Data processing method, device, equipment and storage medium

Abstract

The embodiment of the present invention provides a data processing method, device, equipment and storage medium, wherein the data processing method includes obtaining a trial record related to a trial case in a trial, wherein the trial record carries an identity tag; obtaining trial basis information related to the trial case according to the trial record and the case filing information of the trial case; determining the rationality score of the trial basis information according to the litigation request of the trial case; and determining the probability value of the success of the litigation request according to the rationality score and the trial basis information. The method is used to solve the problem of low trial efficiency in related technologies.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data processing method, device, equipment and storage medium. Background Art

[0002] During the court trial process, the plaintiff and the defendant will each provide case evidence (e.g., indictment, statement of defense) as their respective statements of the case. In this way, the judge can ask questions about the disputed parts based on the case statements of both parties to find out the facts of the case and make a fair judgment.

[0003] However, due to the large number of case documents and the complexity of the dispute, judges need to consider many factors during the trial, resulting in low trial efficiency. Summary of the invention

[0004] One or more embodiments of the present invention describe a data processing method, apparatus, device and storage medium to solve the problem of low trial efficiency in related technologies.

[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0006] According to a first aspect, a data processing method is provided, which may include:

[0007] Obtaining court records related to the case during the trial, which carry identity tags;

[0008] According to the trial records and the case filing information of the trial case, the trial basis information related to the trial case is obtained;

[0009] Determine the reasonableness score of the trial basis information based on the litigation claims in the trial case;

[0010] Determine the probability of success of the litigation request based on the rationality score and trial basis information.

[0011] According to a second aspect, a data interaction method is provided, which may include:

[0012] Receive requests for production of evidentiary information in court cases;

[0013] In response to a display request, obtaining a court record related to the court case, the court record carrying an identity tag;

[0014] Based on the court trial records and the case filing information of the court trial, determine the probability value of the success of the litigation request in the case filing information;

[0015] When the probability value meets the preset threshold, the evidence information of the trial case will be displayed separately; wherein the evidence information includes the trial record and / or case filing information corresponding to the probability value that meets the preset threshold.

[0016] According to a third aspect, a data processing device is provided, which may include:

[0017] An acquisition module, used to acquire court records related to the court case during the court trial, the court records carrying identity tags;

[0018] A processing module, used to obtain trial basis information related to the trial case based on the trial record and the case filing information of the trial case;

[0019] A calculation module for determining the rationality score of the trial basis information based on the litigation request of the trial case;

[0020] The prediction module is used to determine the probability value of the success of the litigation request based on the rationality score and trial basis information.

[0021] According to a fourth aspect, a data interaction device is provided, which may include:

[0022] An acquisition module, used to acquire court records related to the court case during the court trial, the court records carrying identity tags;

[0023] A processing module, used to obtain trial basis information related to the trial case based on the trial record and the case filing information of the trial case;

[0024] A calculation module for determining the rationality score of the trial basis information based on the litigation request of the trial case;

[0025] The prediction module is used to determine the probability value of the success of the litigation request based on the rationality score and trial basis information.

[0026] According to the fifth aspect, a computing device is provided, the device comprising at least one processor and a memory, the memory being used to store computer program instructions, and the processor being used to execute the program in 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.

[0027] According to the sixth aspect, a computer-readable storage medium is provided, on which a computer program is stored. If the computer program is executed in a computer, the computer is caused to execute the data processing method of the first aspect or the data interaction method of the second aspect.

[0028] In the scheme of the embodiment of the present invention, the probability value of the success of the litigation request is determined by obtaining the trial records of the trial case from multiple parties in the trial, and the litigation request based on the trial records, the original case filing information of the trial case, and the litigation request of the case filing information, so as to predict the judgment result of the trial case later. In this way, the probability value of the success of the litigation request can be determined based on a large amount of case vouchers and litigation requests, so as to obtain the predicted trial result of the trial case, provide a trial reference for the judge, and improve the accuracy of the judgment result of the trial case. Conversely, according to the probability value of the success of the litigation request, the evidence information corresponding to the probability value that meets the preset threshold can be quickly and accurately found in the massive case vouchers and litigation requests, so as to improve the credibility of the trial result, thereby improving the efficiency of the trial. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention may be better understood from the following description of specific embodiments of the present invention in conjunction with the accompanying drawings, wherein the same or similar reference numerals represent the same or similar features.

[0030] Figure 1 A schematic diagram showing an application scenario of court trial data processing according to an embodiment is shown;

[0031] Figure 2 A flow chart showing a data processing method according to an embodiment;

[0032] Figure 3 A schematic diagram showing a process of determining a trial record according to an embodiment is shown;

[0033] Figure 4 A schematic diagram of a process for determining memory information according to an embodiment is shown;

[0034] Figure 5 A schematic diagram showing a process of determining trial basis information according to an embodiment;

[0035] Figure 6 A schematic diagram of a process for determining a judgment result according to an embodiment is shown;

[0036] Figure 7 A flowchart showing another data processing according to one embodiment;

[0037] Figure 8 A flow chart showing a data interaction method according to an embodiment;

[0038] Fig. 9 A block diagram showing a data processing apparatus according to an embodiment;

[0039] Fig.10 A block diagram showing a data interaction device according to an embodiment;

[0040] Fig.11 A schematic diagram of the structure of a computing device according to an embodiment is shown. DETAILED DESCRIPTION

[0041] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present invention by illustrating examples of the present invention.

[0042] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such measured relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0043] In order to solve the problems of the prior art, an embodiment of the present invention provides a data processing method, apparatus, device and storage medium, as shown below.

[0044] First: Figure 1 As shown, the application scenario of the trial data processing provided by the embodiment of the present invention is explained.

[0045] First, the case filing information provided by the plaintiff and the defendant (e.g., the plaintiff's indictment and the defendant's defense statement) can be analyzed through the memory network to obtain memory information. Then, during the court hearing of the case, a display request for evidence information of the case is received, and in response to the display request, the trial record related to the case (e.g., trial voice data, trial text data, image data, etc.) is obtained, where the trial record carries an identity tag (e.g., Figure 1As shown, the judge, plaintiff or defendant corresponding to each trial voice data is marked). Furthermore, based on the trial record and the case filing information of the trial case, the probability value of the success of the litigation request in the case filing information is determined, and when the probability value meets the preset threshold, the evidence information of the trial case is displayed in a differentiated manner.

[0046] In this way, the probability value of the success of the litigation request can be determined through the trial records of the trial case obtained by multiple parties in the trial, and the litigation requests based on the trial records, the original case filing information of the trial case, and the case filing information, so as to predict the judgment result of the trial case later. The probability value of the success of the litigation request can be determined based on a large number of case vouchers and litigation requests, so as to obtain the predicted trial result of the trial case, provide a trial reference for the judge, and improve the accuracy of the judgment result of the trial case. Conversely, based on the probability value of the success of the litigation request, the evidence information corresponding to the probability value that meets the preset threshold can be quickly and accurately found in the massive case vouchers and litigation requests to improve the credibility of the trial result, thereby improving the efficiency of the trial.

[0047] Second: Based on the application scenarios in the above trial, the embodiments of the present invention respectively adopt three embodiments and combine Figure 2-Figure 8 The data processing method provided by the embodiment of the present invention is further described.

[0048] Embodiment 1:

[0049] Figure 2 A flow chart of a data processing method according to an embodiment is shown.

[0050] like Figure 2 As shown, the method may include steps 210 to 240: first, step 210, obtaining the trial record related to the trial case during the trial, the trial record carrying an identity tag; then, step 220, obtaining the trial basis information related to the trial case based on the trial record and the case filing information of the trial case; further, step 230, determining the rationality score of the trial basis information based on the litigation request of the trial case; then, step 240, determining the probability value of the success of the litigation request based on the rationality score and the trial basis information.

[0051] The following are detailed descriptions of the above steps:

[0052] First, step 210 is involved. In the embodiment of the present invention, obtaining the trial record can be performed through the following steps:

[0053] Receiving audio information of multiple subjects related to the trial case during the trial;

[0054] The audio information is labeled according to the preset role information to obtain the trial record. Alternatively, the trial recording data related to the trial case is received; the audio information is labeled according to the preset role information to obtain the trial record. Alternatively, the trial text data or image data related to the trial case is received, and the trial text data or image data is determined as the trial record. Among them, the above-mentioned trial records can all carry identity tags, that is, they are said by the judge, the plaintiff or the defendant, etc.

[0055] For example: Figure 3 As shown, 10 audio messages are received, and each of the 10 audio messages is labeled according to the preset role information, namely, judge, plaintiff, defendant or witness, so that among the 10 audio messages, the first audio message is spoken by the judge, the second audio message is spoken by the defendant, and so on until 10 audio messages are labeled.

[0056] Here, the annotation method provided by the embodiment of the present invention can process the audio information through a memory network, as shown below: convert the received audio information into a trial record, and input the trial record into a memory network corresponding to the trial record to obtain a dialogue sentence vector; based on the preset role vector and the dialogue sentence vector, determine the identity sentence vector carrying the identity tag corresponding to the trial record.

[0057] Next, in step 220, the trial basis information related to the trial case can be obtained through the attention mechanism based on the trial record and the case filing information. The specific steps are as follows:

[0058] According to the trial records, the attention mechanism is used to obtain the memory score of each memory information in the case filing information; through the memory score of each memory information and the trial records, the trial basis information is obtained.

[0059] The case filing information in the embodiment of the present invention may include prosecution information and defense information. Here, the steps of determining the memory information based on the prosecution information and the defense information may be as follows:

[0060] Inputting the prosecution information into the memory network corresponding to the prosecution information to obtain the prosecution sentence vector; and inputting the defense information into the memory network corresponding to the defense information to obtain the defense sentence vector;

[0061] The prosecution sentence vector and the defense sentence vector at a preset time are determined as memory information.

[0062] For example, Figure 4As shown, the text content of the prosecution information and the defense information is divided into sentences respectively to obtain the sentence vector corresponding to each sentence; the sentence vector is input into the memory network corresponding to the sentence vector to obtain the prosecution sentence vector and the defense sentence vector. Here, inputting the sentence vector into the memory network corresponding to the sentence vector can be understood as encoding the sentence vector through the bidirectional long and short-term memory network in the memory network to obtain the prosecution sentence vector and the defense sentence vector. Then, the target sentence latent vector (i.e., memory information) corresponding to the word information at the last moment in each prosecution sentence vector or defense sentence vector is represented as the vector of the entire sentence. Here, a memory array can be generated based on multiple target sentence latent vectors so that it can be read repeatedly when determining the trial basis information.

[0063] Thus, based on the memory information obtained above, step 220 may specifically include:

[0064] Through the memory score of each memory information and the trial record, the trial basis information is obtained, which may include:

[0065] According to the memory score of each memory information, a weighted sum is performed on multiple memory information in the case filing information to obtain a memory score for the trial record;

[0066] Based on the memory scores and the trial transcripts, trial basis information was obtained.

[0067] For example, following the above Figure 4 Examples include Figure 5 As shown, through Figure 3 The identity sentence vectors carrying identity tags in the Figure 4 The importance of each memory information (i.e., memory score) is determined by weighting and summing multiple memory information according to the memory score of each memory information to obtain the memory score for the identity sentence vector. Then, based on the memory score for the identity sentence vector and the dialogue sentence vector, the target dialogue sentence vector of the trial basis information is obtained.

[0068] In this way, the importance of each memory information in the case filing information to the trial case can be measured based on the trial records of multiple parties in the trial, that is, the memory score. Then, based on each trial record and the importance corresponding to each trial record, the trial basis information can be obtained. It can be understood that the trial basis information includes both the trial records in the trial and the case filing information with higher importance in the trial case.

[0069] Furthermore, with regard to step 230, in a possible embodiment, before executing step 230, the process may further include: inputting the trial basis information into a memory network corresponding to the trial basis information to obtain a target latent vector.

[0070] Based on this, step 230 may specifically include: obtaining a rationality score of the target latent vector through an attention mechanism according to the litigation request of the court case.

[0071] In this way, the trial basis information is scored according to the trial basis information and the litigation request obtained in step 220, and a rationality score that is closer to the opinions of the plaintiff, the defendant and the judge in the court trial record and case filing information is further obtained for each litigation request compared to step 220, so as to improve the accuracy of the judgment result.

[0072] For example, following the above Figure 5 Examples include Figure 6 As shown, the target dialogue sentence vector is input into the memory network corresponding to the target dialogue sentence vector to obtain the target latent vector; the importance of the target latent vector to the trial case is measured based on the vector corresponding to the litigation request, that is, the rationality score of the target latent vector.

[0073] Then, based on step 230, step 240 may specifically include:

[0074] When the target latent vector includes multiple latent vectors, the multiple latent vectors are weighted and summed according to the rationality score of each latent vector to obtain the rationality score of the target latent vector;

[0075] According to the rationality score of the target latent vector and the target latent vector, a prediction result vector is obtained;

[0076] The prediction result vector is input into the classification model to determine the probability value of the success of the litigation request, so as to obtain the predicted judgment result of the trial case.

[0077] For example, based on step 230, Figure 6 As shown, when the target latent vector includes multiple latent vectors, the multiple target latent vectors are weighted and summed according to each target latent vector and the rationality score corresponding to each target latent vector to obtain a prediction result vector; the prediction result vector is input into the softmax classification model to determine the probability value of the success of the litigation request, so as to predict the judgment result of the litigation request in the court case according to the probability value. Among them, the classification results mainly include: supporting the litigation request, partially supporting the litigation request, and rejecting the litigation request. Here, it should be noted that the target latent vector corresponds to each sentence, and this step is essentially to quantify each sentence to obtain the vector of the overall dialogue, that is, the prediction result vector, and then predict the judgment result of the litigation request of the court case according to the overall court record in the court trial. Of course, the embodiment of the present invention can also predict the judgment result of each litigation request in the court case for each litigation request.

[0078] Therefore, the probability value of the success of the litigation request is determined by obtaining the trial records of the trial case from multiple parties in the trial, and the litigation request based on the trial records, the original case filing information of the trial case, and the litigation request of the case filing information, so as to predict the judgment result of the trial case later. In this way, the probability value of the success of the litigation request can be determined based on a large amount of case vouchers and litigation requests, so as to obtain the predicted trial result of the trial case, provide a trial reference for the judge, and improve the accuracy of the judgment result of the trial case. Conversely, according to the probability value of the success of the litigation request, the evidence information corresponding to the probability value that meets the preset threshold can be quickly and accurately found in the massive case vouchers and litigation requests to improve the credibility of the trial result, thereby improving the efficiency of the trial.

[0079] Embodiment 2:

[0080] In court trials, the plaintiff, defendant, and judge may blur the focus of the dispute and ignore some details due to the large number of case vouchers and the complexity of the disputed content. Therefore, the predicted judgment result obtained above can be used to provide evidence information supporting the intermediate process of the judgment result, that is, the trial records, case filing information, and litigation requests related to the trial case in the court trial. According to the actual situation, the evidence information supporting the trial result can be highlighted to improve the credibility of the predicted trial result.

[0081] In this way, unlike the above-mentioned embodiment 1, the method provided by the embodiment of the present invention may also include: displaying evidence information related to the probability value and / or rationality score of the success of the litigation request in at least one information of the trial record, case filing information and litigation request related to the trial case.

[0082] Combine the following Figure 7 Provide detailed explanation.

[0083] Figure 7 A flow chart showing another data processing method according to an embodiment is shown.

[0084] like Figure 7 As shown, the method may include steps 710 to 750: first, step 710, obtaining the trial record related to the trial case during the trial, wherein the trial record carries an identity tag; then, step 720, obtaining the trial basis information based on the trial record and the case filing information of the trial case; secondly, step 730, determining the rationality score of the trial basis information through the litigation request of the trial case; further, step 740, determining the probability value of the success of the litigation request based on the rationality score and the trial basis information; then, step 750, displaying the evidence information related to the probability value, wherein the evidence information is at least one of the trial record, the case filing information and the litigation request.

[0085] Among them, the method steps in step 710 to step 740 are the same as those described above. Figure 2 The principles involved in the method steps in step 210-step 240 are the same. Therefore, the specific contents of step 710 to step 740 can refer to the description in the above step 210-step 240 and will not be repeated here.

[0086] Then, step 750 is involved, in which evidence information related to the probability value and / or the rationality score of the success of the litigation request is marked in at least one of the court record, case filing information and litigation request related to the court case;

[0087] The evidence information is visualized and displayed in a differentiated manner in at least one of the court trial record, case filing information, and litigation request.

[0088] Continue with the above Figure 6 In the example shown, when the predicted judgment result is "supporting the litigation request", the evidence information related to "supporting the litigation request" can be highlighted in at least one of the trial records, case filing information and litigation request, and the rationality score of the evidence information is higher than other information that is not highlighted.

[0089] Alternatively, the evidence information is displayed in the chronological order in which it was generated, and information irrelevant to the "supporting litigation request" result is not displayed.

[0090] Therefore, the evidence information is highlighted or marked to highlight the information related to the predicted trial results, which is used to assist judges in quickly and accurately finding details related to the trial case from the massive amount of case evidence, thereby ensuring the credibility of the predicted trial results and improving the efficiency of the trial.

[0091] Embodiment 3:

[0092] In addition, based on the above embodiment 2, the embodiment of the present invention also provides a possible embodiment, that is, a data interaction method, which can also be applied to the above Figure 1 In the scenario shown, the data interaction method may specifically include steps 810 to 840, which are specifically as follows:

[0093] Step 810, receiving a request for displaying evidence information of a court case during a court trial.

[0094] Step 820, in response to the display request, obtain the trial record related to the trial case, the trial record carries an identity tag.

[0095] Here, the content described in this step is the same as the content involved in the above step 210 in principle. For details, please refer to the content shown in the above step 210, which will not be repeated here.

[0096] Step 830, based on the court trial record and the case filing information of the court trial, determine the probability value of the success of the litigation request in the case filing information.

[0097] Among them, this step may specifically include: obtaining trial basis information related to the trial case based on the trial records and the filing information of the trial case; determining the rationality score of the trial basis information based on the litigation request in the filing information; determining the probability value of the success of the litigation request based on the rationality score and the trial basis information.

[0098] In this way, the content described in this step is the same in principle as the content involved in the above steps 220 to 240. For details, please refer to the content shown in the above steps 210 to 240, which will not be repeated here.

[0099] Step 840, when the probability value meets the preset threshold, the court trial case evidence information is displayed in a differentiated manner; wherein the evidence information includes the court trial record and / or case filing information corresponding to the probability value that meets the preset threshold.

[0100] Here, the evidence information corresponding to the probability value meeting the preset threshold can be used as evidence for the judgment result of the trial case, and the above evidence information can be displayed separately to provide trial reference for the judge, so as to improve the accuracy of the judgment result of the trial case.

[0101] Third, the embodiment of the present invention also provides a structure of a data processing device corresponding to the above data processing method. Figure 8 Provide detailed explanation.

[0102] Fig. 9 A block diagram of a data processing apparatus according to an embodiment is shown.

[0103] like Fig. 9 As shown, the data processing device 90 may specifically include:

[0104] An acquisition module 901 is used to acquire court records related to the court case during the court trial, where the court records carry an identity tag;

[0105] Processing module 902, for obtaining trial basis information related to the trial case according to the trial record and the case filing information of the trial case;

[0106] A calculation module 903 is used to determine the rationality score of the trial basis information according to the litigation request of the trial case;

[0107] Prediction module 904 is used to determine the probability value of the success of the litigation request based on the rationality score and the trial basis information.

[0108] In one possible embodiment, the processing module 902 may be specifically used to obtain a memory score of each memory information in the case filing information through an attention mechanism according to the trial record;

[0109] The trial basis information is obtained through the memory score of each memory information and the trial records.

[0110] Based on this possibility, the calculation module 903 of the embodiment of the present invention can be specifically used to perform weighted summation of multiple memory information in the case filing information according to the memory score of each memory information, so as to obtain the memory score for the trial record;

[0111] Based on the memory scores and the trial transcripts, trial basis information was obtained.

[0112] Here, the case filing information mentioned above may specifically include prosecution information and defense information. Based on this, the data processing device 90 may also include: a first generation module 905, which is used to input the prosecution information into the memory network corresponding to the prosecution information to obtain the prosecution sentence vector; and input the defense information into the memory network corresponding to the defense information to obtain the defense sentence vector;

[0113] The prosecution sentence vector and the defense sentence vector at a preset time are determined as memory information.

[0114] In another possible embodiment, the data processing device 90 may further include: a second generation module 906, which is used to input the trial basis information into the memory network corresponding to the trial basis information of the second generation module 906 to obtain a target latent vector. In this way, based on this situation, the calculation module 903 can be specifically used to obtain a rationality score of the target latent vector through an attention mechanism according to the litigation request of the trial case.

[0115] Based on this, the prediction module 904 can be specifically used to, when there are multiple target latent vectors, perform weighted summation on the multiple target latent vectors according to each target latent vector and the rationality score corresponding to each target latent vector to obtain a prediction result vector;

[0116] The prediction result vector is input into the classification model to determine the probability value of the success of the litigation request in order to obtain the predicted judgment result of the trial case.

[0117] In addition, in another possible embodiment, the data processing device 90 may further include a display module 907, which is used to mark the evidence information related to the probability value and / or the rationality score of the success of the litigation request in at least one of the court trial records, case filing information and litigation requests related to the court trial case;

[0118] Visualize and display the evidence information.

[0119] In summary, in the scheme of the embodiment of the present invention, the probability value of the success of the litigation request is determined by obtaining the trial records of the trial case from multiple parties in the trial, and the litigation request based on the trial records, the original case filing information of the trial case, and the litigation request of the case filing information, so as to predict the judgment result of the trial case later. In this way, the probability value of the success of the litigation request can be determined based on a large amount of case vouchers and litigation requests, so as to obtain the predicted trial result of the trial case, provide a trial reference for the judge, and improve the accuracy of the judgment result of the trial case. Conversely, according to the probability value of the success of the litigation request, the evidence information corresponding to the probability value that meets the preset threshold can be quickly and accurately found in the massive case vouchers and litigation requests, so as to improve the credibility of the trial result, thereby improving the efficiency of the trial.

[0120] In addition, the embodiment of the present invention also provides a data interaction device, such as Fig.10 As shown, the device 100 shows a block diagram of a data interaction device. The data interaction device 100 may specifically include:

[0121] The acquisition module 1001 is used to acquire the court records related to the court case during the court trial, and the court records carry identity tags;

[0122] Processing module 1002, for obtaining trial basis information related to the trial case according to the trial record and the case filing information of the trial case;

[0123] A calculation module 1003 is used to determine the rationality score of the trial basis information according to the litigation request of the trial case;

[0124] Prediction module 1004 is used to determine the probability value of the success of the litigation request based on the rationality score and the trial basis information.

[0125] Among them, the acquisition module 1001 in the embodiment of the present invention can be specifically used to receive multimedia data related to the trial case in response to a display request; identify the multimedia data according to preset identity information to obtain the trial record; wherein the multimedia data includes at least one of the following: trial voice data, trial text data, and image data.

[0126] Here, the trial voice data includes voice data received during the trial and / or trial recording data.

[0127] In addition, in a possible embodiment, the data interaction device 100 may also include a storage module 1005 for storing the evidence information displayed differently for use in verifying court cases.

[0128] Fourth, the embodiment of the present invention also provides a structure of a computing device corresponding to the above data processing method or data interaction method. Fig.11 Provide detailed explanation.

[0129] Fig.11 A schematic diagram of the structure of a computing device according to an embodiment is shown.

[0130] like Fig.11 , which is a structural diagram of an exemplary hardware architecture of a computing device capable of implementing the data processing method or data interaction method and apparatus according to an embodiment of the present invention.

[0131] The device may include a processor 1101 and a memory 1102 storing computer program instructions.

[0132] 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.

[0133] The memory 1102 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1102 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 1102 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 1102 may be inside or outside the integrated gateway device. In a specific embodiment, the memory 1102 is a non-volatile solid-state memory. In a specific embodiment, the memory 1102 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0134] The processor 1101 implements any one of the data processing methods or data interaction methods in the above embodiments by reading and executing computer program instructions stored in the memory 1102 .

[0135] The transceiver 1103 is mainly used to implement the communication between the devices in the embodiments of the present invention or with other devices.

[0136] In one example, the device may further include a bus 1104. Fig.11As shown, the processor 1101, the memory 1102 and the transceiver 1103 are connected via a bus 1104 and communicate with each other.

[0137] Bus 1104 includes hardware, software or both.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 1104 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0138] Fifth, an embodiment of the present invention also provides a computer-readable storage medium corresponding to the above-mentioned sound source localization method.

[0139] In a possible embodiment, the embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the steps of the sound source localization method of the embodiment of the present invention.

[0140] It should be clear that the present invention is not limited to the specific configurations and processes described in the above embodiments and shown in the figures. For the convenience and brevity of description, a detailed description of the known methods is omitted here, and the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, which will not be repeated here.

[0141] Those skilled in the art can clearly understand that the method process of the present invention is not limited to the specific steps described and shown. Any technician familiar with the technical field, after understanding the spirit of the present invention, can make various changes, modifications and additions, or equivalent substitutions and change the order of steps within the technical scope disclosed by the present invention. These modifications or substitutions should be included in the protection scope of the present invention.

Claims

1. A data processing method, wherein: include: Acquire a court record related to the court case during the court trial, wherein the court record carries an identity tag, wherein the court record includes at least one of the following: court trial voice data, court trial text data, and image data; Obtaining trial basis information related to the trial case based on the trial record and the case filing information of the trial case; Inputting the trial basis information into a memory network corresponding to the trial basis information to obtain a target latent vector; determining a rationality score of the target latent vector based on a vector corresponding to the litigation request; Determine a prediction result vector according to the rationality score of the target latent vector and the target latent vector; process the prediction result vector using a classification model to determine the probability value of success of the litigation request; The method further includes: determining evidence information related to the probability value of success of the litigation request and / or the rationality score from at least one of the trial records related to the trial case, the case filing information and the litigation request, wherein the evidence information is used to provide trial reference.

2. The method according to claim 1, wherein: According to the trial record and the case filing information of the trial case, the trial basis information related to the trial case is obtained, including: Obtaining a memory score for each piece of memory information in the case filing information through an attention mechanism according to the trial record; The trial basis information is obtained through the memory score of each memory information and the trial record.

3. The method according to claim 2, wherein: The trial basis information is obtained through the memory score of each memory information and the trial record, including: Performing weighted summation of multiple memory information in the case filing information according to the memory score of each memory information to obtain a memory score for the trial record; The trial basis information is obtained based on the memory score of the trial record and the trial record.

4. The method according to claim 2, wherein: The case filing information includes prosecution information and defense information, and the method further includes: Inputting the prosecution information into a memory network corresponding to the prosecution information to obtain a prosecution sentence vector; and inputting the defense information into a memory network corresponding to the defense information to obtain a defense sentence vector; The prosecution sentence vector and the defense sentence vector at a preset time are determined as the memory information.

5. The method according to claim 1, wherein: The determining the rationality score of the target latent vector based on the vector corresponding to the litigation request includes: Through the attention mechanism, the rationality score of the target latent vector is obtained according to the vector corresponding to the litigation request.

6. The method according to claim 1, wherein: The step of obtaining a prediction result vector according to the rationality score of the target latent vector and the target latent vector includes: When the target latent vector is multiple, Performing a weighted summation of multiple target latent vectors according to each target latent vector and a rationality score corresponding to each target latent vector; Based on the weighted summed rationality scores, the prediction result vector is determined.

7. The method according to claim 6, wherein: The method further comprises: Marking the evidence information related to the probability value of success of the litigation request and / or the rationality score in at least one of the court record related to the court case, the case filing information, and the litigation request; The evidence information is visualized and displayed.

8. A data interaction method, wherein: include: Receive requests for production of evidentiary information in court cases; In response to the display request, obtaining a trial record related to the trial case, wherein the trial record carries an identity tag, wherein the trial record includes at least one of the following: trial voice data, trial text data, and image data; Based on the trial record and the case filing information of the trial case, obtaining the trial basis information related to the trial case; Inputting the trial basis information into a memory network corresponding to the trial basis information to obtain a target latent vector; determining a rationality score of the target latent vector based on a vector corresponding to the litigation request; Obtaining a prediction result vector according to the rationality score of the target latent vector and the target latent vector; processing the prediction result vector using a classification model to obtain a probability value of success of the litigation request; Determine, from the court record related to the court case, the case filing information, and at least one of the information of the litigation request, evidence information related to the probability value of success of the litigation request and / or the rationality score, wherein the evidence information is used to provide a reference for the trial; When the probability value meets a preset threshold, the evidence information of the trial case is displayed distinctively; wherein the evidence information includes the trial record and / or case filing information corresponding to the probability value that meets the preset threshold.

9. The method according to claim 8, wherein: The step of obtaining, in response to the display request, a court trial record related to the court trial case includes: In response to the display request, receiving multimedia data related to the court case; Marking the multimedia data according to preset identity information to obtain the trial record; Among them, the multimedia data includes at least one of the following: the trial voice data, the trial text data, and the image data.

10. The method according to claim 9, wherein: The court trial voice data includes voice data received during the court trial and / or court trial recording data.

11. The method according to claim 8, wherein: The method further comprises: The evidence information displayed differently is stored for use in verifying the court case.

12. A data processing device, wherein: include: An acquisition module, used to acquire a trial record related to the trial case during the trial, wherein the trial record carries an identity tag, wherein the trial record includes at least one of the following: trial voice data, trial text data, and image data; A processing module, used to obtain trial basis information related to the trial case according to the trial record and the case filing information of the trial case; A calculation module, used for inputting the trial basis information into a memory network corresponding to the trial basis information to obtain a target latent vector; and determining a rationality score of the target latent vector based on a vector corresponding to the litigation request; A prediction module, used to obtain a prediction result vector according to the rationality score of the target latent vector and the target latent vector; and to process the prediction result vector using a classification model to obtain a probability value of success of the litigation request; The device is also used to: determine the evidence information related to the probability value of success of the litigation request and / or the rationality score from the trial records related to the trial case, the case filing information and at least one information of the litigation request, wherein the evidence information is used to provide trial reference.

13. A data interaction device, wherein: include: A transceiver module, used to receive a request for display of evidence information of a case in court during a trial; An acquisition module, configured to acquire, in response to the display request, a trial record related to the trial case, wherein the trial record carries an identity tag, wherein the trial record includes at least one of the following: trial voice data, trial text data, and image data; A determination module is used to obtain trial basis information related to the trial case based on the trial record and the case filing information of the trial case; input the trial basis information into a memory network corresponding to the trial basis information to obtain a target latent vector; determine the rationality score of the target latent vector based on the vector corresponding to the litigation request; obtain a prediction result vector based on the rationality score of the target latent vector and the target latent vector; use a classification model to process the prediction result vector to obtain a probability value of success of the litigation request; A display module, configured to display the court trial case evidence information in a differentiated manner when the probability value meets a preset threshold; wherein the evidence information includes court trial records and / or case filing information corresponding to the probability value meeting the preset threshold; The device is also used to determine the evidence information related to the probability value of success of the litigation request and / or the rationality score from the trial records related to the trial case, the case filing information and at least one information of the litigation request, wherein the evidence information is used to provide trial reference.

14. A computing device, wherein: The device includes at least one processor and a memory, the memory is used to store computer program instructions, and the processor is used to execute the program in the memory to control the computer device to implement the data processing method as described in any one of claims 1 to 7, or to implement the data interaction method as described in any one of claims 8 to 11.

15. A computer-readable storage medium having a computer program stored thereon, wherein: If the computer program is executed in a computer, the computer is enabled to execute the data processing method described in any one of claims 1 to 7, or to implement the data interaction method described in any one of claims 8 to 11.

Images