A CN202010132133 A CN 202010132133A CN 111339379 A CN111339379 A CN 111339379A
- Authority
- CN
- China
- Prior art keywords
- electronic evidence
- evidence
- electronic
- module
- analysis system
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000003064 k means clustering Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 239000004568 cement Substances 0.000 description 11
- 238000013500 data storage Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000004576 sand Substances 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 230000032258 transport Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000013598 vector Substances 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
- G06Q10/10—Office automation; Time management
-
- 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)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of electronic evidence data analysis, in particular to an electronic evidence analysis system, which comprises: the acquisition module is used for inputting electronic evidence data; a database for storing typical cases; the checking module is used for verifying the nondestructive property of the electronic evidence extraction process; the evaluation module evaluates the probability of winning according to the integrity of the evidence chain; and the output module is used for outputting the probability of the victory complaint. The invention has the advantages that the possibility of the victory complaint can be roughly predicted according to the collected evidence data, so that the user has certain psychological expectation on the legal results of the victory complaint or the victory complaint; and the user can preliminarily know the corresponding litigation risk, so that the user can conveniently take corresponding legal measures to guarantee the rights and interests as soon as possible.
Description
Technical Field
The invention relates to the field of electronic evidence data analysis, in particular to an electronic evidence analysis system.
Background
After twenty-first century, internet and mobile communication have been rapidly developed, and related technologies and devices are widely used in life and office. At present, the related electronic evidence analysis method can cause some data omission, and the electronic evidence data cannot be deeply mined. In this regard, document CN103729397A discloses a method for analyzing electronic evidence data based on time trajectory, which includes extracting time features from the electronic evidence data; summarizing and uniformly storing the electronic evidence data based on time characteristics; determining the window size of a time window on a time axis; filtering and clustering the electronic evidence data corresponding to each time window to extract key features in the electronic evidence data; and replacing each time window on the time axis with the corresponding key characteristic and redrawing the time axis. The method can further and more comprehensively mine and analyze the electronic evidence data, greatly reduces interference data on a time axis, enables evidence collection and analysis personnel to visually observe relevant rules and characteristics of events, and obtains key information of the electronic evidence more quickly.
The increasing demand for programmatic legal services by the general public generally expects a certain psychological expectation for the legal consequences of a victory or a complaint. Since electronic data is easily damaged and tampered, the original document can be easily changed or damaged by adopting a computer technical means. To ensure the proof power of the electronic evidence, the non-destructive property of the electronic evidence extraction process must be ensured. Therefore, to accurately predict the probability of a victory complaint through electronic evidence, the non-destructiveness of the electronic evidence extraction process must be verified a priori. In practice, the integrity check value of the electronic evidence is calculated at the first time after the evidence is obtained by the scout organ and noted in the note. When it is necessary to verify whether the electronic data is complete, added, deleted, or modified, the integrity check value of the electronic proof is calculated again. If the two results are consistent, the electronic data is not changed; if not, it is proved that the electronic data has changed.
Disclosure of Invention
The invention provides an electronic evidence analysis system which can predict the possibility of a victory or a victory, according to collected evidence data, so that the public has certain psychological expectation on the legal result of the victory or the victory.
The basic scheme provided by the invention is an electronic evidence analysis system, which comprises: the acquisition module is used for inputting electronic evidence data; a database for storing typical cases; the checking module is used for verifying the nondestructive property of the electronic evidence extraction process; the evaluation module evaluates the probability of winning according to the integrity of the evidence chain; and the output module is used for outputting the probability of the victory complaint.
The working principle of the invention is as follows: the evidence chain is a proving chain formed by objective facts and objects, can be connected in order and combined to form a main link of case occurrence, and can completely prove the criminal process. In criminal cases, the court of law also carries out criminal or innocent identification on criminal suspects according to an evidence chain provided by public security organs when in judgement. Thus, similarly, the higher the integrity of the chain of evidence, the stronger the case is documented and the higher the probability of winning. The invention has the advantages that: the possibility of the victory complaint can be roughly predicted according to the collected evidence data, so that the user has certain psychological expectation on the legal results of the victory complaint or the failure complaint.
The method and the device can roughly predict the probability of the victory prosecution by forming an evidence chain according to the electronic evidence, so that the user can preliminarily know the corresponding risk of litigation, and the user can conveniently take corresponding legal measures to guarantee the rights and interests as soon as possible.
Further, the evaluation module is also used for evaluating the probability of winning according to the text matching degree of the evidence. Because of the profound Chinese bouquet, legal languages are more refined and strict, and the situation that one word is polysemous and multiple words are polysemous is common. If the semantic evaluation winning probability is neglected simply according to the integrity of the evidence chain, the bias is inevitable. If the probability is different from the probability of evaluation according to the evidence chain and the difference is large, the evaluation result is not accurate, and correction should be performed.
And the sorting module is used for extracting the time characteristics in the electronic evidence data and summarizing and storing the electronic evidence data according to the time sequence. Because the events all have a certain sequence, the corresponding evidences also have a certain time sequence. The electronic evidence data are collected and stored according to the time sequence, so that the internal logic of the case can be cleared, and the accuracy of the evaluation of the probability of victory complaints can be improved.
And the characteristic module is used for determining the size of the time step on the time axis and extracting the key characteristic in each time step. Generally, electronic evidence contains a large amount of content, and if the electronic evidence is directly sorted on a time axis according to the time sequence, regular behaviors and characteristics cannot be directly observed. Therefore, the time axis is divided into a plurality of time steps, and then the behavior and the characteristics of the comparative rule can be directly observed according to the key characteristics in each time step.
Further, the system comprises a fact module used for calling case templates of the database to generate case facts according to key features of the electronic data. Keywords are simply isolated words, phrases or phrases, whose meaning is sometimes difficult to derive without a contextual context. Therefore, the fact of the case can be approximately outlined by calling the case template in the database according to the key features, and the accuracy of the evaluation of the probability of winning is improved.
Further, the fact module is also configured to send to the database the fact of the case generated based on the key features of the electronic data. This can increase the amount of data for a case in the database, thereby increasing the number of samples compared.
Further, the characteristic module is also used for filtering the electronic evidence data of each time step; the method comprises the following specific steps: s11, word segmentation; s12, except stop words without actual meaning. Some keywords are long, one keyword sequence is divided into independent words, Chinese word segmentation is successfully carried out, and the effect of improving the automatic recognition of the sentence meaning 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, the characteristic module is also used for clustering the electronic evidence data of each time step by adopting a k-means clustering algorithm (k-means clustering algorithm); the method comprises the following specific steps: s21, inputting keywords; s22, randomly selecting K keywords as initial clustering centers; s23, assigning each keyword to the nearest cluster center; s24, recalculating the clustering center; if the convergence is achieved, outputting a clustering result; if not, go to step S22. The types of keywords in the electronic evidence data are various, and cases are not convenient to generate due to the fact that different types even have intercross situations. The keywords of the same category separated by the k-means clustering algorithm have great similarity, and the similar keywords are all merged into the same category, so that the accuracy of the subsequent case fact generation is improved.
Further, the electronic evidence entered by the acquisition module comprises text evidence, recording evidence and video evidence. Textual evidence, such as contracts, debts; recording evidence, such as a conversation recording by a stylus; video evidence, such as video set by a cell phone.
Further, the output module is also used for giving legal suggestions according to the probability of winning. Giving corresponding suggestions according to the probability of the victory complaint, and if the probability of the victory complaint is high, suggesting the victory complaint; and if the probability of the victory is low, suggesting further collection of evidence or hiring a lawyer.
Drawings
Fig. 1 is a system configuration block diagram of an electronic evidence analysis system 1 according to an embodiment of the present invention.
Fig. 2 is a block diagram of a system structure of an electronic evidence analysis system in embodiment 2 of the present invention.
Detailed Description
The following is a more detailed description of the present invention with reference to specific embodiments.
Example 1
An embodiment of an electronic evidence analysis system of the invention is basically shown in figure 1 and comprises an acquisition module, a verification module, an evaluation module, a database and an output module.
The database stores a large amount of typical cases, case templates, laws and regulations and judicial interpretations, and the typical cases are generally guiding cases released by the highest people's court or extremely representative cases released by various high-level people's courts in the local area, and can be updated in real time.
The input module inputs the collected electronic evidence data (such as contracts, loans, debts, recordings and videos) into the verification module. For example, the contents of these electronic proofs are as follows:
"… Zhang III buys 5 tons of cement from Li IV in 1 st 4 th 2008, and signs a cement buying and selling contract in the same day, and the contract contracts that Li IV transports the cement quality guarantee amount to the stone dam near Zhang III in 15 days, and one-time payment is made when Zhang III receives cement. 16 days 4 and 2008, when Li IV transports the cement to a rock dam near three families, three families are required to pay the price of the cement by 3 ten thousand yuan. The three-in-one table shows that no money exists temporarily, a debt of 3 ten thousand yuan is willing to be delivered to the four-in-one table, the debt is paid at the bottom of 4 months, interest is paid according to the synchronous interest rate of the bank in the period, and the four-in-one table shows agreement. In 2008, 5/1, the plum four holds the debt and goes to Zhang three dwellings, and the debt and interest are required to be paid. Three years show business loss till now, no profit can be paid, and 2 ten thousand yuan is borrowed from 28 days of 4 months and king five, and the borrow is shown in the four views of the plum. Li IV shows that Zhang III is suspicious of being tied up and is informed that the recording and video recording are carried out by a mobile phone when Zhang III signs a contract and a debt. Zhang Sanjian, shows that money is immediately lost, but requires …'s preparation for two days "
And the verification module verifies whether the electronic evidences are complete, added, deleted and modified after receiving the electronic evidences, and particularly the generation time of the electronic evidences is different from the occurrence time of the fact stated by the party. For example, for the claimed 3 ten thousand dollar debt of lie iv, if the time script of the debt (word. doc format) is displayed as 18 days 4/2008, which is different from the time when lie iv transports cement to Zhang III (16 days 4/2008), the debt may be added, deleted or modified by lie iv. Therefore, it is necessary to check whether the strip is non-destructive (complete, not added, deleted, modified). Firstly, MD5 encryption is carried out on the debt displayed as 2008, 4, 16 and a string A is obtained; secondly, MD5 encryption is carried out on the debt displayed as 2008, 4, 18 and the encryption character string B is obtained; and thirdly, comparing the encrypted character string A with the encrypted character string B. If the two are different, the defect strip is not lossless and cannot be adopted; if the two are the same, the defect strip is proved to have no damage and can be adopted. And after the inspection is finished, the checking module sends the electronic evidence with the nondestructive property to the evaluation module.
If the electronic evidences are all lossless, the evaluation module estimates the probability of winning according to the integrity of an evidence chain formed by the electronic evidences after receiving the electronic evidence data. Since the chain of evidence is formed by a series of individual electronic evidences that rely primarily on the meaning of their expression in proving case affairs in real time. Therefore, keywords can be extracted from the electronic evidence, the evidence is replaced by the keywords, the evidence chain is replaced by the keyword chain formed by the keywords, and the number of the keywords is recorded as the number of evidence chain links.
The typical case with the largest matching degree with the electronic evidence data is found from the database as a template. The method specifically comprises the following steps: firstly, extracting a sub-character string from electronic evidence data as a character string to be matched; searching a keyword corresponding to the character string to be matched in a data storage space; thirdly, extracting a corresponding typical case from the data storage space corresponding to the keyword; step four, if the character string to be matched is the same as the inquired character string, outputting a typical case, otherwise, executing the step five; step five, extracting a character from the back of the substring in the inquired character string and combining the character after the substring to form a new substring, taking the new substring as a character string to be matched, and executing step two.
After finding the typical case with the maximum matching degree with the electronic evidence data in the database, counting the number of keywords in the electronic evidence data and recording as N1，N1The number of the rings of the evidence chain formed by the electronic evidence is obtained; counting the number of the fact-identified partial keywords in the typical case, and recording as N2，N2I.e., the number of rings in the chain of evidence for a typical case, then the chain integrity α ═ N1/N2Typical cases in the database are typically guiding cases issued by the highest people's court or very representative cases issued by high-level people's court in the area, and the probability of winning is considered to be 100%1Number of rings N of evidence chain of typical case 50260, the proof integrity α is 50/60 is 0.833, and the probability of winning P is α× 100 is 100% is 0.833 × 100% is 83.3%.
And finally, the output module outputs the evaluation result P of the probability of winning to be 83.3 percent.
Example 2
The only difference from example 1 is that: also comprises a sequencing module, a characteristic module and a fact module, as shown in figure 2.
The input module sends the electronic evidence data to the sorting module. After the sequencing module receives the electronic evidence, extracting the implicit time characteristics in the electronic evidence data, namely the making time of the electronic evidence data; and sequencing and storing the electronic evidence data according to the sequence of the manufacturing time. For example, the electronic evidence is organized as follows: contract, recording for contracting and video for contracting are carried out on 1 day 4 month in 2008; 16 days 4 month 2008, recording of debt, cement delivery and debt, and video of cement delivery and debt; borrow the loans of 28 days 4 and 2008. The sorted electronic evidence data is then sent to the feature module.
After the feature module receives the sequenced electronic evidence data, the time points are used as key analysis factors, the electronic evidence is subjected to data generalization and summarized based on time features, and then the data on the time axis is subjected to further feature extraction. A proper time step needs to be preset, and if the time step is too short, the effect of eliminating interference data is difficult to achieve; if the time step is too long, some valid evidence data will be filtered out. The method specifically comprises the following steps: first, an initial time step is set, such as 15 days. Secondly, dividing the time axis according to the length of the time step; if the time axis is 1 month, the time axis can be divided into 2 segments. Thirdly, calculating the similarity of the electronic data in each time step and judging whether the similarity is lower than a preset similarity value (the calculation of the similarity can refer to the prior art); if yes, continuing the fourth step, otherwise, continuing the fifth step. And fourthly, adjusting the length of the time step, and then continuing the second step. And fifthly, determining the length of the time step on the time axis. In this embodiment, the time axis is not particularly long, so the time step is not adjusted, and the time step can be set to 15 days.
After the length of the time step is determined, the respective contents of the two time steps can be determined. The content as in the first time step (1/4/2008-15/4/2008) is "1/4/2008, contract, recording to sign contract, video to sign contract"; the content in the second time step (16/4/2008-30/4/2008) is "recording of debt, cement delivery and debt, video of cement delivery and debt at 16/4/2008); 28 days 4 month 2008, borrow. Then, the content in each time step is filtered, and words are cut and stop words without actual meanings, such as exclamation words, adverbial words and the like, are removed. And immediately clustering after filtering is finished, wherein text information is extracted and keywords are extracted according to the electronic evidence contained in the time step. The method specifically comprises the following steps: step one, inputting keywords in the time step; randomly selecting K keywords as initial clustering centers; step three, assigning each keyword to a clustering center closest to the keyword; step four, recalculating the clustering center; if the convergence is achieved, outputting a clustering result; if not, executing step two. For example, clustering the three words "debt, arrears, due price" into "arrears" does not consider "debt, due price" because they are all incorporated into "arrears". And finally, replacing each time step on the time axis with the extracted key characteristics, redrawing the time axis, and sending the redrawn time axis to the fact module.
And after receiving the redrawn time axis, the fact module calls a case template corresponding to the database according to the key characteristics, wherein the case template comprises columns of parties, time, places, causes, passes, results and the like. The method specifically comprises the following steps: step one, extracting a sub-character string from key features as a character string to be matched; searching a keyword corresponding to the character string to be matched in a data storage space; step three, extracting a corresponding case template from a data storage space corresponding to the key features; step four, if the character string to be matched is the same as the inquired character string, outputting a case template, otherwise, executing the step five; step five, extracting a character from the back of the substring in the inquired character string and combining the character after the substring to form a new substring, taking the new substring as a character string to be matched, and executing step two. The detailed steps of calling the case template can be referred to in the prior art.
After a case template with the maximum matching degree with the key features is found in a database, the key features on the time axis are matched into columns of parties, time, places, causes, passes, results and the like in the case template, case facts are generated according to the time sequence, and the case facts generated in this way form an evidence chain. The case facts are then sent to the evaluation module, which also sends the case facts to the database. After receiving the case facts, the evaluation module calls typical cases corresponding to the database according to the key features, and the specific steps are similar to the case templates corresponding to the database according to the key features, and the steps or the corresponding prior art can be referred to.
As previously mentioned, case facts include the scenario of principal, time, location, cause, passage, and result, all of which require evidence for proof; the evidentiary events constitute case facts, and the evidences in the case facts form an evidence chain. The fact-identified portion in the typical case can be considered as a standard for comparison, and the evidence chain therein can be considered as a complete evidence chain. Therefore, the completeness of the case fact to be compared with the evidence chain of the typical case can be approximately obtained by comparing the text similarity of the case fact to be compared with the fact-identified part of the typical case.
After the typical case is obtained, the completeness of the case fact compared with the evidence chain of the typical case is calculated, namely the text similarity of the case fact to be compared and the fact-identified part of the typical case. The method comprises the steps of firstly, importing texts of typical cases and case facts; secondly, acquiring the feature vectors of typical case and case fact texts as d respectively1And d2Third step, calculating text similarity β ═ cos<d1，d2>× 100%, if β is not equal to α calculated in example 1 and the difference is large, then β is used as the standard, because the processing in this example is more careful, and obviously more accurate than the proportion of the number of keywords calculated directly in example 1, for example, β is 0.75, and 75% is the probability of winning even though α is 0.833, and finally outputThe module outputs 75% as the probability of winning. Therefore, the probability of winning 75% is higher, and the output module gives out the suggestion of winning the complaint; and if the probability of the victory is low, recommending further collection of evidence or hiring a lawyer.
Example 3
The evaluation module is different from the embodiment 2 only in that the evaluation module further comprises a vulnerability unit, a risk unit, a suggestion unit and a learning unit; the vulnerability unit is used for checking whether the evidence chain has a vulnerability or not according to the time difference; sending the vulnerability information to a risk unit; the risk unit is used for receiving the vulnerability information and evaluating whether legal risk exists according to the vulnerability information; and sending the legal risk information to a suggestion unit; the suggestion unit is used for receiving the legal risk information and generating suggestions according to the legal risk information; the learning unit is used for learning the vulnerability inspection, the legal risk information evaluation and the suggestion generation process.
In this embodiment, the vulnerability unit checks a vulnerability in the evidence chain according to the time difference. For example, Liqu means departure at 6 months and 14 days, and river sand is transported to three homes at 6 months and 16 days. However, it usually takes about 3 days for the four plum fruits to carry the river sand to the three quarters, while the four plum fruits take 2 days. And the statement of lie four shows that a bug exists, and the bug unit sends bug information of non-compliance with the time difference to the risk unit. After receiving the vulnerability information, the risk unit evaluates the legal risk, namely that Liqu may not fulfill the obligation of delivering river sand, and sends the risk information to the suggestion unit. And after the suggestion unit receives the risk information, prompting to supplement the relevant evidence. For example, if the new transportation vehicle is replaced by the plum four, the transportation speed is increased; whether the road conditions are congested or not in the period; whether the high-speed toll station has relevant records, and the like. The learning unit learns the vulnerability check, the legal risk information evaluation and the suggestion generation process. For example, the specific value of the time difference is optimized.
The sequence of the proof strength of the electronic proof is "case-specific" and cannot be easily set by a person. For an electronic proof, the fact that a case can be proved may be manifold, and the strength of the proving force may be different for different aspects. For example, for the contract made by zhang san and lie si, the time of making the contract, the party involved in the contract, and the right obligation relationship between zhang san and lie si can be proved. However, the proof strength of the contract on the right obligation relationship between zhang san and lie si is significantly greater than the proof strength on the sign-in time in terms of the strength of the proof strength. This is because the rights obligation relationship is "black and white paper", which reflects the real will of the party in most cases; in practice, the time of contract is often inconsistent with the actual time of contract due to some factors (e.g., convenient financing or loan).
In addition, for one electronic evidence, the fact in a plurality of cases can be proved, but the strength of the proving force can be different for different cases. For example, on the day (day 1/6) when the contract is made by zhang san and lie si, it is difficult to prove that the pen-down date on the contract matches the day. If someone indicates that Zhang III criminated theft on 6/1, then the evidence that Zhang III was not present is quite sufficient. Therefore, for electronic evidence, multiple pieces of evidence are combined to check whether a vulnerability exists; and if the loophole exists, performing risk analysis pertinently and giving a suggestion.
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. An electronic evidence analysis system characterized by: the method comprises the following steps: the acquisition module is used for inputting electronic evidence data; a database for storing typical cases; the checking module is used for verifying the nondestructive property of the electronic evidence extraction process; the evaluation module evaluates the probability of winning according to the integrity of the evidence chain; and the output module is used for outputting the probability of the victory complaint.
2. An electronic evidence analysis system according to claim 1 wherein: the evaluation module is also used for evaluating the probability of winning according to the text matching degree of the evidence.
3. An electronic evidence analysis system according to claim 2 wherein: the electronic evidence data processing system further comprises a sorting module used for extracting the time characteristics in the electronic evidence data and summarizing and storing the electronic evidence data according to the time sequence.
4. An electronic evidence analysis system according to claim 3 wherein: the system also comprises a characteristic module used for determining the size of the time step on the time axis and extracting the key characteristics in each time step.
5. An electronic evidence analysis system according to claim 4 wherein: the system also comprises a fact module used for calling the case template of the database to generate case facts according to the key features of the electronic data.
6. An electronic evidence analysis system according to claim 5 wherein: the fact module is also for sending to the database the fact of the case generated from the key features of the electronic data.
7. An electronic evidence analysis system according to claim 6 wherein: the characteristic module is also used for filtering the electronic evidence data of each time step; the method comprises the following specific steps: s11, word segmentation; s12, except stop words without actual meaning.
8. An electronic evidence analysis system according to claim 7 wherein: the characteristic module is also used for clustering the electronic evidence data of each time step by adopting a k-means clustering algorithm (k-means clustering algorithm); the method comprises the following specific steps: s21, inputting keywords; s22, randomly selecting K keywords as initial clustering centers; s23, assigning each keyword to the nearest cluster center; s24, recalculating the clustering center; if the convergence is achieved, outputting a clustering result; if not, go to step S22.
9. An electronic evidence analysis system according to claim 8 wherein: the electronic evidence input by the acquisition module comprises text evidence, recording evidence and video evidence.
10. An electronic evidence analysis system according to claim 9 wherein: the output module is also used for giving legal suggestions according to the probability of winning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010132133.XA CN111339379A (en) | 2020-02-29 | 2020-02-29 | Electronic evidence analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010132133.XA CN111339379A (en) | 2020-02-29 | 2020-02-29 | Electronic evidence analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111339379A true CN111339379A (en) | 2020-06-26 |
Family
ID=71185754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010132133.XA Pending CN111339379A (en) | 2020-02-29 | 2020-02-29 | Electronic evidence analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339379A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593618A (en) * | 2013-10-28 | 2014-02-19 | 北京实数科技有限公司 | Verification method and system for adoptability of electronic data evidence |
| CN103729397A (en) * | 2013-10-28 | 2014-04-16 | 公安部第三研究所 | Method for achieving electronic evidence data analysis based on time tracks |
| CN107330820A (en) * | 2017-08-28 | 2017-11-07 | 北京智诚律法科技有限公司 | A kind of forecasting system and method for lawsuit result |
| US20180144421A1 (en) * | 2016-11-21 | 2018-05-24 | Velites Consulting Group, LLC | System and Methods for Complaint Evaluation |
| CN110222145A (en) * | 2019-04-28 | 2019-09-10 | 杭州实在智能科技有限公司 | A kind of intelligence law appraisal procedure and system |
| CN110377632A (en) * | 2019-06-17 | 2019-10-25 | 平安科技（深圳）有限公司 | Lawsuit prediction of result method, apparatus, computer equipment and storage medium |
| CN110472011A (en) * | 2019-07-19 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of cost of litigation prediction technique, device and terminal device |
| CN110825880A (en) * | 2019-09-18 | 2020-02-21 | 平安科技（深圳）有限公司 | Case winning rate determining method, device, equipment and computer readable storage medium |
-
2020
- 2020-02-29 CN CN202010132133.XA patent/CN111339379A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593618A (en) * | 2013-10-28 | 2014-02-19 | 北京实数科技有限公司 | Verification method and system for adoptability of electronic data evidence |
| CN103729397A (en) * | 2013-10-28 | 2014-04-16 | 公安部第三研究所 | Method for achieving electronic evidence data analysis based on time tracks |
| US20180144421A1 (en) * | 2016-11-21 | 2018-05-24 | Velites Consulting Group, LLC | System and Methods for Complaint Evaluation |
| CN107330820A (en) * | 2017-08-28 | 2017-11-07 | 北京智诚律法科技有限公司 | A kind of forecasting system and method for lawsuit result |
| CN110222145A (en) * | 2019-04-28 | 2019-09-10 | 杭州实在智能科技有限公司 | A kind of intelligence law appraisal procedure and system |
| CN110377632A (en) * | 2019-06-17 | 2019-10-25 | 平安科技（深圳）有限公司 | Lawsuit prediction of result method, apparatus, computer equipment and storage medium |
| CN110472011A (en) * | 2019-07-19 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of cost of litigation prediction technique, device and terminal device |
| CN110825880A (en) * | 2019-09-18 | 2020-02-21 | 平安科技（深圳）有限公司 | Case winning rate determining method, device, equipment and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 傅禄;霍勇;: "浅析Relief算法设计思想在电子证据分析中的应用" * |
| 麦水浩;徐伟;聂毅;: "解密电子信息的证据可采性及证明力研究" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107122451B (en) | Automatic construction method of legal document sorter | |
| JP6715838B2 (en) | System and method for automatically identifying potentially important facts in a document | |
| CN112215004B (en) | Application method of transfer learning-based text entity extraction in military equipment | |
| CN111145052A (en) | Structured analysis method and system of judicial documents | |
| US20200089752A1 (en) | Method and system for suggesting revisions to an electronic document | |
| CN113994323A (en) | Intelligent alarm system | |
| CN107807962B (en) | A method of similarity mode being carried out to legal decision document using LDA topic model | |
| CN113297283A (en) | Public opinion analysis method and system for enterprise risk early warning | |
| CN110610005A (en) | Stealing crime auxiliary criminal investigation method based on deep learning | |
| CN111062834A (en) | Dispute case entity identification method and device, computer equipment and storage medium | |
| CN109492097B (en) | Enterprise news data risk classification method | |
| CN108959507A (en) | Contract review method and apparatus, computer readable storage medium | |
| CN110880142A (en) | Risk entity acquisition method and device | |
| EP4252139A1 (en) | Systems and methods for relevance-based document analysis and filtering | |
| CN111144087A (en) | Enterprise legal flow assistant decision-making system and method based on artificial intelligence | |
| CN110472011A (en) | A kind of cost of litigation prediction technique, device and terminal device | |
| Hidayati et al. | Development of conceptual framework for cyber fraud investigation | |
| CN111353716A (en) | Illegal fundamentation detection method, system and computer readable storage medium | |
| Lam et al. | Applying large language models for enhancing contract drafting | |
| CN111339379A (en) | Electronic evidence analysis system | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| CN110766091B (en) | Method and system for identifying trepanning loan group partner | |
| US20210073247A1 (en) | System and method for machine learning architecture for interdependence detection | |
| TW202009735A (en) | Regulatory compliance processing device for auditing | |
| Plachouras et al. | Information extraction of regulatory enforcement actions: From anti-money laundering compliance to countering terrorism finance |
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: 20200626 |
|
| RJ01 | Rejection of invention patent application after publication |