CN110765263A

CN110765263A - Display method and device for retrieval case

Info

Publication number: CN110765263A
Application number: CN201910935571.7A
Authority: CN
Inventors: 陈朗
Original assignee: Ping An Zhitong Consulting Co Ltd Shanghai Branch
Current assignee: Ping An Zhitong Consulting Co Ltd Shanghai Branch
Priority date: 2019-09-29
Filing date: 2019-09-29
Publication date: 2020-02-07
Anticipated expiration: 2039-09-29
Also published as: CN110765263B

Abstract

The application is applicable to the technical field of computer application, and provides a display method and a device for a retrieval case, wherein the display method comprises the following steps: the method comprises the steps of conducting preliminary retrieval on historical cases according to case information in retrieval information to obtain first cases of preliminary screening results, then determining matching degrees of judges and parties in the cases to be screened preliminarily according to judge information and party information in the retrieval information, determining display weights of corresponding party figures and judge figures according to the matching degrees, determining display sequences of the first cases according to comprehensive weights obtained by the two figures, and displaying each first case correspondingly. Not only screening redundant cases, accurately searching cases matched with the retrieval information, determining the case display sequence according to the retrieval information and the matched cases, and correspondingly displaying each first case according to the display sequence, so that the retrieval personnel can acquire the most related historical cases at the first time, and the information acquisition efficiency and accuracy of the retrieval personnel are improved.

Description

Display method and device for retrieval case

Technical Field

The application belongs to the technical field of computer application, and particularly relates to a display method and device for a retrieval case.

Background

When a judge judges a case, the judge is usually assisted by referring to similar cases of past date, namely case retrieval, aiming at uncertain case facts or cases with serious cases at the judge stage.

Similar cases are retrieved in the prior art through an intelligent search mode, namely, based on a general search engine technology, a large amount of professional manual labeling work is assisted, existing open legal referee documents are classified and identified, different types of document classifications are formed, and when the classification identifications are retrieved, the corresponding legal referee documents are displayed. However, this method needs to consume a lot of manpower and financial resources, usually a large number of cases with low matching degree are still presented to the judge, the judge needs to spend a lot of time to screen the required cases, and after the searched cases are obtained by screening, the display sequence of the searched cases is messy, and the judge cannot timely obtain the case most related to the expectation of the searched cases according to the displayed cases, so the problem that the display effect of the search result is not good in the prior art, and the case search efficiency is low is caused.

Disclosure of Invention

The embodiment of the application provides a display method and a display device for searching cases, which can solve the problem that the case searching efficiency is low due to poor display effect of a searching result.

In a first aspect, an embodiment of the present application provides a method for displaying a retrieved case, including:

in a possible implementation manner of the first aspect, the case search information is obtained; the retrieval information comprises case information, judge information and party information; if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case; determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree; and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait, and displaying the first cases according to the comprehensive weight score.

It should be understood that the first case of the preliminary screening result is obtained by preliminarily searching the historical cases according to the case information in the search information, the matching degree of the judge and the party in the preliminary screening case is determined according to the judge information and the party information in the search information, the display weight of the corresponding party portrait and the judge portrait is determined according to the matching degree, the display sequence of the first case is determined according to the comprehensive weight obtained by the two portraits, and each first case is correspondingly displayed according to the display sequence. Not only screening redundant cases, accurately searching cases matched with the retrieval information, and determining the case display sequence according to the retrieval information and the matched cases, and correspondingly displaying each first case according to the display sequence, so that the retrieval personnel can acquire the most related historical cases at the first time, and the information acquisition efficiency and the accuracy of the retrieval personnel are improved.

In a second aspect, an embodiment of the present application provides a display device for retrieving cases, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the following steps when executing the computer program:

acquiring the retrieval information of a case; the retrieval information comprises case information, judge information and party information;

if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case;

determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree;

and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait, and displaying the first cases according to the comprehensive weight score.

In a third aspect, an embodiment of the present application provides a display device for retrieving cases, including:

the acquisition unit is used for acquiring the retrieval information of the case; the retrieval information comprises case information, judge information and party information;

the calculation unit is used for calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case if the first case matched with the case information exists in a preset case library;

the determining unit is used for determining the display weight of the first case corresponding to the preset judge portrait according to the judge matching degree and determining the display weight of the first case corresponding to the preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree;

a weighting unit for calculating a composite weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait;

and the display unit is used for determining the display sequence of each first case according to the comprehensive weight score and correspondingly displaying each first case according to the display sequence.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method of the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer program product, which, when running on a terminal device, causes the terminal device to execute the method for displaying a retrieved case according to any one of the first aspect.

It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.

Compared with the prior art, the embodiment of the application has the advantages that: the method comprises the steps of conducting preliminary retrieval on historical cases according to case information in retrieval information to obtain first cases of preliminary screening results, then determining matching degrees of judges and parties in the cases to be screened preliminarily according to judge information and party information in the retrieval information, determining display weights of corresponding party figures and judge figures according to the matching degrees, finally determining display sequences of the first cases according to comprehensive weights obtained by the two figures, and correspondingly displaying each first case according to the display sequences. Not only screening redundant cases, accurately searching cases matched with the retrieval information, and determining the case display sequence according to the retrieval information and the matched cases, and correspondingly displaying each first case according to the display sequence, so that the retrieval personnel can acquire the most related historical cases at the first time, and the information acquisition efficiency and the accuracy of the retrieval personnel are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

FIG. 1 is a flowchart illustrating a method for displaying a retrieved case according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a case-searching display method according to a second embodiment of the present application;

FIG. 3 is a schematic diagram of a display device for searching cases according to a third embodiment of the present application;

fig. 4 is a schematic diagram of a display device for searching cases according to the fourth embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to" determining "or" in response to detecting ". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

Referring to fig. 1, fig. 1 is a flowchart of a display method for retrieving cases according to an embodiment of the present application. The main implementation body of the display method for searching cases in the embodiment is a device with a case searching function, including but not limited to a computer, a server, a tablet computer or a terminal. The display method of the retrieval case as shown in the figure may include the steps of:

s101: acquiring the retrieval information of a case; the retrieval information comprises case information, judge information and party information.

In many cases, the retrieval and review of historical cases plays a very important role in the analysis and decision of new cases. For example, when a judge judges a case, the judge is usually assisted by referring to similar cases of past times, namely, class retrieval, for uncertain case facts or cases with serious cases at the judge stage.

When a user searches, the searching information of a case is firstly obtained. The search information in this embodiment includes case information, judge information, and party information. Specifically, the case information includes information such as case reason, case details, decision results, and the like, the judge information is used to indicate information of judges participating in the trial, such as identity information, professional information, and the party information is used to indicate information of parties related to the case, such as identity information, historical case information related thereto, and the like, and this is not limited herein.

Optionally, in this embodiment, the manner of obtaining the retrieval information of the case may be text input, or may also be that the user performs voice input, and the retrieval information is obtained by performing voice recognition, which is not limited herein.

S102: if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case.

In this embodiment, a case library is preset, which includes all processed history cases and detailed information of each history case. And identifying keywords for representing the historical case information according to the case information in the retrieval information and the content of the historical case in the case library, and matching the keywords with the case information in the retrieval information to determine a primary screening case matched with the case information, namely a first case.

It should be noted that the preliminary screening cases in this embodiment are used to indicate cases matched with case information, and are not related to judge information, party information, or case generation time.

Further, step S102 specifically includes S1021 to S1024:

s1021: and screening the keywords of the historical cases in the case library.

When a first case matched with case information is screened in a case library, word segmentation processing is firstly carried out on the case information and the content of a historical case, and keywords representing the case information in the historical case are determined. The word segmentation process in this embodiment may be to identify the word segmentation in the case information according to a preset word segmentation dictionary. It should be noted that, in this embodiment, the keywords of the history case include at least two keywords, and the keywords are used to represent important information such as case information of the history case.

Furthermore, the case information and the content of the historical case can be filtered, and the virtual words and functional words which have no practical meaning and are frequently used in the text of the historical case, such as words of ' yes ', and ' bar ', but also, the word, that ' and the like can be filtered. Because they often overwhelm the truly useful words, the existing stop word list is used to remove the words which have little contribution to the text representation, the occurrence times of the rest words in the text are counted, and only one term is reserved for the repeatedly-appearing words, so that the redundant words in case information are reduced.

Optionally, when the text information base of the history case is very large and the information is relatively stable, establishing an index structure that fully covers the text will greatly improve the search speed. In the full-text index, the index establishment of some useless entries wastes the index space of the system and affects the system performance, so that indexes are not necessarily established for all entries appearing in the text, but some more important entries are selected to establish the index, and after the text word segmentation and the particle filtering processing, a proper feature extraction method can be used for screening the keywords in the historical cases.

Further, step S1021 includes: and identifying the participles in the historical case and the frequency of each participle in the historical case, namely the frequency of each participle in the historical case, according to a preset participle mode. Calculating case frequency of the participles appearing in the historical cases according to the frequency; the case frequency is used for representing the frequency of the occurrences of the participles in the historical cases. Identifying the case number of the historical cases comprising the word segmentation, and calculating case density according to the case number; the case density is used for representing the density of the historical cases related to the participle in the case library; and calculating word segmentation weights of the segmented words according to the case frequency and the case density, and identifying the corresponding segmented words as the keywords when the word segmentation weights are greater than the preset word segmentation weights.

Specifically, the case frequency of the participle in the historical case is calculated through the following formula:

wherein i is used to represent a keyword, f_iIndicating the number of times the keyword i appears in the history case and N indicating the number of history cases. The case frequency in this embodiment is used to indicate the proportion of the number of occurrences of each participle in a single history case, i.e., the frequency.

Identifying the case number of the historical cases comprising the participle, and calculating the case density through the following formula: df is a_i＝log(n/N)；

Wherein n represents the case number of the history cases with the keywords i; the case density in this embodiment is used to indicate the density of the historical case related to the word segmentation in the case library, that is, the greater the density of the hotness case of the word segmentation in the historical case, the higher the hotness of the information corresponding to the word segmentation.

Calculating a segmentation weight of the segmentation by the following formula: i is_i＝α×tf_i×df_iThe weight coefficient corresponding to the participle at the document position of the history case is represented by x log (1+ l), wherein l represents the character string length of the participle, and α represents the corresponding weight coefficient of the participle at the document position of the history case, exemplarily, when the participle is located in a title, a summary segment, and a keyword table in case information, α is set to 1, and when the participle is located in a segment head, a segment tail, and a conclusive sentence, α is set to 0.5, otherwise, α is set to 0.

S1022: and determining the matching degree between each historical case and the case information according to the keywords of the historical cases and the keywords in the case information.

In the embodiment, the matching degree of the case information in the retrieval information and the keywords in the historical case text is calculated to serve as the matching degree between each historical case and the case information. The specific calculation method is as follows:

wherein D1 is used to represent the search information; d2 is used for representing historical cases; i is₁For indicating cases in search informationInformation; i is₂For representing keywords in the text of the historical case.

S1023: if the matching degree corresponding to a first historical case is larger than a preset matching degree threshold value, identifying the first historical case as the first case;

after the matching degree between the historical case and the case information is obtained through calculation, the greater the matching degree is, the greater the similarity is, and the smaller the similarity is otherwise; if the two vectors are identical, the matching degree is 1. Setting a filtering threshold, if Sim (D1, D2) is smaller than the filtering threshold, D1 and D2 are irrelevant; otherwise, it is correlated.

In this embodiment, a matching degree threshold is preset and used for measuring a matching degree between the historical cases and the case information, and when the matching degree corresponding to the first historical case is greater than the preset matching degree threshold, the first historical case is identified as the first case. In addition, the first case can be judged through quantity, namely when the quantity of the keywords related between the keywords in the historical case and the case information is larger than a preset quantity threshold value, the first case is the first case.

S1024: and calculating the judge matching degree between the judge information and the judge information in the first case and the party matching degree between the party information and the party information in the first case.

After the preliminary screening cases that conform to the case information are screened, the matching degrees between these cases and the judge information and the party information are calculated, and the specific matching degree calculation mode is the same as the matching degree calculation mode in steps S1022 and S1023, which is not described herein again.

S103: determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree.

In the embodiment, the judge portrait and the party portrait corresponding to each historical case are respectively constructed in advance according to the judge information and the party information in the historical case information, so that the information of one case is represented vividly and comprehensively through the judge portrait and the party portrait. After the matching degree of the party and the matching degree of the legal organ are obtained, the display weight of the portrait is determined according to the matching degree of the party and the matching degree of the legal organ. The display weight in this embodiment is proportional to the matching degree, and the display weight corresponding to the matching degree is larger as the matching degree is larger, and when the display weight of the image of the judge and the display weight of the image of the person concerned are determined, the display weight of the image corresponding to the matching degree is determined according to the size of the matching degree, and the display weight based on the information of the judge and the information of the person concerned in each first case is determined.

Further, in order to be closer to the requirement of a searcher, after the display sequence based on all the information in each historical case is determined, fine adjustment is performed again according to the matching degree calculated by the data information corresponding to each small label based on the weight under each large category; the result of the large classification includes the party information and the official information, and the small label is used for representing the party label and the official label set in the party information and the official information respectively.

Specifically, the matching degree between the data information corresponding to each label in the history case information and the retrieval information is calculated, a small label with high matching degree with the retrieval information is determined, and the portrait display weight corresponding to the small label is increased. For example, if the data information corresponding to the name tag of the party in a history case is "zhangsan", and the information of the party included in the search information is "zhangsan, liqing", the matching degree corresponding to the name tag of the party is 1, that is, the maximum, and the display weight of the history case is increased based on the small tag of the name of the party.

S104: and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait.

In this embodiment, the display weight of the facial image and the display weight of the person of interest may be weighted and averaged to calculate the integrated weight score of each first case, and the specific weight value may be set by the search person.

Illustratively, the composite weight score (20) ═ 1 × case similarity score (10) +0.5 × sense matching score (10) +0.5 × principal matching score (10); further, based on the weight in each large category, the matching degree calculated from the data information corresponding to each small label is fine-tuned again, for example, the subject matching degree score (10 points) is 1 times the subject name (1 point) +1 times the subject id number (3 points) +1 times the judgment date (2 points) +1 times the judgment court (2 points).

S105: and determining the display sequence of each first case according to the comprehensive weight score, and correspondingly displaying each first case according to the display sequence.

After the composite weight score is obtained, the higher the composite weight score is, the earlier the display order of the corresponding first case is. In this embodiment, the first cases may be sorted according to the order from high to low according to the magnitude of the composite weight score, the obtained sort is a display order of the first cases, and finally, each first case is correspondingly displayed according to the display order.

According to the scheme, the retrieval information of the case is obtained; the retrieval information comprises case information, judge information and party information; if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case; determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree; and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait, and displaying the first cases according to the comprehensive weight score. The method comprises the steps of conducting preliminary retrieval on historical cases according to case information in retrieval information to obtain first cases of preliminary screening results, then determining matching degrees of judges and parties in the cases to be screened preliminarily according to judge information and party information in the retrieval information, determining display weights of corresponding party figures and judge figures according to the matching degrees, finally determining display sequences of the first cases according to comprehensive weights obtained by the two figures, and correspondingly displaying each first case according to the display sequences. Not only screening redundant cases, accurately searching cases matched with the retrieval information, and determining the case display sequence according to the retrieval information and the matched cases, and correspondingly displaying each first case according to the display sequence, so that the retrieval personnel can acquire the most related historical cases at the first time, and the information acquisition efficiency and the accuracy of the retrieval personnel are improved.

Referring to fig. 2, fig. 2 is a flowchart of a display method for retrieving cases according to an embodiment of the present application. The main implementation body of the display method for searching cases in the embodiment is a device with a case searching function, including but not limited to a computer, a server, a tablet computer or a terminal. The display method of the retrieval case as shown in the figure may include the steps of:

s201: acquiring the retrieval information of a case; the retrieval information comprises case information, judge information and party information.

The manner of acquiring the search information of the case in step S201 of this embodiment is completely the same as the manner of acquiring the search information of the case in S101 in the embodiment corresponding to fig. 1, and specific reference may be made to the related description of S101 in the embodiment corresponding to fig. 1, and details thereof are not repeated here.

Further, after step S201, the method further includes:

if the case library does not have a first case matched with the case information, determining a second case corresponding to judge information and party information in the retrieval information in the case library; calculating the matching degree between the case information of the second case and the retrieval information; and displaying the second case according to the matching degree.

Specifically, when the first case matching the case information is not found in the case library, it is indicated that the case information in the search information does not have a similar corresponding case in the case library, and therefore, the present embodiment performs a re-search through the information of the judge and the party, that is, determines the second case corresponding to the information of the judge and the information of the party in the search information in the case library, calculates the matching degree between the case information of the second case and the search information, and displays the second case according to the matching degree.

When the matching degree between the case information of the second case and the search information is calculated, the matching degree between the party information in the case information and the party information in the search information and the matching degree between the judge information in the case information and the judge information in the search information are calculated, the matching between the two is averaged to obtain the final matching degree, and finally the second case is displayed in descending order according to the final matching degree.

S202: if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case.

In this embodiment, the implementation manner of S202 is completely the same as that of S102 in the embodiment corresponding to fig. 1, and reference may be specifically made to the related description of S102 in the embodiment corresponding to fig. 1, which is not repeated herein.

S203: and acquiring historical case information.

The history case information includes all case contents, that is, the party information, the judge information and the case information. Wherein the party information may include the name of the party, the identity card number of the party, the title, the decision date, the decision court, etc.; the judge information may include the name of the judge, the work time, the competent court, the historical case, etc., and is not limited herein.

S204: and extracting judge information and party information from the historical case information.

The history case information acquired in this embodiment may be in a text form, for example, a table form, which is not limited herein, and various types of information in the history case are displayed in the text according to a certain sequence and format, so that the judge information and the party information in the history case information may be extracted by identifying a text format or a text position in the text.

S205: and constructing the judge portrait according to the judge information, and constructing the party portrait according to the party information.

The process of constructing the portrait is divided into two parts, namely, a tag library is constructed by utilizing historical case information, and a judge portrait and a party portrait are respectively constructed by utilizing judge information and party information.

Further, step S205 includes S2051 to S2052:

s2051: extracting a judge label value corresponding to a preset judge label from the judge information, and constructing the judge portrait according to the judge label value; the judge label comprises a first identity label, a first time label and a post label;

when the label library is constructed by the historical case information, firstly, the label corresponding to each information type is generated according to the information types, and then all the labels are constructed into the label library. The tags in the tag library can be divided into two broad categories, namely, principal tags and judge tags. Wherein the judge label comprises: a first identity tag, a first time tag, and a job tag, etc. Specifically, the first identity tag correspondingly comprises data about names, identities and the like of the judges, wherein the data can be Chinese names, English names, certificate numbers, qualification certificates and the like; the first time tag corresponds to data including the time of the legal officer's job and the case processing time; the job label correspondence includes information about the legal title, the processed history case, etc., which is not limited herein.

According to the label names of all labels in the label library, determining the information characteristics corresponding to each label name, wherein the information characteristics in the embodiment are used for representing the data type, the character form, the character keywords and the like of the data information corresponding to each label name, and identifying the data information corresponding to each label in each historical case information through the information characteristics. After the data information corresponding to all the labels in the judge label is determined, the judge portrait is generated according to the data information corresponding to each label in the judge label.

Further, after the data information corresponding to all the tags in the judge tag is determined, the judge matching degree can be calculated according to the data information corresponding to all the tags in the judge tag and the case information in the retrieval information, so that the corresponding display weight can be determined according to the matching degrees corresponding to different tags.

S2052: extracting a party tag value corresponding to a preset party tag from the party information, and constructing the party portrait according to the party tag value; the party tags include a second identity tag, a case label, a second time tag, and a court label.

When the label library is constructed by the historical case information, firstly, the label corresponding to each information type is generated according to the information types, and then all the labels are constructed into the label library. The tags in the tag library can be divided into two broad categories, namely, principal tags and judge tags. Wherein the party tag comprises: a second identity tag, a case label, a second time tag, a court label, and the like. Specifically, the second identity tag correspondingly comprises data about names, identities and the like of the parties, wherein the data can be Chinese names, English names, certificate numbers, qualification certificates and the like; the case label correspondingly comprises data of reason, pass and the like of the case of the party; the second time tag correspondingly comprises case time, decision time and prison time data about the party; the court label correspondingly comprises related court data about trial of the party, and the court label is only an example and is not limited specifically.

According to the label names of all labels in the label library, determining the information characteristics corresponding to each label name, wherein the information characteristics in the embodiment are used for representing the data type, the character form, the character keywords and the like of the data information corresponding to each label name, and identifying the data information corresponding to each label in each historical case information through the information characteristics. After the data information corresponding to all the tags in the party tag is determined, a party portrait is generated according to the data information corresponding to each tag in the party tag.

Further, after the data information corresponding to all the tags in the tags of the party is determined, the matching degree of the party can be calculated according to the data information corresponding to all the tags in the tags of the party and the case information in the retrieval information, so that the corresponding display weight can be determined according to the matching degree corresponding to different tags.

S206: determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree.

After the matching degree of the party and the matching degree of the legal organ are obtained, the display weight of the portrait is determined according to the matching degree of the party and the matching degree of the legal organ. The display weight in this embodiment is proportional to the matching degree, and the display weight corresponding to the matching degree is larger as the matching degree is larger, and when the display weight of the image of the judge and the display weight of the image of the person concerned are determined, the display weight of the image corresponding to the matching degree is determined according to the size of the matching degree, and the display weight based on the information of the judge and the information of the person concerned in each first case is determined.

The method comprises the steps of constructing a judge portrait and a party portrait corresponding to each historical case according to judge information and party information in historical case information in advance, determining display weights of the party portrait and the judge portrait corresponding to the two parties according to matching degree, and finally determining a display sequence of a first case according to comprehensive weights obtained by the two portraits. Not only screening redundant cases, accurately searching cases matched with the retrieval information, but also determining the display sequence of the cases according to the retrieval information and the cases obtained by retrieval.

S207: and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait.

In this embodiment, the display weight of the facial image and the display weight of the person of interest may be weighted and averaged to calculate the integrated weight score of each first case, and the specific weighting value may be set by the search person, and after the integrated weight score is obtained, the first cases may be displayed in descending order of the integrated weight score.

Furthermore, different search result display threshold values can be set according to different case types and the dimensionality of personal portrait scores of judges, search results with comprehensive scores higher than the threshold values are displayed in a reverse order, and meanwhile, the search results with the search results lower than the display threshold values are automatically shielded and filtered.

According to the method, comprehensive weight scores are formed from dimensions such as multi-dimensional facial portrait, case matching, party portrait, intelligent filtering and the like, and search results with the scores higher than a threshold value are displayed to a user in a reverse order. Therefore, the accuracy of the search result can be measured more comprehensively, the matching degree of the search result is further improved, and the result with a low score value is filtered. When the accurate result is preferentially displayed to the user, the inaccurate result is filtered out, and unnecessary time loss of the judge in searching excessive search results is reduced. Moreover, the history cases which are greatly related to the retrieval information can be displayed at the position near the front of the retrieval result, so that the retrieval personnel can acquire the history cases with the most relation at the first time, and the information acquisition efficiency of the retrieval personnel is improved.

S208: and determining the display sequence of each first case according to the comprehensive weight score, and correspondingly displaying each first case according to the display sequence.

The manner of acquiring the search information of the case in step S208 in this embodiment is completely the same as the manner of acquiring the search information of the case in S105 in the embodiment corresponding to fig. 1, and specific reference may be made to the related description of S105 in the embodiment corresponding to fig. 1, and details thereof are not repeated here.

According to the scheme, the retrieval information of the case is obtained; the retrieval information comprises case information, judge information and party information; if a first case matched with the case information exists in a preset case library, calculating the judge matching degree between the judge information and the first case and the party matching degree between the party information and the first case; acquiring historical case information; extracting judge information and party information from the historical case information; and constructing the judge portrait according to the judge information, and constructing the party portrait according to the party information. Determining the display weight of the first case corresponding to a preset judge portrait according to the judge matching degree, and determining the display weight of the first case corresponding to a preset party portrait according to the party matching degree; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree; and calculating a comprehensive weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait, and displaying the first cases according to the comprehensive weight score. The historical cases are preliminarily searched according to the case information in the search information to obtain a first case of a preliminary screening result, and the matching degree of the first case in the preliminary screening case on the aspects of the judge and the party is determined according to the judge information and the party information in the search information. The method comprises the steps of constructing a judge portrait and a party portrait corresponding to each historical case according to judge information and party information in historical case information in advance, determining display weights of the party portrait and the judge portrait corresponding to the historical case and the party portrait according to matching degree, determining a display sequence of a first case according to comprehensive weights obtained by the two portraits, and displaying each first case correspondingly according to the display sequence. Not only screening redundant cases, accurately searching cases matched with the retrieval information, and determining the case display sequence according to the retrieval information and the matched cases, and correspondingly displaying each first case according to the display sequence, so that the retrieval personnel can acquire the most related historical cases at the first time, and the information acquisition efficiency and the accuracy of the retrieval personnel are improved.

Referring to fig. 3, fig. 3 is a schematic view of a display device for searching cases according to a third embodiment of the present application. The display device 300 for searching cases may be a terminal such as a smart phone or a tablet computer. The display device 300 for retrieving cases in this embodiment includes units for performing the steps in the embodiment corresponding to fig. 1, and please refer to fig. 1 and the related description in the embodiment corresponding to fig. 1 for details, which are not repeated herein. The display device 300 for searching cases of the present embodiment includes:

an obtaining unit 301, configured to obtain search information of a case; the retrieval information comprises case information, judge information and party information;

a calculating unit 302, configured to calculate a judge matching degree between the judge information and the first case and a party matching degree between the party information and the first case if the first case matching the case information exists in a preset case library;

a determining unit 303, configured to determine, according to the cast matching degree, a display weight of a preset cast corresponding to the first case, and determine, according to the matching degree of the party, a display weight of a preset cast corresponding to the first case; the display weight of the facial portrait is in direct proportion to the facial matching degree, and the display weight of the party portrait is in direct proportion to the party matching degree;

a weighting unit 304, configured to calculate a composite weight score for each of the first cases according to the display weight of the forensic portrait and the display weight of the principal portrait;

a display unit 305, configured to determine a display order of each first case according to the comprehensive weight score, and correspondingly display each first case according to the display order.

Further, the calculating unit 302 includes:

the screening unit is used for screening the keywords of the historical cases in the case library;

the first matching unit is used for determining the matching degree between each history case and the case information according to the keywords of the history cases and the keywords in the case information;

the first identification unit is used for identifying a first historical case as the first case if the matching degree corresponding to the first historical case is greater than a preset matching degree threshold value;

and the second matching unit is used for calculating the judge matching degree between the judge information and the judge information in the first case and the party matching degree between the party information and the party information in the first case.

Further, the screening unit includes:

the second identification unit is used for identifying the participles in the historical case and the frequency of each participle in the historical case according to a preset participle mode;

the first calculating unit is used for calculating case frequency of the participles appearing in the historical cases according to the frequency; the case frequency is used for representing the frequency degree of the occurrences of the participles in the historical cases;

the second calculation unit is used for identifying the case number of the historical cases comprising the participles and calculating the case density according to the case number; the case density is used for representing the density of the historical cases related to the participle in the case library;

and the third calculation unit is used for calculating the word segmentation weight of the word segmentation according to the case frequency and the case density, and identifying the corresponding word segmentation as the keyword when the word segmentation weight is greater than the preset word segmentation weight.

Further, the identifying the participles in the historical case and the frequency of each participle appearing in the historical case according to a preset participle mode comprises

Calculating case frequency of the participle in the historical case through the following formula:

wherein f is_iRepresenting the number of times of occurrence of the keyword i in the text of the historical case, and N representing the number of the historical cases;

further, the identifying the case number of the historical cases including the word segmentation, and calculating case density according to the case number comprises:

Wherein n represents the case number of the history cases with the keywords i;

further, the calculating the word segmentation weight of the word segmentation according to the case frequency and the case density includes:

calculating a segmentation weight of the segmentation by the following formula: i is_i＝α×tf_i×df_iX log (1+ l), wherein l represents the character string length of the participle, and α represents the corresponding weighting coefficient of the participle at the document position of the history case.

Further, the display device 300 for searching cases further includes:

the history acquisition unit is used for acquiring history case information;

the extracting unit is used for extracting judge information and party information from the historical case information;

and the construction unit is used for constructing the judge portrait according to the judge information and constructing the party portrait according to the party information.

Further, the construction unit includes:

the first construction unit is used for extracting a judge label value corresponding to a preset judge label from the judge information and constructing the judge portrait according to the judge label value; the judge label comprises a first identity label, a first time label and a post label;

the second construction unit is used for extracting a party label value corresponding to a preset party label from the party information and constructing the party portrait according to the party label value; the party tags include a second identity tag, a case label, a second time tag, and a court label.

Further, the display device 300 for searching cases further includes:

a third matching unit, configured to determine, in the case library, a second case corresponding to the judge information and the party information in the search information if the case library does not have a first case matching the case information;

the fourth calculating unit is used for calculating the matching degree between the case information of the second case and the retrieval information;

and the second weighting unit is used for displaying the second case according to the matching degree.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Referring to fig. 4, fig. 4 is a schematic view of a display device for searching cases according to a fourth embodiment of the present application. The display device 400 of the retrieval case in the present embodiment as shown in fig. 4 may include: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. The steps in the above-described embodiments of the method for displaying individual search cases are implemented when the processor 401 executes the computer program 403. The memory 402 is used to store a computer program comprising program instructions. Processor 401 is operative to execute program instructions stored in memory 402. Wherein the processor 401 is configured to call the program instruction to perform the following operations:

the processor 401 is configured to:

Further, the processor 401 is specifically configured to:

screening key words of historical cases in the case library;

determining the matching degree between each historical case and the case information according to the keywords of the historical cases and the keywords in the case information;

if the matching degree corresponding to a first historical case is larger than a preset matching degree threshold value, identifying the first historical case as the first case;

and calculating the judge matching degree between the judge information and the judge information in the first case and the party matching degree between the party information and the party information in the first case.

Further, the processor 401 is specifically configured to:

identifying the participles in the historical case and the frequency of each participle in the historical case according to a preset participle mode;

calculating case frequency of the participles appearing in the historical cases according to the frequency; the case frequency is used for representing the frequency degree of the occurrences of the participles in the historical cases;

identifying the case number of the historical cases comprising the word segmentation, and calculating case density according to the case number; the case density is used for representing the density of the historical cases related to the participle in the case library;

and calculating word segmentation weights of the segmented words according to the case frequency and the case density, and identifying the corresponding segmented words as the keywords when the word segmentation weights are greater than the preset word segmentation weights.

Further, the processor 401 is specifically configured to:

Wherein n represents the case number of the history cases with the keywords i;

Further, the processor 401 is specifically configured to:

acquiring historical case information;

extracting judge information and party information from the historical case information;

and constructing the judge portrait according to the judge information, and constructing the party portrait according to the party information.

Further, the processor 401 is specifically configured to:

extracting a judge label value corresponding to a preset judge label from the judge information, and constructing the judge portrait according to the judge label value; the judge label comprises a first identity label, a first time label and a post label;

extracting a party tag value corresponding to a preset party tag from the party information, and constructing the party portrait according to the party tag value; the party tags include a second identity tag, a case label, a second time tag, and a court label.

Further, the processor 401 is specifically configured to:

if the case library does not have a first case matched with the case information, determining a second case corresponding to judge information and party information in the retrieval information in the case library;

calculating the matching degree between the case information of the second case and the retrieval information;

and displaying the second case according to the matching degree.

It should be understood that, in the embodiment of the present Application, the Processor 401 may be a Central Processing Unit (CPU), and the Processor may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 402 may include both read-only memory and random access memory, and provides instructions and data to the processor 401. A portion of the memory 402 may also include non-volatile random access memory. For example, the memory 402 may also store device type information.

In a specific implementation, the processor 401, the memory 402, and the computer program 403 described in this embodiment of the present application may execute the implementation manners described in the first embodiment and the second embodiment of the display method for a retrieved case provided in this embodiment of the present application, and may also execute the implementation manner of the terminal described in this embodiment of the present application, which is not described herein again.

In another embodiment of the present application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program comprising program instructions that when executed by a processor implement:

Further, the computer program when executed by the processor further implements:

screening key words of historical cases in the case library;

Wherein n represents the case number of the history cases with the keywords i;

acquiring historical case information;

and displaying the second case according to the matching degree.

The computer readable storage medium may be an internal storage unit of the terminal according to any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially or partially contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A display method for a search case is characterized by comprising the following steps:

calculating a composite weight score of each first case according to the display weight of the judge portrait and the display weight of the party portrait;

and determining the display sequence of each first case according to the comprehensive weight score, and correspondingly displaying each first case according to the display sequence.

2. The method for displaying retrieved cases according to claim 1, wherein if a first case matching the case information exists in a preset case library, calculating a judge matching degree between the judge information and the first case and a party matching degree between the party information and the first case includes:

screening key words of historical cases in the case library;

3. The method for displaying retrieved cases according to claim 2, wherein said filtering keywords of historical cases in said case library comprises:

4. The display method of retrieved cases according to claim 3, wherein said calculating case frequency of occurrence of said participle in said history case according to said frequency comprises:

the identifying the case number of the historical cases including the word segmentation, and calculating case density according to the case number comprises the following steps:

Wherein n represents the case number of the history cases with the keywords i;

the calculating the word segmentation weight of the word segmentation according to the case frequency and the case density comprises the following steps:

5. The method as claimed in claim 1, wherein before determining the display weight of the preset facial image corresponding to the first case according to the facial matching degree and determining the display weight of the preset facial image corresponding to the first case according to the facial matching degree, the method further comprises:

acquiring historical case information;

6. The method of displaying a retrieved case as recited in claim 5, wherein said constructing said judge representation based on said judge information and said constructing said party representation based on said party information comprises:

7. The method for displaying retrieved cases according to claim 1, further comprising, after said obtaining the retrieved information of the case:

and displaying the second case according to the matching degree.

8. A display device for searching cases, comprising:

9. A display device for retrieving cases, comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of the method according to any one of claims 1 to 7 when executing said computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.