Case information processing method and system based on big data

Abstract

The invention belongs to the technical field of data processing, and particularly relates to a case information processing method and system based on big data, and the method comprises the steps: determining a first number according to the retrieval frequency of each retrieval information data in case information and a preset number, determining an identification bit combination of each piece of retrieval information data according to the first quantity and all bits in binary data corresponding to the retrieval information data, determining priority identification information of the case information according to the identification bit combination of all the retrieval information data, and sorting and storing all the case information according to the size of the priority identification information. The method comprises the following steps: performing retrieval in response to a retrieval requirement input by a user, predicting a preliminary screening range of priority identification information according to the retrieval requirement, further determining a preliminary screening result, performing accurate matching in the preliminary screening result according to the retrieval requirement, obtaining a retrieval result, and returning the retrieval result to the user. According to the method, the case information retrieval speed and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology. More specifically, the present invention relates to a case information processing method and system based on big data. Background Art

[0002] With the openness and transparency of social information, the trial results of cases have attracted more and more attention from the society. For the same case, the discretion standards of different judges are often different. Therefore, before the case is decided, by referring to and analyzing similar cases in the past, judges can be provided with unified judgment standards and sentencing standards, reducing inconsistent judgments caused by subjective differences, thereby improving the fairness and transparency of the judiciary and enhancing the public's trust and satisfaction with judicial judgments.

[0003] Since the amount of judicial case data is huge and covers multiple dimensions such as laws and regulations, judicial interpretations, case verdicts, and judicial documents, an intelligent case retrieval system is needed to help judges, lawyers, and other legal practitioners quickly and accurately find past cases similar to the current case from massive data for reference and analysis.

[0004] Compared with numerical information, which can quickly and efficiently obtain matching results based on the value of the numerical information, text information needs to be accurately matched with each stored information, which takes a long time to obtain matching results, and the retrieval speed is slow and the retrieval efficiency is low.

[0005] Most of the case information is text-based. Therefore, when searching for case information, it is necessary to accurately match the search information with each stored case information, and provide all matching case information to the user as search results, resulting in slow case information retrieval speed and low retrieval efficiency.

[0006] In order to quickly and efficiently extract useful case information from a large amount of case information, a high-speed case information retrieval method is urgently needed. Summary of the invention

[0007] In order to solve the above-mentioned technical problems of slow case information retrieval speed and low retrieval efficiency, the present invention provides solutions in the following aspects.

[0008] In a first aspect, the present invention provides a case information processing method based on big data, comprising: collecting case information of a judicial case, the case information comprising a plurality of search information data; rounding the product of the frequency of search of the search information data and a preset number as a first number and recording it as ; Select from all bits in the binary data corresponding to the retrieved information data bits, forming an identification bit combination of retrieval information data; in order of the frequency of retrieval from large to small, record the sequence composed of the values ​​of each retrieval information data of the case information on each bit of the identification bit combination as the identification sequence of the case information; take the sum of the values ​​of each position in the identification sequence and all the positions before it as the cumulative value of each position; take the sum of the cumulative values ​​of all positions as the priority identification information of the case information; sort and store all case information according to the size of the priority identification information; perform retrieval in response to a retrieval requirement input by a user, the retrieval requirement comprising at least one retrieval information data, predict a preliminary screening range of the priority identification information according to the values ​​of each retrieval information data on each bit of the identification bit combination in the retrieval requirement; take the case information of the priority identification information in the preliminary screening range as the preliminary screening result; perform precise matching within the preliminary screening result according to the retrieval requirement, obtain the retrieval result and return it to the user.

[0009] The present invention determines priority identification information of case information based on the identification bit combination of all search information data. The priority identification information is numerical information. The priority identification information is used to represent case information with a large amount of text information, and all case information is sorted and stored according to the priority identification information. When a user performs a search, the preliminary screening range of the priority identification information can be predicted according to the search requirements input by the user. The number of case information that needs to be accurately matched with the search requirements is reduced through the preliminary screening range, and the search results are quickly and efficiently obtained and returned to the user, thereby improving the speed and efficiency of case information retrieval.

[0010] Preferably, the frequency at which the search information data is searched is equal to the number of historical search contents including the search information data. The number of all historical searches Ratio .

[0011] Preferably, the method for obtaining the binary data corresponding to the retrieval information data is: encode all keywords contained in each retrieval information data in the case information to obtain the binary data corresponding to each retrieval information data; for any retrieval information data, use the maximum length of the binary data corresponding to the retrieval information data in all case information as the fixed length of the retrieval information data; and fill 0 after the binary data corresponding to the retrieval information data in the case information so that the length of the binary data corresponding to the retrieval information data in the case information is equal to the fixed length of the retrieval information data.

[0012] Preferably, the selecting of all bits in the binary data corresponding to the search information data bits, forming an identification bit combination of the search information data, including: any of the first bits of the binary data corresponding to the search information data first bits to form a bit combination; for any bit combination among all the bit combinations, all the case information is divided according to the values ​​of the retrieval information data of the case information on each bit of the bit combination, to obtain the division result corresponding to the bit combination; according to the division results corresponding to each bit combination, the selectivity of each bit combination is calculated; the bit combination with the largest selectivity is used as the identification bit combination of the retrieval information data.

[0013] The present invention selects the bit combination with the largest degree from all bit combinations as the identification bit combination for retrieving information data. At this time, the priority identification information of the case information calculated based on the identification bit combination can ensure that the greater the frequency of retrieval of the retrieval information data contained in the retrieval request input by the user, the faster the retrieval speed, thereby improving the speed and efficiency of case information retrieval.

[0014] Preferably, obtaining the division result corresponding to the bit combination includes: dividing the case information with the same value on each bit of the bit combination into a group, and dividing all the case information into Group; all groups are divided into groups corresponding to bit combinations.

[0015] Preferably, the selectivity of the bit combination satisfies the expression: ; In the formula, Indicates The selectivity of the bit combination, Indicates the sequence number of the bit combination, Take all All integers in the range, Represents permutations and combinations, represents the first quantity, Indicates the fixed length of the retrieved information data. Indicates The division result corresponding to the bit combination The frequency of the group, Indicates the sequence number of the group. Take all All integers in the range, Represents an exponential function with a natural constant as its base.

[0016] In order to ensure the overall retrieval efficiency, the selected bit combination is required to be able to divide all case information into multiple groups of the same number, so that when the initial screening is performed based on the identification information, the number of case information initially screened out is approximately the same, which can ensure the overall retrieval efficiency.

[0017] Preferably, the method further comprises: recording a sequence of bits of the identification bit combinations of each retrieval information data in descending order of search frequency as an identification bit sequence.

[0018] The more frequently retrieved retrieval information data is, the more likely it is to appear in the retrieval requirements. Placing the identification bit combination of the most frequently retrieved retrieval information data closer to the left in the identification sequence can ensure that when the retrieval requirements include the most frequently retrieved retrieval information data, the retrieval speed is faster, thereby improving the speed and efficiency of case information retrieval.

[0019] Preferably, the predicted preliminary screening range of priority identification information includes: determining the corresponding position of each bit of the identification bit combination of each retrieval information data contained in the retrieval request in the identification bit sequence, which is recorded as the first position; recording the remaining positions in the identification bit sequence except the first position as the second position; recording the sum of the serial numbers of all second positions as the first numerical value; and predicting the preliminary screening range of the priority identification information based on the numerical values ​​of each retrieval information data contained in the retrieval request at each bit of the identification bit combination, the serial numbers of all first positions and the first numerical value.

[0020] Predicting the initial screening scope of priority identification information can reduce the amount of case information that needs to be accurately matched with the search requirements, quickly and efficiently obtain search results and return them to users, thereby improving the speed and efficiency of case information retrieval.

[0021] Preferably, the initial screening scope of the priority identification information is: ; In the formula, Indicates the value of the t-th bit of the identification bit combination for the a-th item of search information data contained in the search request. represents the serial number of the first position corresponding to the t-th bit of the identification bit combination of the a-th retrieval information data contained in the retrieval request, M represents the first numerical value, a represents the serial number of the retrieval information data contained in the retrieval request, t represents the serial number of the bit of the identification bit combination of the retrieval information data, B represents the number of all retrieval information data contained in the retrieval request, Indicates the first quantity of the a-th item of search information data included in the search request.

[0022] In a second aspect, the present invention provides a case information processing system based on big data, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned case information processing method based on big data is implemented.

[0023] By adopting the above technical solution, the above-mentioned case information processing method based on big data is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0024] The beneficial effects of the present invention are: The present invention determines the priority identification information of the case information according to the identification bit combination of all the search information data, the priority identification information is numerical information, the case information with a large amount of text information is represented by the priority identification information, and all the case information is sorted and stored according to the priority identification information, so that when the user performs a search, the preliminary screening range of the priority identification information can be predicted according to the search requirements input by the user, and the number of case information that needs to be accurately matched with the search requirements is reduced through the preliminary screening range, and the search results are quickly and efficiently obtained and returned to the user, thereby improving the speed and efficiency of case information retrieval; in addition, the present invention selects the bit combination with the largest degree from all the bit combinations as the identification bit combination of the search information data, and the priority identification information of the case information calculated according to the identification bit combination can ensure that when the search information data included in the search requirements input by the user is retrieved more frequently, the search speed is faster, thereby improving the speed and efficiency of case information retrieval; at the same time, in order to ensure the overall search efficiency, it is required that the selected bit combination can divide all the case information into multiple groups of the same number, so that when the initial screening is performed according to the identification information later, the number of case information initially screened out is approximately the same, which can ensure the overall search efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart schematically showing a case information processing method based on big data in the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] The embodiment of the present invention discloses a case information processing method based on big data, referring to Figure 1 , comprising steps S1 to S4: S1. Collect case information of judicial cases.

[0029] Specifically, in the legal field, when describing a judicial case, it is necessary to accurately and clearly convey the case information of the case. The case information includes multiple pieces of information data, including the case name, case number, case type, party information, case facts, dispute focus, applicable law, and judgment results, among which: (1) The format of the case name is usually “Plaintiff’s name + Suit + Defendant’s name + Cause of action”; example: Zhang San vs. Li Si Tort Liability Dispute.

[0030] (2) The case number is a unique number assigned to a case when the court files the case, which is used for case management and retrieval; example: (2023) Jing0101 Minchu 1234.

[0031] (3) Case types are divided into civil cases, criminal cases and administrative cases.

[0032] (4) Information on the parties includes information on the plaintiff, defendant, and third party, including name, gender, date of birth, ethnicity, and home address.

[0033] (5) The facts of a case include the background and disputed facts. The background includes the time, place and background of the case, and the disputed facts refer to the specific points of dispute between the two parties. Example: On May 10, 2023, the plaintiff Zhang San and the defendant Li Si had a dispute over a house rental contract. The plaintiff claimed that the defendant did not pay the rent as agreed in the contract, while the defendant believed that there were quality problems with the house, which made it impossible to use it normally.

[0034] (6) The focus of the dispute refers to the main legal dispute between the two parties in the case; example: The focus of the dispute in this case is whether the defendant has breached the contract and whether the plaintiff has the right to require the defendant to pay liquidated damages.

[0035] (7) Applicable law refers to the legal provisions, judicial interpretations, etc. applicable to the case; Example: This case is subject to the relevant provisions of the Contract Code of the Civil Code of the People’s Republic of China, especially the provisions on lease contracts.

[0036] (8) The judgment result refers to the final decision of the court on the case; Example: After trial, the court held that the defendant Li Si failed to pay the rent as agreed in the contract, constituting a breach of contract, and ordered the defendant to pay the plaintiff rent and liquidated damages totaling RMB 100,000.

[0037] Further, multiple keywords are extracted from each information data, where: (1) Regarding the case name, the format of the case name is "plaintiff name + lawsuit + defendant name + cause of action"; therefore, a regular expression is used to match the format of the case name and extract multiple keywords in the case name, including the plaintiff name, defendant name and cause of action.

[0038] (2) For case numbers, the format of the case number is “(year) + court abbreviation + case type + case number”; therefore, a regular expression is used to match the format of the case number and extract multiple keywords in the case number, including year, court abbreviation, case type, and case number.

[0039] (3) Based on the case type, keyword matching is used and the extracted keyword is one of “civil”, “criminal” and “administrative”.

[0040] (4) Regarding the party information, since the party information usually includes the basic information of the plaintiff, defendant and third party, we first use keyword matching to extract paragraphs containing words such as "plaintiff", "defendant" and "third party", and then use regular expressions to extract keywords, including name, gender, date of birth, ethnicity and home address.

[0041] (5) Regarding the facts of the case, we first use keyword matching to extract paragraphs containing words such as "facts" and "process", and then use natural language processing technology (such as sentence segmentation and dependency parsing) to extract keywords.

[0042] (6) Regarding the focus of the dispute, we first use keyword matching to extract paragraphs containing words such as “focus of the dispute” or “disputed point”, and then use natural language processing technology to extract keywords.

[0043] (7) Regarding the applicability of law, we first use keyword matching to extract paragraphs containing words such as “applicable”, “according to”, and “based on”, and then use regular expressions to extract specific legal provisions.

[0044] (8) For the judgment results, we first use keyword matching to extract paragraphs containing words such as "judgment", "ruling", and "decision", and then use regular expressions to extract keywords.

[0045] Furthermore, all information data included in the case information is used as search information data.

[0046] Further, according to all the historical search contents, the frequency of each search information data being searched is determined, and the frequency of the search information data being searched is equal to the number of historical search contents including the search information data. The number of all historical searches Ratio .

[0047] The historical search content refers to the content input by the user when searching in the intelligent case retrieval system. Each historical search content contains one or more search information data to screen out suitable judicial cases.

[0048] S2. Determine a first quantity of each retrieval information data according to the frequency of retrieval of each retrieval information data and a preset quantity, and determine an identification bit combination of each retrieval information data according to the first quantity and all bits in the binary data corresponding to the retrieval information data.

[0049] It should be noted that for numerical information, some information can be preliminarily retrieved from all case information based on the size of the numerical value, and then the preliminarily retrieved information can be matched, which makes the retrieval speed faster and the retrieval efficiency higher. However, most of the case information is text information. Unlike numerical information, text information cannot be preliminarily retrieved based on the size of the numerical value. Instead, the retrieval information needs to be matched with each stored case information. It takes a long time to obtain the matching results, resulting in slow retrieval speed and low retrieval efficiency.

[0050] Specifically, all keywords contained in each search information data in the case information are encoded to obtain binary data corresponding to each search information data; for any search information data, the maximum length of the binary data corresponding to the search information data in all case information is used as the fixed length of the search information data; and by padding 0 after the binary data corresponding to the search information data in the case information, the length of the binary data corresponding to the search information data in the case information is equal to the fixed length of the search information data.

[0051] The binary data includes a plurality of bits, and the value of each bit is the first digit or the second digit, which are the 1st bit to the Rth bit in order from left to right, and R represents the fixed length of the retrieval information data.

[0052] In this embodiment, 0 is used as the first digital number and 1 is used as the second digital number; in other embodiments, 1 may be used as the first digital number and 0 may be used as the second digital number.

[0053] The encoding method includes but is not limited to UTF8 encoding method, UTF16 encoding method, GB2312 encoding method, and ASCII encoding method.

[0054] It should be noted that the priority identification information of the case information needs to be stored. The priority identification information is obtained based on the identification bit combination of all the retrieval information data. Therefore, the more bits there are in the identification bit combination of all the retrieval information data, the larger the amount of data of the priority identification information of the case information obtained, and the greater the storage pressure. In order to improve the speed and efficiency of retrieval without excessively increasing the storage pressure, the present invention selects some bits from all the bits of the binary data corresponding to each retrieval information data to form an identification bit combination.

[0055] Specifically, the sum of the fixed lengths of all the search information data is recorded as the total number; the product of the total number and the preset ratio is rounded to an integer, which is used as the preset number.

[0056] Among them, the specific numerical value of the preset ratio can be set according to the actual application scenario and needs. The larger the preset number is, the larger the amount of identification information that needs to be stored subsequently is, which affects the storage efficiency. The smaller the preset number is, the larger the amount of case information that is initially screened out based on the identification information is, which affects the retrieval efficiency. Therefore, the value of the preset ratio is more appropriate within the range of [0.1, 0.3]. The present invention sets the preset ratio to 0.2.

[0057] It should be further explained that the more bits there are in the identification bit combination of the retrieval information data, the smaller the value range of the priority identification information corresponding to the retrieval requirement will be when the retrieval requirement input by the user is the retrieval information data, the fewer preliminary screening results will be obtained, the fewer times of matching are required for further screening, and the faster the retrieval speed will be; therefore, for retrieval information data that is retrieved more frequently, the larger the number of bits in its identification bit combination needs to be, so as to improve the speed and efficiency of case information retrieval.

[0058] Optionally, the product of the frequency of retrieval of the retrieval information data and a preset number is rounded to an integer, which is taken as the first number and recorded as S; S bits are selected from all bits in the binary data corresponding to the retrieval information data to form an identification bit combination of the retrieval information data.

[0059] It should be noted that the binary data corresponding to the retrieval information data contains multiple bits. Selecting bit combinations composed of different bits as identification bit combinations will result in different priority identification information. If the selected bit combination can divide all case information into multiple groups of the same number, when the subsequent initial screening is performed based on the identification information, the number of case information initially screened out will be approximately the same, which can ensure the overall retrieval efficiency.

[0060] Preferably, any S first bits among all the first bits in the binary data corresponding to the retrieval information data are combined into a bit combination; for any bit combination among all the bit combinations, all the case information is divided according to the values ​​of the retrieval information data of the case information on each bit of the bit combination, to obtain the division result corresponding to the bit combination; according to the division results corresponding to each bit combination, the selectivity of each bit combination is calculated; the bit combination with the largest selectivity is used as the identification bit combination of the retrieval information data.

[0061] For example, the first number S of the search information data is 3, and the fixed length R of the search information data is 8. Then the total number of the search information data is Bit combinations include , , , , …, ,in, , , , , , , , They respectively represent the 1st, 2nd, 3rd, 4th, 5th, 6th, 7th and 8th bits of all the bits of the search information data.

[0062] It should be noted that the obtained identification bit combination is used to calculate the priority identification information of the case information. Therefore, when the bit combination with the highest selectivity among all bit combinations is used as the identification bit combination of the retrieval information data, the retrieval speed can be ensured to be faster when the retrieval information data contained in the retrieval requirements input by the user is retrieved more frequently, thereby improving the speed and efficiency of case information retrieval.

[0063] Wherein, the obtaining of the division result corresponding to the bit combination includes: dividing the case information with the same value on each bit of the bit combination into a group, and dividing all the case information into Group; all groups are divided into groups corresponding to bit combinations.

[0064] For example, for the bit combination of the retrieval information data , the first bit in the bit combination of all case information And the second bit And the third bit The case information is divided into group 1; in all case information, the first bit in the bit combination And the second bit And the third bit The case information is divided into the second group; in all case information, the first bit in the bit combination And the second bit And the third bit The case information is divided into the third group; and so on, in all case information, the first bit in the bit combination And the second bit And the third bit The case information is divided into the 8th group; then all case information is divided into 8 groups.

[0065] The selectivity of the bit combination satisfies the expression: ; In the formula, Indicates The selectivity of the bit combination, Indicates the sequence number of the bit combination, Take all All integers in the range, Represents permutations and combinations, represents the first quantity, Indicates the fixed length of the retrieved information data. Indicates The division result corresponding to the bit combination The frequency of the group, Indicates the sequence number of the group. Take all All integers in the range, Represents an exponential function with a natural constant as its base.

[0066] It should be noted that in order to achieve better overall retrieval efficiency, it is required that the frequencies of all groups in the division results corresponding to the bit combinations are approximately the same, so that when the initial screening is performed based on the identification information, the number of case information initially screened out is approximately the same, which can ensure the overall retrieval efficiency; It represents the ideal frequency of each group in the partition result corresponding to the bit combination under the ideal situation that the overall retrieval efficiency is the highest. Represents the The first bit combination in the partition result The difference between the actual frequency of the group and the ideal frequency, Represents the The sum of the differences between the actual frequencies and the ideal frequencies of all groups in the partition results corresponding to the bit combination. The smaller the value, the The selectivity of the bit combination The bigger.

[0067] S3. Determine the priority identification information of the case information according to the identification bit combination of all the search information data, and sort and store all the case information according to the size of the priority identification information.

[0068] It should be noted that the priority identification information obtained by the present invention is the sum of the accumulated values ​​of all positions in the identification sequence obtained by splicing the identification bit combinations of all the search information data; since the search requirements contain one or more search information data, the number and type of the search information data contained in the search requirements are different, the size of the preliminary screening range of the priority identification information obtained is different, and the number of case information contained in the preliminary screening results obtained according to the different sizes of preliminary screening ranges is different, and for the position closer to the left in the identification sequence, that is, the position with a larger serial number, when its value can be determined, the smaller the preliminary screening range obtained, and the smaller the number of case information contained in the corresponding preliminary screening results, the faster the retrieval speed, and the more frequently the search information data is retrieved, the more likely it is to appear in the search requirements. Placing the identification bit combination of the search information data with a higher frequency of retrieval closer to the left of the identification sequence can ensure that when the search requirements include the search information data with a higher frequency of retrieval, the retrieval speed is faster.

[0069] Specifically, in descending order of search frequency, a sequence consisting of the values ​​of each bit of the identification bit combination of each search information data of the case information is recorded as the identification sequence of the case information.

[0070] Furthermore, in descending order of search frequency, a sequence consisting of the bits of the identification bit combinations of each search information data is recorded as an identification bit sequence.

[0071] It should be noted that the more frequently the retrieval information data is retrieved, the more likely it is to appear in the retrieval requirements. Therefore, in order to improve the speed and efficiency of case information retrieval based on the retrieval requirements, it is necessary to place the identification bit combination of the more frequently retrieved retrieval information data closer to the left in the identification sequence.

[0072] It should be noted that in the identification sequence of case information, the numbers of each position are from 1 to , Equal to the total quantity.

[0073] Furthermore, the sum of the numerical values ​​of each position in the identification sequence and all the previous positions is used as the cumulative value of each position; and the sum of the cumulative values ​​of all positions is used as the priority identification information of the case information.

[0074] Exemplarily, the sequence composed of the values ​​of each bit of the identification bit combination of all the retrieved information data of the case information is 10101010. For the obtained identification sequence, the sum of the values ​​of each position in the identification sequence and all the positions before it is taken as the cumulative value of each position. For the third position in the identification sequence, the value at the third position is "0", and the values ​​of all positions before the third position, that is, the values ​​at the first position and the second position are "0" and "1" respectively, then the cumulative value of the third position is equal to 0+1+0=1; similarly, the cumulative values ​​of all positions are obtained, and the cumulative values ​​of each position are 0, 1, 1, 2, 2, 3, 3, 4 respectively, and the sum of the cumulative values ​​of all positions is 16, then the priority identification information of the case information is 16.

[0075] In this embodiment, all case information is sorted and stored according to the priority identification information from small to large; in other embodiments, all case information is sorted and stored according to the priority identification information from large to small.

[0076] It should be noted that, for case information with a large amount of text information, the identification bit combination is determined from all the search information data of the case information to obtain the priority identification information of the case information; since the obtained priority identification information is numerical information, all case information can be sorted and stored according to the priority identification information based on the characteristics of the numerical information.

[0077] S4. Respond to the user inputting the search request and perform a search. Predict the preliminary screening range of the priority identification information according to the search request, and then determine the preliminary screening results. Perform an accurate match within the preliminary screening results according to the search request to obtain the search results and return them to the user.

[0078] Specifically, when a user searches in the intelligent case retrieval system and selects suitable case information, the user first inputs a search requirement, which includes at least one type of search information data.

[0079] Furthermore, in response to a search request input by the user, a search is performed, and a preliminary screening range of the priority identification information is predicted based on the values ​​of each bit of the identification bit combination of each search information data in the search request; the case information of the priority identification information in the preliminary screening range is used as the preliminary screening result; an accurate match is performed within the preliminary screening result according to the search request, and the search result is obtained and returned to the user.

[0080] It should be noted that since all case information is sorted and stored using the numerical information of the case information, namely the priority identification information, when the user subsequently searches, it is possible to predict the preliminary screening range of the priority identification information based on the search requirements input by the user, thereby reducing the amount of case information that needs to be precisely matched with the search requirements, and being able to quickly and efficiently obtain search results and return them to the user, thereby improving the speed and efficiency of case information retrieval.

[0081] Among them, the method of predicting the preliminary screening range of the priority identification information based on the values ​​of each bit of the identification bit combination of each retrieval information data in the retrieval request includes: determining the corresponding position of each bit of the identification bit combination of each retrieval information data contained in the retrieval request in the identification bit sequence, recording it as the first position; recording the remaining positions in the identification bit sequence except the first position as the second position; recording the sum of the serial numbers of all the second positions as the first numerical value; predicting the preliminary screening range of the priority identification information based on the values ​​of each bit of the identification bit combination of each retrieval information data contained in the retrieval request, the serial numbers of all the first positions and the first numerical value.

[0082] Among them, the preliminary screening scope of the priority identification information is: ; In the formula, Indicates the first The item retrieves the information data in the first position of the identification bit combination. The value of the bit, Indicates the first The first bit combination of the identification bit of the search information data The serial number of the first position corresponding to the bits, represents the first value, Indicates the sequence number of the search information data contained in the search request. The bit number representing the identification bit combination of the retrieved information data, Indicates the number of all search information data included in the search request. Indicates the first The first quantity of the item retrieves the information data.

[0083] It should be noted that by predicting the preliminary screening scope of priority identification information, the amount of case information that needs to be accurately matched with the search requirements can be reduced, and the search results can be obtained quickly and efficiently, thereby improving the speed and efficiency of case information retrieval.

[0084] Among them, the precise matching is performed within the preliminary screening results according to the search requirements to obtain the search results and return them to the user, including: taking the case information in the preliminary screening results that can fully match the search requirements as the search results, and returning it to the user, so as to quickly screen out suitable case information for the user according to the search requirements input by the user.

[0085] An embodiment of the present invention also discloses a case information processing system based on big data, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a case information processing method based on big data according to the present invention is implemented.

[0086] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

Claims

1. A case information processing method based on big data, characterized in that: include: Collect case information of judicial cases, which includes multiple search information data; The product of the frequency of retrieval of the retrieval information data and the preset number is rounded to an integer as the first number and recorded as ; Select among all the bits in the binary data corresponding to the search information data bits, constituting the identification bit combination of the retrieval information data; In descending order of the frequency of retrieval, the sequence of values ​​of each bit of the identification bit combination of each retrieval information data of the case information is recorded as the identification sequence of the case information; the sum of the values ​​of each position in the identification sequence and all previous positions is used as the cumulative value of each position; the sum of the cumulative values ​​of all positions is used as the priority identification information of the case information; all case information is sorted and stored according to the size of the priority identification information; Responding to a search request input by a user, a search is performed, wherein the search request includes at least one search information data; based on the values ​​of each search information data in the search request at each bit of the identification bit combination, a preliminary screening range of the priority identification information is predicted; case information of the priority identification information in the preliminary screening range is used as a preliminary screening result; and accurate matching is performed within the preliminary screening result according to the search request to obtain a search result and return it to the user.

2. The case information processing method based on big data according to claim 1 is characterized in that: The frequency at which the search information data is searched is equal to the number of historical search contents including the search information data The number of all historical searches Ratio .

3. The case information processing method based on big data according to claim 1 is characterized in that: The method for obtaining the binary data corresponding to the retrieval information data is: Encode all keywords contained in each search information data in the case information to obtain binary data corresponding to each search information data; for any search information data, use the maximum length of the binary data corresponding to the search information data in all case information as the fixed length of the search information data; and pad 0 after the binary data corresponding to the search information data in the case information so that the length of the binary data corresponding to the search information data in the case information is equal to the fixed length of the search information data.

4. The case information processing method based on big data according to claim 1 is characterized in that: The method selects from among all the bits of the binary data corresponding to the retrieved information data bits, forming the identification bit combination of the retrieval information data, including: Any of the first bits in the binary data corresponding to the retrieved information data The first bits form a bit combination; For any one of all bit combinations, all case information is divided according to the values ​​of the search information data of the case information at each bit of the bit combination, to obtain a division result corresponding to the bit combination; Calculate the selectivity of each bit combination according to the division results corresponding to each bit combination; The bit combination with the greatest selectivity is used as the identification bit combination for the retrieval information data.

5. A case information processing method based on big data according to claim 4, characterized in that: Obtaining a division result corresponding to the bit combination includes: The case information with the same value in each bit of the bit combination is divided into a group, and all the case information is divided into Group; All groups are regarded as the division results corresponding to the bit combinations.

6. A case information processing method based on big data according to claim 4, characterized in that: The selectivity of the bit combination satisfies the expression: ； In the formula, Indicates The selectivity of the bit combination, Indicates the sequence number of the bit combination, Take all All integers in the range, Represents permutations and combinations, represents the first quantity, Indicates the fixed length of the retrieved information data. Indicates The division result corresponding to the bit combination is The frequency of the group, Indicates the sequence number of the group. Take all All integers in the range, Represents an exponential function with a natural constant as its base.

7. The case information processing method based on big data according to claim 1 is characterized in that: The method further comprises: In descending order of search frequency, a sequence consisting of the bits of the identification bit combinations of each search information data is recorded as an identification bit sequence.

8. The case information processing method based on big data according to claim 7 is characterized in that: The scope of the initial screening of the predicted priority identification information includes: Determine the corresponding position of each bit of the identification bit combination of each retrieval information data contained in the retrieval request in the identification bit sequence, and record it as the first position; The remaining positions in the identification bit sequence except the first position are recorded as the second positions; The sum of the serial numbers of all the second positions is recorded as the first value; The preliminary screening range of the priority identification information is predicted based on the values ​​of each bit of the identification bit combination of each retrieval information data included in the retrieval request, the serial numbers of all first positions and the first values.

9. The case information processing method based on big data according to claim 8 is characterized in that: The initial screening scope of the priority identification information is: ； In the formula, Indicates the first The item retrieves the information data in the first position of the identification bit combination. The value of the bit, Indicates the first The first bit combination of the identification bit of the search information data The serial number of the first position corresponding to the bits, represents the first value, Indicates the sequence number of the search information data contained in the search request. The bit number representing the identification bit combination of the retrieved information data, Indicates the number of all search information data included in the search request. Indicates the first The first quantity of the item retrieves the information data.

10. A case information processing system based on big data, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a case information processing method based on big data according to any one of claims 1 to 9 is implemented.

Images