CN112949665A - Data processing method, device, equipment and storage medium - Google Patents
Data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112949665A CN112949665A CN201911171346.7A CN201911171346A CN112949665A CN 112949665 A CN112949665 A CN 112949665A CN 201911171346 A CN201911171346 A CN 201911171346A CN 112949665 A CN112949665 A CN 112949665A
- Authority
- CN
- China
- Prior art keywords
- court trial
- information
- trial
- court
- memory
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 52
- 239000013598 vector Substances 0.000 claims description 79
- 238000012545 processing Methods 0.000 claims description 20
- 230000003993 interaction Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000000977 initiatory effect Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 3
- 230000004807 localization Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a data processing method, a device, equipment and a storage medium, wherein the data processing method comprises the steps of obtaining court trial records related to court trial cases in a court trial, wherein the court trial records carry identity marks; obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases; determining the rationality score of the trial basis information according to the litigation request of the court trial case; and determining the probability value of success of the litigation request according to the rationality score and the judging basis information. The method is used for solving the problem of low trial efficiency in the court trial in the related technology.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a data processing method, apparatus, device, and storage medium.
Background
In the court trial process, case evidences (such as a prosecution and an answer) are provided by the original and the defended parties respectively as case statement of respective positions. Thus, the judge can issue a question against the dispute section based on the statement of the case of both parties to ascertain the fact of the case and thereby make a fair decision.
However, due to the factors of the large number of case documents, the complicated dispute content and the like, the court officer needs to consider more factors in court trial, and the trial efficiency is low.
Disclosure of Invention
One or more embodiments of the invention describe a data processing method, device, equipment and storage medium, which are used for solving the problem of low trial efficiency in a court trial in the related art.
In order to solve the technical problem, the invention is realized as follows:
according to a first aspect, there is provided a data processing method, which may comprise:
acquiring court trial records related to court trial cases in a court trial, wherein the court trial records carry identity marks;
obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases;
determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and determining the probability value of success of the litigation request according to the rationality score and the judging basis information.
According to a second aspect, there is provided a data interaction method, which may include:
receiving a display request for evidence information of a court trial case in a court trial;
acquiring a court trial record related to the court trial cases in response to the display request, wherein the court trial record carries an identity mark;
determining the probability value of success of the litigation request in the filing information based on the court trial records and the filing information of the court trial cases;
under the condition that the probability value meets a preset threshold value, distinguishing and displaying the court trial case evidence information; wherein the evidence information comprises court trial record and/or protocol information corresponding to the probability value meeting the preset threshold value.
According to a third aspect, there is provided a data processing apparatus, which may comprise:
the acquisition module is used for acquiring court trial records related to court trial cases in a court trial, and the court trial records carry identity marks;
the processing module is used for obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases;
the calculation module is used for determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and the prediction module is used for determining the probability value of success of the litigation request according to the rationality score and the judging basis information.
According to a fourth aspect, there is provided a data interaction apparatus, which may include:
the acquisition module is used for acquiring court trial records related to court trial cases in a court trial, and the court trial records carry identity marks;
the processing module is used for obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases;
the calculation module is used for determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and the prediction module is used for determining the probability value of success of the litigation request according to the rationality score and the judging basis information.
According to a fifth aspect, there is provided a computing device comprising at least one processor and a memory, the memory being adapted to store computer program instructions, the processor being adapted to execute a program of the memory to control the computing device to implement the data processing method of the first aspect or the data interaction method of the second aspect.
According to a sixth aspect, there is provided a computer-readable storage medium having stored thereon a computer program which, if executed in a computer, causes the computer to perform the data processing method of the first aspect or the data interaction method of the second aspect.
In the scheme of the embodiment of the invention, the probability value of successful court trial request is determined through the court trial record of the multi-party objects about the court trial cases obtained in the court trial and the court trial request according to the court trial record, the original scheme information of the court trial cases and the scheme information, so that the judgment result of the court trial cases can be predicted later. Therefore, the probability value of successful litigation requests can be determined based on massive case vouchers and litigation requests, so that the predicted judging results of the court trial cases are obtained, judging references are provided for judges, and the accuracy of the judging results of the court trial cases is improved. On the contrary, the evidence information corresponding to the probability value meeting the preset threshold can be quickly and accurately found in the case vouchers and the litigation requests according to the probability value of success of the litigation requests, so that the credibility of the trial results is improved, and the trial efficiency of the court is improved.
Drawings
The present invention will be better understood from the following description of specific embodiments thereof taken in conjunction with the accompanying drawings, in which like or similar reference characters designate like or similar features.
FIG. 1 illustrates a schematic diagram of an application scenario for court trial data processing, according to one embodiment;
FIG. 2 shows a flow diagram of a data processing method according to one embodiment;
FIG. 3 illustrates a flow diagram for determining court trial records, according to one embodiment;
FIG. 4 illustrates a flow diagram for determining memory information, according to one embodiment;
FIG. 5 illustrates a flow diagram for determining trial basis information, according to one embodiment;
FIG. 6 illustrates a flow diagram for determining a decision result according to one embodiment;
FIG. 7 shows a flow diagram of another data process in accordance with one embodiment;
FIG. 8 illustrates a flow diagram of a data interaction method, according to one embodiment;
FIG. 9 shows a block diagram of a data processing apparatus according to an embodiment;
FIG. 10 shows a block diagram of a data interaction device, according to one embodiment;
FIG. 11 illustrates a schematic structural diagram of a computing device, according to one embodiment.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any such measured 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 … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In order to solve the problems in the prior art, embodiments of the present invention provide a data processing method, an apparatus, a device, and a storage medium, which are specifically shown as follows.
Firstly, the method comprises the following steps: as shown in fig. 1, an application scenario of court trial data processing according to an embodiment of the present invention is described.
First, the plan information of the court trial plan provided by the original and the defendant (for example, the original complaint of the original and the answer of the defendant) can be analyzed through the memory network, and the memory information can be obtained. Next, in a court trial, a display request for evidence information of the court trial is received, and in response to the display request, a court trial record (e.g., court trial voice data, court trial text data, image data, etc.) related to the court trial is obtained, wherein the court trial record carries an identity tag (as shown in fig. 1, the corresponding judge, originator or recipient of each court trial voice data is tagged). And determining the probability value of successful litigation requests in the filing information based on the court trial records and the filing information of the court trial cases, and displaying the evidence information of the court trial cases in a distinguishing way under the condition that the probability value meets a preset threshold value.
In this way, the probability value of success of the litigation request can be determined through the court trial records of the multi-party objects about the court trial cases obtained in the court trial and the litigation requests according to the court trial records, the original proposal information of the court trial cases and the proposal information, so as to predict the judgment result of the court trial cases later. The probability value of success of the litigation request can be determined based on massive case vouchers and litigation requests, so that the predicted judging result of the court trial cases is obtained, the judging reference is provided for judges, and the accuracy of the judging result of the court trial cases is improved. On the contrary, the evidence information corresponding to the probability value meeting the preset threshold can be quickly and accurately found in the case vouchers and the litigation requests according to the probability value of success of the litigation requests, so that the credibility of the trial results is improved, and the trial efficiency of the court is improved.
Secondly, the method comprises the following steps: based on the application scenarios in the court trial, the embodiment of the invention further adopts three embodiments, and combines fig. 2 to fig. 8 to further explain the data processing method provided by the embodiment of the invention.
Example 1:
FIG. 2 shows a flow diagram of a data processing method according to one embodiment.
As shown in fig. 2, the method may include steps 210 to 240: firstly, step 210, acquiring court trial records related to court trial cases in a court trial, wherein the court trial records carry identity marks; next, step 220, obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases; furthermore, step 230, determining the rationality score of the trial basis information according to the litigation request of the court trial case; then, in step 240, the probability value of success of the litigation request is determined according to the rationality score and the judgment basis information.
The above steps are described in detail below:
referring first to step 210, in an embodiment of the present invention, obtaining a court trial record may include the following steps:
receiving audio information of a plurality of objects related to court trial cases in a court trial;
and marking the audio information according to the preset role information to obtain court trial records. Or, receiving court trial recording data related to the court trial cases; and marking the audio information according to the preset role information to obtain court trial records. Or, receiving court trial text data or image data related to the court trial cases, and determining the court trial text data or image data as a court trial record. The court trial records can be provided with identity marks, namely, the court trial records are spoken by a judge, an original advertiser or an advertised advertiser.
For example, the following steps are carried out: as shown in fig. 3, 10 pieces of audio information are received, and each of the 10 pieces of audio is labeled according to preset role information, i.e., a judge, an original, an advertised party, or a witness, so as to obtain 10 pieces of audio, where the first piece of audio is spoken by the judge, the second piece of audio is spoken by the advertised party, and so on until 10 pieces of audio are labeled.
Here, the tagging method provided by the embodiment of the present invention may process the audio information through a memory network, which is specifically as follows: converting the received audio information into a court trial record, and inputting the court trial record into a memory network corresponding to the court trial record to obtain a dialogue sentence vector; and determining an identity sentence vector carrying identity marks corresponding to the court trial records according to the preset role vector and the dialogue sentence vector.
Next, referring to step 220, trial basis information related to the court trial cases may be obtained through an attention mechanism based on the court trial records and the protocol information, and the specific steps are as follows:
obtaining the memory score of each memory information in the protocol information through an attention mechanism according to the court trial records; and obtaining the judgment basis information through the memory score and the court trial record of each memory information.
The plan information in the embodiment of the present invention may include the prosecution information and the answer information, where the step of determining the memory information based on the prosecution information and the answer information may be as follows:
inputting the complaint initiating information into a memory network corresponding to the complaint initiating information to obtain a complaint initiating sentence vector; inputting the answer information into a memory network corresponding to the answer information to obtain an answer sentence vector;
and determining the starting sentence vector and the answering and resolving sentence vector at the preset moment as memory information.
For example, as shown in fig. 4, the text contents of the prosecution information and the answer information are respectively sentence-divided to obtain a sentence vector corresponding to each sentence; the sentence vector is input into the memory network corresponding to the sentence vector to obtain the starting sentence vector and the answer and resolution sentence vector. Here, inputting a sentence vector into a memory network corresponding to the sentence vector can be understood as encoding the sentence vector by a bidirectional long-and-short term memory network in the memory network to obtain a starting sentence vector and an answering and resolving sentence vector. Then, the target sentence hidden vector (i.e., memory information) corresponding to the last word information in each of the starting sentence vector or the answering sentence vector is expressed as a vector of the whole sentence. Here, a memory array may be generated based on a plurality of target sentence hidden vectors so as to be repeatedly read when the criterion information is determined.
Thus, based on the obtained memory information, step 220 may specifically include:
obtaining the trial basis information through the memory score and the court trial record of each memory information, which may specifically include:
weighting and summing a plurality of memory information in the strategy information according to the memory score of each memory information to obtain a memory score aiming at the court trial record;
and obtaining the trial basis information based on the memory score and the court trial record of the court trial record.
For example, as shown in fig. 5, the identity sentence vector carrying the identity tag in fig. 3 is used to measure the importance degree (i.e., memory score) of each memory information in fig. 4, the memory scores of each memory information are weighted and summed to obtain a memory score for the identity sentence vector, and then a target dialog sentence vector for the trial basis information is obtained according to the memory score and the dialog sentence vector for the identity sentence vector.
Thus, the importance degree of each memory information in the plan information to the court trial case, namely the memory score, can be measured based on the multi-party court trial records in the court trial, and then the trial basis information can be obtained based on each court trial record and the importance degree corresponding to each court trial record, and the trial basis information can be understood to comprise both the court trial records in the court trial and the plan information with higher importance degree in the court trial case.
Still further, referring to step 230, in a possible embodiment, before performing step 230, the method may further include: and inputting the judging basis information into a memory network corresponding to the judging basis information to obtain a target hidden vector.
Based on this, step 230 may specifically include: and obtaining the rationality score of the target hidden vector through an attention mechanism according to the litigation request of the court trial case.
Thus, the trial basis information is scored according to the trial basis information and the litigation requests obtained in step 220, and compared with the step 220, the reasonableness scoring which is closer to the opinions of the original advising party, the advised party and the judges for each litigation request in the court trial records and the case setting information is further obtained, so that the accuracy of the judgment result can be improved.
For example, as shown in fig. 6, the target dialogue sentence vector is input into the memory network corresponding to the target dialogue sentence vector to obtain a target hidden vector, which follows the example of fig. 5; and measuring the importance degree of the target hidden vector to the court trial case, namely the rationality score of the target hidden vector based on the vector corresponding to the litigation request.
Then, based on step 230, step 240 may specifically include:
when the target hidden vectors comprise a plurality of hidden vectors, carrying out weighted summation on the hidden vectors according to the rationality score of each hidden vector to obtain the rationality score of the target hidden vector;
obtaining a pre-judgment result vector according to the rationality score of the target hidden vector and the target hidden vector;
and inputting the vector of the pre-judgment result into the classification model, and determining the probability value of success of the litigation request so as to obtain the predicted judgment result of the court trial cases.
For example, based on step 230, as shown in fig. 6, when the target hidden vectors include multiple hidden vectors, the multiple target hidden vectors are weighted and summed according to each target hidden vector and the rationality score corresponding to each target hidden vector, so as to obtain a pre-judgment result vector; and inputting the vector of the pre-judgment result into the softmax classification model, and determining the probability value of success of the litigation request so as to predict the judgment result of the litigation request of the trial case according to the probability value. Wherein, the classification result mainly comprises: support litigation requests, partial support litigation requests, and rejectional litigation requests. Here, it is to be noted that the target hidden vector corresponds to each sentence, and this step is essentially to quantize each sentence to obtain a vector of the overall dialog, i.e., a prejudgment result vector, and then predict the judgment result of the litigation request for the court trial cases based on the overall court trial record in the court trial. Of course, the embodiment of the present invention may also predict the decision result of each litigation request in the court trial case for each litigation request.
Therefore, the probability value of successful litigation request is determined according to the court trial record of the multi-party objects about the court trial cases obtained in the court trial and the court trial request according to the court trial record, the original proposal information of the court trial cases and the proposal information, so as to predict the judgment result of the court trial cases later. Therefore, the probability value of successful litigation requests can be determined based on massive case vouchers and litigation requests, so that the predicted judging results of the court trial cases are obtained, judging references are provided for judges, and the accuracy of the judging results of the court trial cases is improved. On the contrary, the evidence information corresponding to the probability value meeting the preset threshold can be quickly and accurately found in the case vouchers and the litigation requests according to the probability value of success of the litigation requests, so that the credibility of the trial results is improved, and the trial efficiency of the court is improved.
Example 2:
in court trial, the original, the reported and the judge can obscure the dispute focus and ignore details due to the large number of case vouchers and the complicated dispute content. Thus, the evidence information supporting the intermediate process of the decision result, that is, the court trial record and the proposal information related to the court trial case in the court trial and the information related to the decision result in the litigation request can be provided by the obtained prejudged decision result. According to the actual situation, evidence information supporting the trial result can be highlighted, so that the reliability of the predicted trial result is improved.
Thus, unlike embodiment 1, the method provided in the embodiment of the present invention may further include: evidence information relating to a probability value and/or a rationality score for success of the litigation request is displayed in at least one of the court trial record, the proposal information, and the litigation request relating to the court trial case.
This is explained in detail below with reference to fig. 7.
FIG. 7 illustrates a flow diagram of another data processing method according to one embodiment.
As shown in fig. 7, the method may include steps 710 to 750: firstly, step 710, acquiring court trial records related to court trial cases in a court trial, wherein the court trial records carry identity marks; then, step 720, obtaining trial basis information according to the court trial record and the scheme information of the court trial cases; secondly, step 730, determining the rationality score of the trial basis information according to the litigation request of the court trial case; thirdly, in step 740, determining the probability value of success of the litigation request according to the rationality score and the judging basis information; then, in step 750, evidence information related to the probability value is displayed, wherein the evidence information is at least one of court trial record, protocol information and litigation request.
The method steps in step 710 to step 740 are the same as the method steps in step 210 to step 240 in fig. 2, and thus, the details in step 710 to step 740 may refer to the descriptions in step 210 to step 240, and are not described herein again.
Then, step 750 is involved of tagging evidence information related to a probability value of success and/or a rationality score of the litigation request in at least one of court trial record, the proposal information, and the litigation request related to the court trial case;
the evidence information is visualized and displayed in a differentiated manner in at least one of the court trial record, the proposal information, and the litigation request.
In the example shown in fig. 6, when the predicted decision result is "support for litigation request", evidence information related to "support for litigation request" may be highlighted in at least one of the court trial record, the filing information, and the litigation request, and the rationality score of the evidence information may be higher than that of other information not highlighted.
Alternatively, the evidence information is displayed in chronological order of the evidence information generation, and information irrelevant to the result of the "support litigation request" is not displayed.
Therefore, the evidence information is highlighted or marked, the information related to the predicted trial result is highlighted, the information is used for assisting the judge to quickly and accurately find out details related to the court trial cases from a large number of case certificates, and the court trial efficiency is improved while the credibility of the predicted trial result is ensured.
Example 3:
in addition, based on the foregoing embodiment 2, an embodiment of the present invention further provides a possible embodiment, that is, a data interaction method, which may also be applied in the scenario shown in fig. 1, where the data interaction method specifically includes steps 810 to 840, and specifically as follows:
Here, the content described in this step is the same as the content related to step 210, and the content shown in step 210 may be referred to specifically, and is not described again here.
Wherein, the step may specifically include: obtaining trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases; determining the rationality score of the judging basis information according to the litigation request of the filing information; and determining the probability value of success of the litigation request according to the rationality score and the judging basis information.
Thus, the content described in this step is the same as the content related to the above step 220 to step 240 in principle, and specific reference may be made to the content shown in the above step 210 to step 240, which is not described herein again.
Here, the evidence information corresponding to the probability value satisfying the preset threshold value may be used as the evidence of the judgment result of the court trial case, and the evidence information may be differentially displayed so as to provide a trial reference for a judge, so as to improve the accuracy of the judgment result for the court trial case.
Third, an embodiment of the present invention further provides a structure of a data processing apparatus corresponding to the data processing method. This is explained in detail below with reference to fig. 8.
FIG. 9 shows a block diagram of a data processing apparatus according to one embodiment.
As shown in fig. 9, the data processing device 90 may specifically include:
an obtaining module 901, configured to obtain a court trial record related to a court trial case in a court trial, where the court trial record carries an identity tag;
a processing module 902, configured to obtain trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases;
the calculating module 903 is used for determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and the prediction module 904 is used for determining the probability value of success of the litigation request according to the rationality score and the trial basis information.
In a possible embodiment, the processing module 902 may be specifically configured to obtain a memory score of each piece of memory information in the protocol information according to the court trial record through an attention mechanism;
and obtaining the judgment basis information through the memory score and the court trial record of each memory information.
Based on the possibility, the calculating module 903 in the embodiment of the present invention may be specifically configured to perform weighted summation on a plurality of pieces of memory information in the plan information according to the memory score of each piece of memory information, so as to obtain a memory score for the court trial record;
and obtaining the trial basis information based on the memory score and the court trial record of the court trial record.
Here, the aforementioned plan information may specifically include prosecution information and answer information. Based on this, the data processing apparatus 90 may further include: a first generating module 905, configured to input the prosecution information into a memory network corresponding to the prosecution information, so as to obtain a prosecution sentence vector; inputting the answer information into a memory network corresponding to the answer information to obtain an answer sentence vector;
and determining the starting sentence vector and the answering and resolving sentence vector at the preset moment as memory information.
In another possible embodiment, the presetting device 90 may further include: the second generating module 906 is configured to input the trial basis information into a memory network corresponding to the trial basis information of the second generating module 906, so as to obtain a target hidden vector. Thus, based on the situation, the calculation module 903 may be specifically configured to obtain the rationality score of the target hidden vector through an attention mechanism according to the litigation request of the court trial case.
Based on this, the prediction module 904 may be specifically configured to, when there are a plurality of target hidden vectors, perform weighted summation on the plurality of target hidden vectors according to each target hidden vector and the rationality score corresponding to each target hidden vector, to obtain a pre-judgment result vector;
and inputting the vector of the pre-judgment result into the classification model, and determining the probability value of success of the litigation request so as to obtain the predicted judgment result of the court trial cases.
Moreover, in yet another possible embodiment, the data processing device 90 may further include a display module 907 for tagging evidence information related to the probability value of success and/or the rationality score of the litigation request in at least one of the court trial record, the proposal information, and the litigation request related to the court trial case;
and carrying out visualization processing on the evidence information and displaying the evidence information.
In summary, in the solution of the embodiment of the present invention, the probability value of success of the litigation request is determined through the court trial record of the court trial cases about the multi-party objects obtained in the court trial, and the litigation request according to the court trial record, the original proposal information of the court trial cases, and the proposal information, so as to predict the judgment result of the court trial cases later. Therefore, the probability value of successful litigation requests can be determined based on massive case vouchers and litigation requests, so that the predicted judging results of the court trial cases are obtained, judging references are provided for judges, and the accuracy of the judging results of the court trial cases is improved. On the contrary, the evidence information corresponding to the probability value meeting the preset threshold can be quickly and accurately found in the case vouchers and the litigation requests according to the probability value of success of the litigation requests, so that the credibility of the trial results is improved, and the trial efficiency of the court is improved.
In addition, an embodiment of the present invention further provides a data interaction apparatus, and as shown in fig. 10, the apparatus 100 shows a block diagram of a data interaction apparatus. The data interaction apparatus 100 may specifically include:
an obtaining module 1001 for obtaining a court trial record related to a court trial case in a court trial, the court trial record carrying an identity tag;
the processing module 1002 is configured to obtain trial basis information related to the court trial cases according to the court trial records and the setting information of the court trial cases;
the calculation module 1003 is used for determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and the prediction module 1004 is used for determining the probability value of success of the litigation request according to the rationality score and the trial basis information.
The obtaining module 1001 in the embodiment of the present invention may be specifically configured to, in response to a display request, receive multimedia data related to a court trial case; carrying out identity marking on the multimedia data according to preset identity information to obtain court trial records; wherein the multimedia data comprises at least one of: court trial voice data, court trial text data and image data.
Here, the court trial voice data includes voice data and/or court trial recording data received in the court trial.
In addition, in a possible embodiment, the data interaction device 100 may further include a storage module 1005 for storing the differentially displayed evidence information for use in checking the court trial case.
Fourth, the embodiment of the present invention further provides a structure of a computing device corresponding to the data processing method or the data interaction method. This is explained in detail below with reference to fig. 11.
FIG. 11 illustrates a schematic structural diagram of a computing device, according to one embodiment.
As shown in fig. 11, a block diagram of an exemplary hardware architecture of a computing device capable of implementing a data processing method or a data interaction method and apparatus according to an embodiment of the present invention.
The apparatus may include a processor 1101 and a memory 1102 in which computer program instructions are stored.
Specifically, the processor 1101 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
The processor 1101 reads and executes the computer program instructions stored in the memory 1102 to implement any one of the data processing methods or the data interaction methods in the above-described embodiments.
The transceiver 1103 is mainly used for implementing the apparatus in the embodiment of the present invention or communicating with other devices.
In one example, the device may also include a bus 1104. As shown in fig. 11, the processor 1101, the memory 1102 and the transceiver 1103 are connected via a bus 1104 to complete the communication therebetween.
Fifth, an embodiment of the present invention further provides a computer-readable storage medium corresponding to the sound source localization method.
In one possible embodiment, the embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, which, when the computer program is executed in a computer, causes the computer to perform the steps of the sound source localization method of the embodiment of the present invention.
It is to be understood that the invention is not limited to the particular arrangements and instrumentality described in the above embodiments and shown in the drawings. For convenience and brevity of description, detailed description of a known method is omitted here, and for the specific working processes of the system, the module and the unit described above, reference may be made to corresponding processes in the foregoing method embodiments, which are not described herein again.
It will be apparent to those skilled in the art that the method procedures of the present invention are not limited to the specific steps described and illustrated, and that various changes, modifications and additions, or equivalent substitutions and changes in the sequence of steps within the technical scope of the present invention are possible within the technical scope of the present invention as those skilled in the art can appreciate the spirit of the present invention.
Claims (15)
1. A data processing method, comprising:
acquiring a court trial record related to a court trial case in a court trial, wherein the court trial record carries an identity mark;
obtaining trial basis information related to the court trial cases according to the court trial records and the scheme information of the court trial cases;
determining the rationality score of the judging basis information according to the litigation request of the filing information;
and determining the probability value of success of the litigation request according to the reasonability score and the judging basis information.
2. The method of claim 1, wherein obtaining trial basis information related to the court trial cases based on the court trial record and the protocol information for the court trial cases comprises:
obtaining the memory score of each memory information in the protocol information according to the court trial records through an attention mechanism;
and obtaining the trial basis information according to the memory score of each memory information and the court trial record.
3. The method of claim 2, wherein obtaining the trial basis information through the memory score of each memory information and the court trial record comprises:
weighting and summing a plurality of pieces of memory information in the protocol information according to the memory score of each piece of memory information to obtain a memory score aiming at the court trial record;
and obtaining the trial basis information based on the memory score of the court trial record and the court trial record.
4. The method according to claim 1 or 2, wherein the proposal information comprises prosecution information and answer information; the method further comprises the following steps:
inputting the complaint initiating information into a memory network corresponding to the complaint initiating information to obtain a complaint initiating sentence vector; inputting the answer information into a memory network corresponding to the answer information to obtain an answer sentence vector;
and determining the starting sentence vector and the answering and resolving sentence vector at a preset moment as the memory information.
5. The method of claim 1 or 2, wherein the method further comprises:
inputting the judging basis information into a memory network corresponding to the judging basis information to obtain a target hidden vector;
wherein, through the litigation request, determining the reasonability score of the judgment basis information comprises:
and obtaining the rationality score of the target hidden vector through an attention mechanism according to the litigation request.
6. The method of claim 5, wherein determining a probability value of success of the litigation request according to the rationality score and the judge information comprises:
when the target hidden vector is plural in number,
carrying out weighted summation on a plurality of target hidden vectors according to each target hidden vector and the rationality score corresponding to each target hidden vector to obtain a pre-judgment result vector;
and inputting the vector of the prejudgment result into a classification model, and determining the probability value of success of the litigation request.
7. The method of claim 6, further comprising:
tagging evidence information related to a probability value of success of the litigation request and/or the rationality score in at least one of the court trial record, the filing information, and the litigation request related to the court trial case;
and carrying out visualization processing on the evidence information and displaying the evidence information.
8. A data interaction method comprises the following steps:
receiving a display request for evidence information of a court trial case in a court trial;
responding to the display request, and acquiring a court trial record related to the court trial cases, wherein the court trial record carries an identity mark;
determining the probability value of success of the litigation request in the court trial information based on the court trial record and the court trial information of the court trial cases;
under the condition that the probability value meets a preset threshold value, the court trial case evidence information is displayed in a distinguishing manner; wherein the evidence information comprises court trial records and/or protocol information corresponding to a probability value meeting a preset threshold.
9. The method of claim 8, wherein the retrieving, in response to the display request, a court trial record related to the court trial cases comprises:
receiving multimedia data related to the court trial case in response to the display request;
carrying out identity marking on the multimedia data according to preset identity information to obtain the court trial record;
wherein the multimedia data comprises at least one of: court trial voice data, court trial text data and image data.
10. The method of claim 9, wherein the court trial voice data comprises voice data and/or court trial recording data received in a court trial.
11. The method of claim 8, wherein the method further comprises:
and storing the evidence information which is displayed distinctively for checking the court trial cases.
12. A data processing apparatus, comprising:
the acquisition module is used for acquiring court trial records related to court trial cases in a court trial, and the court trial records carry identity marks;
the processing module is used for obtaining trial basis information related to the court trial cases according to the court trial records and the scheme information of the court trial cases;
the calculation module is used for determining the rationality score of the trial basis information according to the litigation request of the court trial case;
and the prediction module is used for determining the probability value of success of the litigation request according to the reasonability score and the judging basis information.
13. A data interaction device, comprising:
the receiving and sending module is used for receiving a display request for the evidence information of the court trial cases in the court trial;
the acquisition module is used for responding to the display request and acquiring the court trial records related to the court trial cases, wherein the court trial records carry identity marks;
the determining module is used for determining the probability value of success of the litigation request in the court trial information based on the court trial record and the court trial information of the court trial cases;
the display module is used for displaying the trial case evidence information in a distinguishing way under the condition that the probability value meets a preset threshold value; wherein the evidence information comprises court trial records and/or protocol information corresponding to a probability value meeting a preset threshold.
14. A computing device, wherein the device comprises at least one processor and a memory, the memory being adapted to store computer program instructions, the processor being adapted to execute the program of the memory to control the computing device to implement a data processing method according to any one of claims 1 to 7 or to implement a data interaction method according to any one of claims 8 to 11.
15. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, if executed in a computer, causes the computer to perform the data processing method of any one of claims 1 to 7 or to implement the data interaction method of any one of claims 8 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911171346.7A CN112949665A (en) | 2019-11-26 | 2019-11-26 | Data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911171346.7A CN112949665A (en) | 2019-11-26 | 2019-11-26 | Data processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949665A true CN112949665A (en) | 2021-06-11 |
Family
ID=76224866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911171346.7A Pending CN112949665A (en) | 2019-11-26 | 2019-11-26 | Data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949665A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145089A1 (en) * | 2015-03-09 | 2016-09-15 | Skytree, Inc. | System and method for using machine learning to generate a model from audited data |
| CN108665182A (en) * | 2018-05-18 | 2018-10-16 | 中国科学技术大学 | A kind of patent action Risk Forecast Method |
| CN109241285A (en) * | 2018-08-29 | 2019-01-18 | 东南大学 | A kind of device of the judicial decision in a case of auxiliary based on machine learning |
| CN109472017A (en) * | 2017-09-08 | 2019-03-15 | 北京国双科技有限公司 | Obtain the method and device that judgement document the court to be generated thinks section relevant information |
-
2019
- 2019-11-26 CN CN201911171346.7A patent/CN112949665A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016145089A1 (en) * | 2015-03-09 | 2016-09-15 | Skytree, Inc. | System and method for using machine learning to generate a model from audited data |
| CN109472017A (en) * | 2017-09-08 | 2019-03-15 | 北京国双科技有限公司 | Obtain the method and device that judgement document the court to be generated thinks section relevant information |
| CN108665182A (en) * | 2018-05-18 | 2018-10-16 | 中国科学技术大学 | A kind of patent action Risk Forecast Method |
| CN109241285A (en) * | 2018-08-29 | 2019-01-18 | 东南大学 | A kind of device of the judicial decision in a case of auxiliary based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 黄元佗;: "集体选择机制在民事诉讼调解中的应用", 科技信息, no. 27, 25 September 2010 (2010-09-25) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11610394B2 (en) | Neural network model training method and apparatus, living body detecting method and apparatus, device and storage medium | |
| Peng et al. | Detecting Spam Review through Sentiment Analysis. | |
| CN109344257B (en) | Text emotion recognition method and device, electronic equipment and storage medium | |
| CN112256849B (en) | Model training method, text detection method, device, equipment and storage medium | |
| CN110674788A (en) | Vehicle damage assessment method and device | |
| CN104780282A (en) | Method and equipment for classifying speech content in telephone conference | |
| CN112990294B (en) | Training method and device of behavior discrimination model, electronic equipment and storage medium | |
| EP3859558A1 (en) | Answer marking method for mental calculation questions, device, electronic apparatus, and storage medium | |
| US20190385253A1 (en) | Systems and methods for determining structured proceeding outcomes | |
| US9317887B2 (en) | Similarity calculating method and apparatus | |
| Smith et al. | Wage-setting and gender pay equality in Australia: Advances, retreats and future prospects | |
| Raman et al. | The diagnostic performance of Cxbladder Resolve, alone and in combination with other Cxbladder tests, in the identification and priority evaluation of patients at risk for urothelial carcinoma | |
| US10529337B2 (en) | Symbol sequence estimation in speech | |
| CN107798457A (en) | Investment combination proposal recommending method, device, computer equipment and storage medium | |
| Ghaemmaghami et al. | A study of speaker clustering for speaker attribution in large telephone conversation datasets | |
| CN112949665A (en) | Data processing method, device, equipment and storage medium | |
| JP2015041333A (en) | Information processing device and information processing program | |
| CN110309691B (en) | Face recognition method, face recognition device, server and storage medium | |
| CN115527520A (en) | Anomaly detection method, device, electronic equipment and computer readable storage medium | |
| CN112819565B (en) | Method, system and storage medium for detecting buoy string | |
| CN111310064B (en) | Computing method, device and storage medium for eliminating business comment | |
| Zheng et al. | A generative approach to audio-visual generalized zero-shot learning: Combining contrastive and discriminative techniques | |
| Rivera et al. | Annotation process for the dialog act classification of a taglish e-commerce q&a corpus | |
| CN116628206B (en) | Enterprise credit analysis management system based on data analysis | |
| CN111222040B (en) | Scheme self-matching processing method and system based on training requirements |
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 |