Systems, methods, and computer program products for mining text documents to identify groundbreaking questions and groundbreaking cases

Abstract

Embodiments of the present disclosure relate to systems, methods, and computer product programs for identifying one or more seminal cases within a database containing legal case data. The disclosed systems and methods provide a way to identify one or more seminal cases for a particular legal issue by mining a text database containing electronic legal documents for citation reasons and mining the text therein to determine whether the legal issue addressed in the citation reasons involves a seminal case. Data is created by data mining and is obtained from a plurality of citation reasons that identify seminal cases for a particular legal issue, such that when one or more of the seminal cases are returned as search results, output data corresponding to the seminal cases enables an external device to distinguish the seminal cases.

Description

[0001] Cross-references

[0002] This application claims priority under 35 U.S.C. 119(e) to U.S. Provisional Patent Application No. 62 / 610,356, filed on December 26, 2017, entitled “Systems, Methods and Computer Program Products for Mining Text Documents to Identify Seminal Cases,” which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates generally to electronic document processing and, more particularly, to systems, methods, and computer program products for identifying and extracting seminal issues embedded in legal databases through data mining. Background Art

[0004] Legal scholars and other experts can sometimes identify legal cases that are considered influential in a particular area of ​​law. These influential cases may be referred to as seminal cases. Seminal cases resolve important legal issues and are often cited by subsequent cases that also resolve the same issues. For example, a seminal case may be the first case from the highest court in a jurisdiction that has decided a particular legal issue and states the proposition of the law in question. In another example, a seminal case may be considered an important case that established new law and set new precedents. Seminal cases may also be considered cases that are decided in courts and used as examples to decide similar cases.

[0005] Because groundbreaking cases have legal significance, they are often cited by lawyers and judges. However, groundbreaking cases are usually not well-known when they are announced and when the case is entered into a database and is available for search. On the contrary, as many lawyers and judges quote and rely on the important legal issues solved by the groundbreaking case, the case becomes more well-known over time. Therefore, many groundbreaking cases that solve specific legal issues may not be marked or easily identified in other ways when they are stored in the database provided to the search engine. As a result, when searching, the user may not realize that the case is a groundbreaking case. In addition, in the absence of information identifying some cases as groundbreaking, a search engine that is configured to provide the most important cases at the top of the search results or otherwise distinguish the most important cases may not do the above operations for groundbreaking cases. Summary of the invention

[0006] In one embodiment, a system for identifying one or more seminal cases that solve a specific legal problem is provided. The system includes a processing device; and a non-transitory processor-readable storage medium that communicates with the processing device. The non-transitory processor-readable storage medium includes one or more programming instructions, which, when executed, cause the processing device to obtain an electronic legal document from a repository, the electronic legal document including multiple texts; search the multiple texts of the electronic legal document for multiple citations including multiple legal problem texts; search the multiple citations to identify multiple seminal clues, and generate a data list with the multiple seminal clues from the multiple citations to identify multiple potential seminal cases; filter the data list containing the multiple potential seminal cases to identify only seminal cases based on the calculated seminal reference frequency and generate a working corpus from the filtered data list; and output data corresponding to the seminal cases from the working corpus, so that when one or more of the seminal cases are returned as a result of the search, the data enables an external device to distinguish the seminal cases.

[0007] In another embodiment, a method for identifying one or more seminal cases that solve a specific legal problem is provided. The method includes: obtaining an electronic legal document from a repository by a processing device, the electronic legal document including a plurality of texts; searching the plurality of texts of the electronic legal document by the processing device for a plurality of citations including a plurality of legal problem texts; and searching the plurality of citations by the processing device to identify a plurality of seminal clues. The method further includes: generating, by the processing device, a data list with the multiple pioneering clues from the multiple citation reasons to identify multiple potential pioneering cases; filtering, by the processing device, the data list containing the multiple potential pioneering cases to only identify pioneering cases based on the calculated pioneering reference frequency and generating a working corpus from the filtered data list; mining, by the processing device, the multiple legal issue texts from the multiple citation reasons of all the pioneering cases in the working corpus to establish sentence data, the sentence data including multiple sentences, the multiple sentences including multiple legal discussions of the multiple legal issue texts from the pioneering cases in the working corpus; and assigning, by the processing device, a unique identifier to each of the multiple sentences that reference the pioneering case. Further, the method includes: by the processing device, for each of the pioneering cases in the working corpus, collecting each of the multiple sentences from the sentence data and storing the collected sentences from the sentence data as temporary sentence data; and by the processing device, applying a text clustering algorithm to the temporary sentence data to create a plurality of text clusters; by the processing device, selecting a top cluster from the plurality of text clusters, wherein the top cluster includes one or more sentences surrounding the plurality of legal discussions and the plurality of legal issue texts identified with each of the pioneering cases; and outputting data corresponding to the pioneering cases from the working corpus to a user display device, so that when one or more of the pioneering cases are returned as a result of a search, the data enables the user display device to distinguish the pioneering cases.

[0008] In yet another embodiment, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium being operable by a computer to identify one or more seminal cases that solve a specific legal problem. The non-transitory computer-readable storage medium having one or more programming instructions stored thereon causes a processing device to obtain an electronic legal document from a repository, the electronic legal document comprising a plurality of texts; search the plurality of texts of the electronic legal document for a plurality of citations comprising a plurality of legal problem texts; search the plurality of citations to identify a plurality of seminal clues, and generate a data list having the plurality of seminal clues from the plurality of citations to identify a plurality of potential seminal cases; filter the data list containing the plurality of potential seminal cases to identify only seminal cases based on the calculated seminal reference frequency and generate a working corpus from the filtered data list; and output data corresponding to the seminal cases from the working corpus, so that when one or more of the seminal cases are returned as a result of the search, the data causes an external device to distinguish the seminal cases.

[0009] These and other features provided by the embodiments described herein will be more fully understood in view of the following detailed description taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The embodiments set forth in the drawings are illustrative and exemplary in nature and are not intended to limit the subject matter defined by the claims. The following detailed description of the illustrative embodiments can be understood when read in conjunction with the following drawings, in which like structures are represented by like reference numerals, and in which:

[0011] Figure 1 schematically depicts an illustrative computing network for a system for mining text document data to identify one or more seminal cases that address a particular legal issue in accordance with one or more embodiments described and illustrated herein;

[0012] Figure 2A Schematically depicts a schematic diagram of a circuit according to one or more embodiments described and illustrated herein. Figure 1 The case mining device further illustrates hardware components and software components that can be used to mine text document data to identify one or more seminal cases that address a particular legal issue;

[0013] Figure 2B Schematically depicts a schematic diagram of a circuit according to one or more embodiments described and illustrated herein. Figure 1 A user computing device further illustrating hardware components and software components that can be used to initiate a search query to identify one or more seminal cases that address a particular legal issue;

[0014] Figure 3 depicts a flow chart of an illustrative method of facilitating key groundbreaking question search queries in accordance with one or more embodiments shown and described herein;

[0015] Figure 4 depicts a flow chart of an illustrative method of mining text document data to identify one or more seminal cases that address a particular legal issue in accordance with one or more embodiments shown and described herein;

[0016] Figure 5 A flowchart depicting an illustrative method of selecting a citation reason to represent a groundbreaking question according to one or more embodiments described and illustrated herein; and

[0017] Figure 6 Schematically depicted is a graphical user interface with a legal question query field and a results list according to one or more embodiments described and illustrated herein. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure relate to systems, methods, and computer product programs for identifying one or more groundbreaking cases within a database containing legal case data. More specifically, the disclosed system and method provide a way to identify one or more groundbreaking cases and legal issues resolved by a specific groundbreaking case by mining a text database containing electronic legal documents. Traditionally, when groundbreaking cases and their corresponding legal issues are initially added to a database, the groundbreaking cases and their corresponding legal issues stored in the database are unmarked or otherwise identified. This is because it is usually unknown at the time of publication whether a case will eventually become particularly important in a specific legal field. Further, a case may be considered groundbreaking only for one legal issue among many legal issues that may have been resolved in the case. Therefore, the process described herein generates data corresponding to a groundbreaking case, and provides or sends the data to an external device, which uses the data to display the groundbreaking case at the top of a search result list, or otherwise indicates the groundbreaking case, which improves the function of the external device in providing the most relevant information to the user when identifying the groundbreaking case. That is, the search results generated as a result of the process described herein may cater to or boost a particular case only when the groundbreaking questions of the case meet the search needs of a particular user.

[0019] Various systems, methods, and computer product programs for identifying seminal cases by mining a text document database are described in detail herein.

[0020] Now referring to the accompanying drawings, Figure 1An illustrative computing network depicting components of a system for mining text documents to identify seminal cases is depicted in accordance with the embodiments shown and described herein. Figure 1 As shown, the computer network 100 may include a wide area network (WAN) (such as the Internet), a local area network (LAN), a mobile communication network, a public service telephone network (PSTN), a personal area network (PAN), a metropolitan area network (MAN), a virtual private network (VPN), and / or another network. The computer network 100 may be configured to electronically connect one or more computing devices and / or components thereof. Illustrative computing devices may include, but are not limited to, a user computing device 102a, a case mining device 102b, and an administrator computing device 102c.

[0021] The user computing device 102a can generally provide an interface between a user and other components connected to the computer network 100. Thus, the user computing device 102a can be used to perform one or more user-oriented functions, such as receiving one or more inputs from a user or sending data or information, such as data related to initiating an electronic search query for one or more legal issues. More specifically, in order to perform an electronic search query, the user computing device 102a can present a user interface to the user, which allows the user to input one or more legal issues to be searched. The user interface can be configured to receive a search request from the user, initiate a search, and utilize data received from the case mining device 102b when displaying search results, as described in more detail herein. The search request may include terms and / or other data for retrieving documents. The components and functions of the user computing device 102a will be described in detail below.

[0022] In addition, included Figure 1 In the case mining device 102b is an administrator computing device 102c. In the event that the case mining device 102b requires supervision, updating, or correction, the administrator computing device 102c can be configured to provide the desired supervision, updating, and / or correction. The administrator computing device 102c can also be used to input additional data into the data storage portion of the case mining device 102b. For example, the administrator computing device 102c can edit a headnote. It should be understood that the headnote can be the key points of the case extracted directly from the language of the court by an attorney editor. Because the headsnotes are commonly understood, they are not discussed in further detail herein.

[0023] The case mining device 102b can search a document database using one or more legal issues to identify a result set of documents. The case mining device 102b can also determine potential groundbreaking case keywords or clues to identify groundbreaking cases related to a result set of documents, and the result set of the document indicates a groundbreaking case for each legal issue. The case mining device 102b can also send information to the user computing device 102a so that the user computing device 102a can display the result set of the document and information related to the result set of the document, wherein the groundbreaking case is displayed on top of the result set of the document and the information. The case mining device 102b can provide or send data to an external device (such as the user computing device 102a) to display or otherwise indicate the groundbreaking case found. The components and functions of the case mining device 102b will be described in detail below.

[0024] It should be understood that while the user computing device 102a and the administrator computing device 102c are depicted as personal computers and the case mining device 102b is depicted as a server, these are merely examples. More specifically, in some embodiments, any type of computing device (e.g., mobile computing device, personal computer, server, etc.) may be used for any of these components. Furthermore, while each of these computing devices may be used in Figure 1 102a, 102b, and 102c. In particular, each of the user computing device 102a, the case mining device 102b, and the administrator computing device 102c may represent multiple computers, servers, databases, and the like.

[0025] In addition, it should be understood that although the embodiments depicted herein relate to a network of computing devices, the present disclosure is not limited to such networks. For example, in some embodiments, the various processes described herein may be performed by a single computing device, such as a non-networked computing device or a networked computing device that does not use a network to complete the various processes described herein.

[0026] Figure 2A A case mining device 102b according to the embodiments shown and described herein is depicted, and further a system for identifying one or more seminal cases and their corresponding legal issues by utilizing hardware, software, and / or firmware is shown. According to the embodiments shown and described herein, the case mining device 102b may include a non-transitory computer-readable medium configured to search a document corpus or identify text surrounding a plurality of citation reasons, abstracts, etc., embodied as hardware, software, and / or firmware.

[0027] Although in some embodiments, the case mining device 102b can be configured as a general-purpose computer with the necessary hardware, software, and / or firmware, in other embodiments, the case mining device 102b can also be configured as a special-purpose computer specially designed to perform the functions described herein. For example, the case mining device 102b can be a special-purpose device that specifically determines case citations, multiple citation reasons, summaries, etc. located within the text of an electronic document. In a further example, the case mining device 102b can be a special-purpose device that further searches the multiple legal issue texts of each of the multiple citation reasons to identify multiple groundbreaking clues, and generates a data list from the multiple legal issue texts with multiple groundbreaking clues to identify multiple potential groundbreaking cases. When an external component (e.g., the user computing device 102a ( Figure 1 ))When performing a search and providing the user with results that are sorted by importance (e.g., groundbreaking cases are more important than other cases) or otherwise indicated within the displayed search results, the case mining device 102b then provides the generated data list to the external component for the purpose of improving the accuracy of the external component.

[0028] Likewise Figure 2A As shown in , the case mining device 102b may include: a processor 230; input / output hardware 232; network interface hardware 234; a data storage component 236, which stores a database of electronic document data 238a, keyword data 238b, potential pioneering case data 238c, pioneering case data 238d, top text clustering data 238e, key term data 238f, citation reason data 238g or summary data; and a memory component 240. The memory component 240 may be a non-transitory computer-readable memory. The memory component 240 may be configured as a volatile and / or non-volatile memory and may therefore include a random access memory (including SRAM, DRAM and / or other types of random access memory), flash memory, registers, compact disks (CDs), digital versatile disks (DVDs) and / or other types of storage components. In addition, the memory component 240 can be configured to store operation logic 244, search logic 244a, keyword logic 244b, seminal case identification logic 244c, text clustering logic 244d, key term identification logic 244e, and citation reason identifier logic 244f (each of which can be embodied as a computer program, firmware, or hardware, as examples). The local interface 246 is also included in Figure 2A2 and may be implemented as a bus or other interface to facilitate communication between components of the case mining device 102b. It should be understood that the processor 230, the memory component 240, and various logic modules such as the search logic 244a, the keyword logic 244b, the seminal case identification logic 244c, the text clustering logic 244d, the key term identification logic 244e, and the citation reason identifier logic 244f may define a computer program product for identifying seminal cases by mining a text document database.

[0029] Processor 230 may include any (multiple) processing components configured to receive and execute instructions, such as instructions from data storage component 236 and / or memory component 240. Input / output hardware 232 may include a monitor, keyboard, mouse, printer, camera, microphone, speaker, and / or other device for receiving, sending, and / or presenting data. Network interface hardware 234 may include any wired or wireless networking hardware, such as a modem, LAN port, wireless fidelity (Wi-Fi) card, WiMax card, mobile communication hardware, and / or other hardware for communicating with other networks and / or devices.

[0030] It should be understood that the data storage component 236 may reside locally and / or remotely from the case mining device 102b and may be configured to store one or more pieces of data accessed by the case mining device 102b and / or other components, determine a citation reason, and / or determine whether a seminal lead exists. Figure 2AAs shown in , the data storage component 236 stores a database of electronic document data 238a. As described above, the electronic document may include legal documents (i.e., cases, defense statements, etc.) that have been organized and indexed for searching. Keyword data 238b stores potential keywords or groundbreaking clues that can be used to identify potential groundbreaking cases. For example, a potential groundbreaking case can be identified by determining whether the reasons for citing a subsequent case that cites a specific case include multiple keywords or groundbreaking clues. These keywords or groundbreaking clues are indicators that the opinions in the reasons for citing or the summary indicate that the authoring judge's beliefs and authoritative thinking have been important and / or influential to the cited case in terms of the specific legal provisions in question. Keywords or groundbreaking clues may include, but are not limited to: groundbreaking cases, groundbreaking rulings, groundbreaking opinions, groundbreaking rulings, groundbreaking rulings, groundbreaking determinations, milestone cases, milestone rulings, milestone opinions, milestone determinations, milestone rulings, leading cases, leading rulings, leading opinions, leading determinations, leading rulings, etc. In one particular example, if the opinion text of a subsequent case states, "In this seminal Fourth Amendment case, decided 120 years ago, the Court wrote in oft-cited language that the Fourth Amendment's prohibitions apply to 'all intrusions by the government and its employees upon the sanctity of the home and the privacy of one's life,'" then the subsequent case may indicate that the prior case was seminal. Potential seminal case data 238c may include potentially seminal cases identified by keywords or seminal clues.

[0031] The seminal case data 238d includes a plurality of sentences having unique identifiers assigned based on the inclusion of references to seminal cases and any cases that have been identified as seminal cases by keywords or seminal clues included in the keyword data 238b. For example, the citation reason may include keywords or seminal clues in the opinion of the authoring judge (i.e., using the terms "seminal", "leading", etc.), which refer to a specific case or legal issue after the seminal case, but the authoring judge has ruled that the seminal case is a precedent in the subsequent case. The seminal case data 238d only includes seminal cases that have been filtered from the potential seminal case data 238c. More specifically, the seminal case data 238d only includes the following seminal cases: the seminal cases have been filtered by determining whether the case is seminal (e.g., keywords such as "seminal", "leading", "generational", etc.) based on the preset frequency of keywords or seminal clues in the citation reason or summary. It should be understood that, in general, the higher the frequency of keywords or seminal clues, the more likely the case is a seminal case. The top text cluster data 238e includes one or more text clusters that are identified as potentially addressing a seminal issue in one of the seminal cases. The top text cluster data 238e includes one or more sentences that discuss a seminal legal issue for a particular seminal case (e.g., "In a lawsuit in which a guardian seeks to stop nutrition and hydration for a person diagnosed with a persistent vegetative state, a state may apply a clear and convincing standard of evidence."). The key term data 238f may include a set of key terms that represent a particular seminal issue. As discussed herein, the set of key terms may be normalized by the system to capture specific terms that may be spelled or referred to in a variety of ways. Thus, the key term data 228f may also include any variations of the set of key terms (e.g., based on the example sentences above), which may be: "state," "applicable," "clear," "clear and convincing," "clear and convincing evidence," "convincing," "convincing evidence," "convincing standard of evidence," "evidence," "standard of evidence," "standard," "litigation," "guardian," "seek," "stop," "nutrition," "hydration," "person," "diagnosis," "persistence," "persistent vegetative state," "vegetative," "vegetative state," etc.). The citation reason data 238g may include multiple citation reasons or summaries and multiple terms for each of the multiple citation reasons, summaries, etc., wherein each of the multiple terms may represent a seminal legal issue resolved by a particular seminal case.

[0032] Included in the memory component 240 are operating logic 244, search logic 244a, keyword logic 244b, seminal case identification logic 244c, text clustering logic 244d, key term identification logic 244e, and citation reason identifier logic 244f. Operating logic 244 may include an operating system and / or other software for managing components of case mining device 102b. Search logic 244a may include programming instructions to facilitate electronic searches during the data generation process, as described in more detail herein. Further, search logic 244a may include programming instructions to mine electronic documents for legal topics and sort, store, classify, etc. any cases related to those topics. Search logic 244a may send data to a search computer (i.e., user computing device 102a) so that when a search request is received and a result list is generated, the search computer knows which cases are seminal cases, as described in more detail herein. Thus, the search computer (i.e., user computing device 102a) has information that triggers the search computer to move those groundbreaking cases to the top of the search results list or otherwise distinguish the search results (e.g., highlighting, stars, etc.) so that when the user reads the results list, the user knows that the cases distinguished in the search results or at the top of the results list are groundbreaking cases.

[0033] Keyword logic 244b may include programming instructions to select electronic document data 238a, search electronic document data 238a, identify citation reason text from the search of electronic document data 238a, and identify one or more keywords in the citation reason text indicating a potential groundbreaking case. Keyword logic 244b may save one or more keywords as keyword data 238b. Groundbreaking case identification logic 244c may include programming instructions to identify one or more groundbreaking cases based on the frequency of keywords in keyword data 238b being mentioned in potential groundbreaking cases stored in potential groundbreaking case data 238c. Text clustering logic 244d may be an algorithm configured to identify top text clustering data 238e using text clustering. The algorithm of text clustering logic 244d may identify one or more sentences in the text of the citation reason of the groundbreaking case stored in groundbreaking case data 238d. Key term identification logic 244e may include programming instructions to identify the group of key terms of key term data 238f by searching for sentences of top text clustering data 238e. As described above, the key term identification logic 244e may also normalize the key terms. The citation identifier logic 244f may include programming instructions to select one or more citations or abstracts stored in the citation data 238g based on the semantic distance between the multiple terms of each of the multiple citations or abstracts and the normalized key terms, as described in more detail herein. As described above, the selected multiple citations or abstracts represent the seminal issues addressed by the seminal case.

[0034] It should be understood that Figure 2A The components depicted in are illustrative only and are not intended to limit the scope of the present disclosure. More specifically, although Figure 2A The components in are illustrated as residing within the case mining device 102b, but this is a non-limiting example. In some embodiments, one or more of the components may reside outside the case mining device 102b. Similarly, although Figure 2A Reference is made to the case mining device 102 b , but other components, such as the user computing device 102 a and the administrator computing device 102 c , may include similar hardware, software, and / or firmware.

[0035] Figure 2B A user computing device 102a is depicted in accordance with the embodiments shown and described herein, further illustrating a system for identifying search queries by utilizing hardware, software, and / or firmware. Additionally, in accordance with the embodiments shown and described herein, the user computing device 102a may include a non-transitory computer-readable medium configured to display and transmit a search query initiated by a user, embodied as hardware, software, and / or firmware.

[0036] While in some embodiments, the user computing device 102a may be configured as a general purpose computer with the necessary hardware, software, and / or firmware, in other embodiments, the user computing device 102a may be configured as a special purpose computer specifically designed to perform the functions described herein. For example, the user computing device 102a may be a special purpose device that displays a user interface for inputting a search query for at least one legal issue and displays a plurality of generated results for the search query, wherein seminal cases for the searched legal issue are displayed at the top of the search results or otherwise indicated within the search results for the purpose of improving the accuracy of the search results provided to the user.

[0037] If also Figure 2B As shown in , the user computing device 102a may include: a processor 270; input / output hardware 272; network interface hardware 274; a data storage component 276 that stores a database of search query data 278a and display data 278b; and a memory component 280. The memory component 280 may be a non-transitory computer-readable memory. The memory component 280 may be configured as a volatile and / or non-volatile memory and may therefore include a random access memory (including SRAM, DRAM, and / or other types of random access memory), flash memory, registers, compact disks (CDs), digital versatile disks (DVDs), and / or other types of storage components. In addition, the memory component 280 may be configured to store operating logic 282a, search query logic 282b, and display logic 282c (each of which may be embodied as a computer program, firmware, or hardware, as examples). The local interface 284 is also included. Figure 2B and may be implemented as a bus or other interface to facilitate communication between components of the user computing device 102a.

[0038] Processor 270 may include any (multiple) processing components configured to receive and execute instructions (such as instructions from data storage component 276 and / or memory component 280). Input / output hardware 272 may include a monitor, keyboard, mouse, printer, camera, microphone, speaker, and / or other device for receiving, sending, and / or presenting data. Network interface hardware 274 may include any wired or wireless networking hardware, such as a modem, LAN port, wireless fidelity (Wi-Fi) card, WiMax card, mobile communication hardware, and / or other hardware for communicating with other networks and / or devices.

[0039] It should be understood that the data storage component 276 may reside locally and / or remotely on the user computing device 102a and may be configured to store one or more pieces of data for access by the user computing device 102a and / or other components, store data (such as search query data 278a) that may be received from an external device (e.g., the case mining device 102b), and / or store data to be displayed. Figure 2B As shown in , the data storage component 276 stores a database of search query data 278a. As described above, the search query data 278a may include data related to the legal issues being searched and / or data received from an external device (i.e., the case mining device 102b). The display data 278b may include data related to the data to be displayed. For example, the display data 278b may include the order of the cases to be displayed on the user computing device 102a (such as, the case mining device 102b) or otherwise distinguish the cases.

[0040] Included in the memory component 280 are operating logic 282a, search query logic 282b, and display logic 282c. The operating logic 282a may include an operating system and / or other software for managing components of the user computing device 102a. The search query logic 282b may contain programming instructions to facilitate electronic searches or queries initiated by users. The search query logic 282b may be configured to compile, organize, and / or display electronic documents and other data into a certain order, such as indicating and / or distinguishing groundbreaking cases for groundbreaking legal issues at the top of a list of search results or otherwise, which are identifiable when displayed to the user. The search query logic 282b may also be configured to provide data for a user interface to the user computing device 102a or a display device of the user computing device 102a.

[0041] The display logic 282c may display a graphical user interface usable by a user of the user computing device 102a to provide an electronic document search query, display a visualization of a plurality of metadata associated with a selected plurality of citations or summaries representing at least one seminal problem solved by at least one seminal case, and display results of metadata associated with a selected plurality of citations or summaries representing at least one seminal problem solved by at least one seminal case. The display logic 282c may generally be configured to display information on a display of the user computing device 102a. The functionality of the operation logic 282a, the search query logic 282b, and the display logic 282c will be described in further detail below.

[0042] It should be understood that Figure 2B The components depicted in are illustrative only and are not intended to limit the scope of the present disclosure. More specifically, although Figure 2BThe components in are illustrated as residing within the user computing device 102a, but this is a non-limiting example. In some embodiments, one or more of these components may reside outside the user computing device 102a. Similarly, although Figure 2B Reference is made to a user computing device 102a, but other components, such as an administrator computing device 102c, may include similar hardware, software, and / or firmware.

[0043] Reference now Figure 3 , provides a flowchart graphically depicting an illustrative method 300 for facilitating key seminal question search queries. Figure 3 The steps associated with the blocks will be described as separate tasks, but in other embodiments, the blocks may be combined or omitted. Figure 3 The steps associated with the blocks will be described as being performed in a particular order, but in other embodiments, the steps may be performed in a different order.

[0044] Still refer to Figure 3 At block 302, the case mining device 102b ( Figure 1 ) may send data related to a particular legal issue and data related to groundbreaking cases addressing the particular legal issue to the user computing device 102a ( Figure 1 ). From the case mining device 102b ( Figure 1 ) is sent to the user computing device 102a ( Figure 1 ) is intended to enable the user computing device 102a ( Figure 1 ) know which cases are groundbreaking cases, so as to move these cases to the top of the search result list or otherwise indicate groundbreaking cases or distinguish them from other cases. That is, the case mining device 102b ( Figure 1 ) can generate the display logic 282c ( Figure 2B ) displayed. It should be understood that from the case mining device 102b ( Figure 1 ) has been sent by the case mining device 102b ( Figure 1 ) compilation, and case mining device 102b ( Figure 1 ) can automatically transmit the data at predetermined times and / or intervals.

[0045] At block 304, a graphical user interface is displayed. In some embodiments, the graphical user interface is displayed on the user computing device 102a ( Figure 1). The graphical user interface described herein can display groundbreaking cases based on a legal issue search in an intuitive and user-friendly manner, such that at least one groundbreaking case for a legal issue queried by the user can be displayed at the top of a search result list or otherwise indicated in the search results or distinguished from other cases. In some embodiments, the computer network 100 is the Internet, and the graphical user interface described herein is presented to the user on a display device of the user computing device 102a via a web browser.

[0046] Still refer to Figure 3 At block 306, a search query may be generated by a user and executed by the user computing device 102a ( Figure 1 ) receives the search query. In some embodiments, the search query received at block 306 may have been input into a browser that is hosted by the user computing device 102a ( Figure 1 ) is displayed. The user interface may be configured to receive a search query from a user and initiate a search. Once the search query is received, in response to the user initiating the search (i.e., by pressing enter or selecting a search initiation icon, or by entering text that is automatically searched), the user computing device 102a ( Figure 1 ) can perform a search query for data or information related to one or more legal issues being queried by the user, and display the search results at box 308. When displaying cases in the search results, the search results can be displayed using the data from the case mining device 102b ( Figure 1 ) to indicate which of the cases related to the legal issue being queried are seminal cases by moving the cases to the top of a search result list or otherwise indicating seminal cases or distinguishing them from other cases.

[0047] Reference now Figure 4 , provides a flowchart graphically illustrating an illustrative method 400 of mining text document data to identify one or more seminal cases that address a particular legal issue, according to one or more embodiments. Figure 4 The steps associated with the blocks will be described as separate tasks, but in other embodiments, the blocks may be combined or omitted. Figure 4 The steps associated with the boxes will be described as being performed in a particular order, but in other embodiments, the steps may be performed in a different order. Figure 4 As a result of the described process, data is generated, which may be accessed by an external device (e.g., user computing device 102a ( Figure 1) to complete one or more additional processes with the generated data (e.g., conducting a search and indicating groundbreaking cases in the search results).

[0048] Still refer to Figure 4 During the data generation process, at block 405, the system obtains all electronic documents from a corpus (e.g., a legal corpus). For example, the electronic documents may be obtained from a repository containing electronic documents (e.g., a legal case reporter repository). In some embodiments, such a repository may be local. For example, as described in more detail herein, the electronic documents may be obtained from the data storage component 236 ( Figure 2A ) to obtain the electronic document from the electronic document data 238a. In other embodiments, the document may be obtained from an off-site data storage repository (such as a repository of an electronic document publisher, etc.). The document is typically an electronic document and may typically contain information arranged in paragraph form. In some embodiments, the document may be a legal document, such as, for example, case law, statutes, complaints, pleadings, legal memoranda, etc., and the electronic document may contain a compilation of abstracts, compilation of citations, etc.

[0049] At box 410, the text in the electronic document is searched for multiple citation reasons or summaries. Multiple citation reasons or summaries usually contain multiple legal issue texts and other texts related to the importance of the legal issue being discussed, such as whether the ruling or argument is based on a groundbreaking case or a landmark case. That is, multiple citation reasons or summaries can identify potential groundbreaking cases and / or identify the outstanding issues discussed by each groundbreaking case. In other words, the legal issues that make groundbreaking cases confirmed or recognized can be identified. Therefore, once multiple citation reasons are identified, multiple citation reason texts are searched at box 415 to identify groundbreaking clues or keywords indicating potential groundbreaking cases at box 420 and generate a data list containing all citation reasons or summaries, and all citation reasons or summaries contain the potential groundbreaking cases. The groundbreaking clues or keywords to be identified can be keywords or groundbreaking clues stored in keyword data 238b (Fig. 2). These keywords or seminal clues are identifiers that, in the opinion of the authoring judge in the reasons or briefs for citing the seminal case in a subsequent case, indicate the belief and / or authoritative thinking that the case referenced or cited has significance, influence, or is a precedent for the current case with respect to the specific legal provision in question. Therefore, these authoring judges often use keywords or seminal clues to indicate that the case cited is a seminal case. Keywords or seminal clues may include, for example, seminal case, seminal ruling, seminal opinion, seminal ruling, seminal ruling, seminal determination, landmark case, landmark ruling, landmark opinion, landmark determination, landmark ruling, leading case, leading ruling, leading opinion, leading determination, leading ruling, etc.

[0050] Based on the identification of multiple groundbreaking cases by searching for multiple citation reasons at box 410 and the data list containing multiple groundbreaking clues generated at box 420, multiple potential groundbreaking cases are identified within the data list at box 425. The data list containing potential groundbreaking cases is filtered at box 430, so that only groundbreaking cases based on the calculated groundbreaking reference frequency are identified at box 435 and a working corpus is generated. It should be understood that the working corpus is generated from the filtered data list. Further, groundbreaking cases are identified in the following manner: the frequency at which groundbreaking clues or keywords are mentioned is calculated for each potential groundbreaking case, and any potential groundbreaking cases with low frequencies for the keywords are subsequently removed from the data list. The working corpus of groundbreaking cases corresponds to the multiple citation reasons identified from box 410. In some embodiments, there may be more than one citation reference that mentions a potential groundbreaking case or more than one reference that may cite a potential groundbreaking case. For example, the citation reasons of the hypothetical case Harris v. Fisher include the hypothetical case Smith v. Jones, and wherein Smith v. Jones is mentioned in six lawsuits and each of these lawsuits includes a seminal clue. Smith v. Jones may be a seminal case, or it may be a common citation of a seminal case. Therefore, further investigation (such as frequency calculation) is needed to confirm whether Smith v. Jones is relevant and whether Smith v. Jones is actually a seminal case. During the investigation, it was determined that five of the six lawsuits of Smith v. Jones actually cited another case (e.g., Younger v. Harris) and the last lawsuit cited another case Monroe v. Pape. In this way, because it can now be determined that Smith v. Jones itself is not a seminal case for this particular legal issue, on the contrary Younger v. Harris may be a seminal case, the hypothetical case Smith v. Jones can now be considered a co-seminal citation. Therefore, because Smith v. Jones only cites other cases that may be seminal cases, Smith v. Jones may be removed from the data set when filtering is performed at blocks 430-435. Filtering keywords and ultimately cases from the data set is important to ensure that only potentially seminal cases based on the frequency of seminal references are included within the data set. Thus, the data set includes only seminal cases.

[0051] At box 440, multiple legal issue texts of all seminal cases in the working corpus are mined from multiple citation reasons or summaries, which are determined from the seminal cases identified according to box 435 and based on the multiple citation reasons with multiple legal issue texts according to box 410.

[0052] At box 445, sentence data comprising a plurality of sentences is established from the text of the plurality of legal issues of all seminal cases in the working corpus according to box 440, the plurality of sentences having text including a plurality of legal discussions of the plurality of legal issues from the seminal cases. The sentence data isolates sentences having legal discussions including a plurality of seminal threads. At box 450, each of the plurality of sentences within the sentence data is assigned a unique identifier along with the cited case or referenced seminal case. An example uniquely identified sentence may be used for the hypothetical case of Harris v. Fisher, where the Harris case would be assigned a unique identifier for any related sentences, such as "More importantly, the Supreme Court, after a thorough review of informed consent cases, concluded that legally competent persons have a liberty interest in refusing unwarranted medical treatment under the Due Process Clause."

[0053] At block 455, a determination is made as to whether there are additional seminal cases in the working corpus that contain legal discussions from the plurality of legal issues that have not yet been assigned a unique identifier. If there are additional seminal cases, the process is repeated at block 445. If, at block 450, all of the seminal cases in the working corpus already have a unique identifier assigned to each sentence, the process may continue at block 460. For each of the plurality of seminal cases, all of the plurality of sentences in the sentence data are collected at block 460 and stored at block 465 in seminal case data 238d (FIG. 2) as temporary sentence data for each seminal case.

[0054] At box 470, a text clustering algorithm can be used or applied to each of a plurality of sentences having a unique identifier and stored as temporary sentence data to create a plurality of text clusters. The text clustering algorithm can be used to identify sentences within the citation text that potentially address seminal issues. That is, the text clustering algorithm is configured to analyze a plurality of sentences within the temporary sentence data in the following manner: the text of the plurality of sentences is transformed into transformed data so that the algorithm can create a plurality of cluster-wise labels representing the data contained in these clusters. The transformed data is then normalized and analyzed using a plurality of text clustering tools (i.e., open source tools such as RapidMiner, KNIME Analytics, Open Calais, etc.) to determine the data that best represents the seminal issues while removing data that does not represent key legal issues.

[0055] At box 475, at least one top cluster is selected from a plurality of text clusters. The at least one top cluster includes one or more sentences discussing groundbreaking legal issues for a particular groundbreaking case. It should be understood that when there are two clusters, the two clusters include one or more sentences discussing groundbreaking legal issues for a particular groundbreaking case, a human editor can determine whether one cluster is used or both clusters are used. It should also be understood that by selecting at least one top cluster, other sentences from a plurality of citation reasons or summaries are removed from the temporary sentence data. More specifically, the system is biased toward sentences citing keywords (i.e., words such as "leading", "groundbreaking", etc.). Therefore, sentences within the citation reason text that are not focused on groundbreaking legal issues for a particular groundbreaking case can be discarded. In the case of identifying at least one top cluster, at box 480, data corresponding to groundbreaking cases from a working corpus is output. When one or more groundbreaking cases in the groundbreaking case are returned as a result of the search, the output data enables an external device (such as user computing device 102a) to distinguish the groundbreaking cases.

[0056] The outputted data is based on at least one top cluster selected from the plurality of text clusters at block 475. It should be appreciated that the data, including metadata, may be accessed by the user computing device 102a ( Figure 1 ) is used to display the search results in a manner that distinguishes seminal cases or otherwise indicates the presence of seminal cases. However, it should be understood that data can also be output according to block 475 to other devices that utilize the data in other ways (e.g., not for indicating documents in search results).

[0057] refer to Figure 5, a flowchart of an illustrative method 500 for selecting citations to represent seminal issues is provided according to one or more embodiments. In an embodiment, once at least one top cluster is selected, a set of normalized key terms representing one or more seminal issues identified using each seminal case is represented from all sentences of at least one top cluster at box 510. That is, a text clustering algorithm is used to analyze multiple cluster-oriented labels representing data contained in these clusters to identify data that best represents seminal issues, so that the top clusters with the most relevant sentences can be identified, and the data within those sentences can be searched to identify the set of key terms representing seminal legal issues. The identification of a normalized set of key terms can be calculated based on the weights and frequencies of the terms. At box 520, multiple citations associated with each seminal case are collected. At box 530, multiple citations are scanned, and multiple normalized terms can be extracted from the multiple citations. For example, the term "US citizen" can be described by multiple similar terms. That is, the term "US citizen" may also be referred to as "citizen of the United States", "United States citizen", "US citizen", "citizens of the United States", "citizen of United States", etc. Therefore, the key term may be referred to as a normalized key term.

[0058] At box 540, once a normalized set of key terms is extracted, the normalized key terms for each of the multiple citation reasons extracted in box 530 are compared with a set of normalized key terms representing the seminal issues from each seminal case generated at box 510. At box 550, the semantic distance between a set of key terms identified in the multiple citation reasons and the multiple terms of each of the multiple citation reasons is determined. The semantic distance can be determined by calculating the cosine similarity between the normalized key terms and the multiple terms within the multiple citation reason terms. The cosine similarity can be a calculation of the cosine angle θ between the vector of the normalized key term and the vector of the multiple terms, so as to determine whether the terms are similar based on the value of θ. That is, each of the multiple terms within the multiple citation reasons has a term vector that can be calculated to be closest to the normalized key term, and then the term vector is selected to represent the seminal issue. In one embodiment, the system can identify two different top text clusters that focus on different issues at the same time. If two top text clusters are identified, the system can select two citation reasons (i.e., one citation reason for each top text cluster). If necessary, an individual may review both citations and select one of them as the abstract to represent the seminal issue.

[0059] At block 560, a particular citation may then be selected based on the semantic distance between the set of key terms and the plurality of terms as discussed above with reference to block 550. The particular citation may represent a seminal issue addressed by the seminal case. At block 570, the legal issue of the citation is then assigned to the seminal case as its seminal issue.

[0060] Reference now Figure 6 , the graphical user interface 600 includes a legal question query field 610 and a result list 620. The legal question query field 610 is configured to request submission of a legal question search query from a user. In some embodiments, text input may be provided in the legal question query field 610, such as in Figure 6 , an illustrative user input of the term “search and seizure” depicted in FIG. 1 . In some embodiments, a separate search screen (e.g., a user interface with a search box and a “Search” button or a user interface with a search box that immediately causes a search to be run upon entering text) may have been provided to the user that is used by the user to enter a search query, such as by typing a legal issue search query into the search box.

[0061] Search results 620 display multiple cases related to the searched legal issue. The cases displayed in search results 620 are provided as seminal cases 630, 640 and are moved to the top of the search results list. That is, with respect to the legal issue search query "search and seizure," two seminal cases 630, 640 are identified and moved to the top of search results 620. The first seminal case is Katz v. United States and the second seminal case is Terry v. Ohio. Thus, the interface is provided so that the user can visually identify these two cases as two seminal cases related to the legal issue search for "search and seizure." The data used to identify and indicate seminal cases in the search results is provided as part of the description herein of the seminal cases. Figure 4 It should be understood that groundbreaking cases may not be pushed or moved to the top of the search results, but may be indicated or distinguished in other ways, such as highlighting, starring, marking, etc., so that visually, users can easily recognize that these cases are groundbreaking cases for a particular legal issue.

[0062] It should be understood that the disclosed systems, methods, and computer program products are configured to identify one or more groundbreaking cases within a database containing various text documents. More specifically, the disclosed systems, methods, and computer program products provide a way to identify one or more groundbreaking cases and the legal issues resolved by a particular groundbreaking case by mining a text database containing legal documents. Traditionally, groundbreaking cases and their corresponding legal issues stored in a database are not marked or otherwise identified. This is because it is usually not known at the time of publication whether a case will eventually become particularly important in a particular legal field. In addition, the disclosed systems, methods, and computer program products send data to a search computer for the purpose of improving search results. In addition, the disclosed method uses a novel or unconventional approach to mine a text document database for one or more groundbreaking cases and the corresponding issues resolved by each case.

[0063] Although specific embodiments have been shown and described herein, it should be understood that various other changes and modifications may be made without departing from the spirit and scope of the claimed subject matter. In addition, although various aspects of the claimed subject matter have been described herein, these aspects need not be utilized in combination. Therefore, the appended claims are intended to cover all such changes and modifications within the scope of the claimed subject matter.

Claims

1. A system for identifying one or more seminal cases that address a particular legal issue, the system comprising: Processing equipment; as well as a non-transitory processor-readable storage medium in communication with the processing device, the non-transitory processor-readable storage medium comprising one or more programming instructions that, when executed, cause the processing device to: Retrieving an electronic legal document from a repository, the electronic legal document comprising a plurality of texts, searching the plurality of texts of the electronic legal document for a plurality of citations including a plurality of legal issue texts, searching the plurality of citation reasons to identify a plurality of seminal threads based on indicators of the importance and / or influence that the authoring judges attached to particular legal provisions discussed in the plurality of legal issue texts; generating a data list from the plurality of cited reasons to identify a plurality of potential groundbreaking cases through the plurality of groundbreaking clues, filtering the data list containing the plurality of potential seminal cases to identify only seminal cases based on the calculated seminal reference frequencies and generating a working corpus from the filtered data list, and Data corresponding to the seminal cases from the working corpus is output such that when one or more of the seminal cases are returned as a result of a search, the data enables an external device to distinguish the seminal cases.

2. The system of claim 1 , wherein the calculated seminal reference frequency is determined by a predetermined set of rules configured to determine the number of times a particular case is cited as a seminal case to establish a frequency. The system according to claim 1 , wherein the citation reason text is a summary text.

4. The system of claim 1 , wherein the non-transitory processor-readable storage medium further comprises one or more programming instructions that, when executed, cause the processing device to: mining the plurality of legal issue texts from the plurality of cited reasons of all the seminal cases in the working corpus to establish sentence data, the sentence data comprising a plurality of sentences including a plurality of legal discussions of the plurality of legal issue texts from the seminal cases in the working corpus, assigning a unique identifier to each of the plurality of sentences that reference the seminal case, for each seminal case in the working corpus, collecting the sentences of the plurality of sentences from the sentence data, for each of the seminal cases in the working corpus, storing the collected sentences from the sentence data as temporary sentence data, applying a text clustering algorithm to the temporary sentence data to create a plurality of text clusters, and A top cluster is selected from the plurality of text clusters, wherein the top cluster includes one or more sentences surrounding the plurality of legal issue texts identified with each of the seminal cases.

5. The system of claim 4, wherein selecting the top cluster from the plurality of text clusters of the provisional sentence data removes the sentences that are not focused on the plurality of legal issue texts identified with seminal cases from the provisional sentence data. The system of claim 4 , wherein the top clusters are a plurality of sentences.

7. The system of claim 4, wherein the non-transitory processor-readable storage medium further comprises one or more programming instructions that, when executed, cause the processing device to: generating a set of normalized key terms from the one or more sentences of the top cluster, the set of normalized key terms representing seminal issues identified with each seminal case, collecting said plurality of citations associated with each seminal case, For each of the plurality of citation reasons, scanning and extracting a plurality of normalized terms, comparing the set of normalized key terms to the plurality of normalized terms, determining a semantic distance between the set of normalized key terms and the plurality of normalized terms for each citation reason, selecting a particular citation justification based on the semantic distance between the set of normalized key terms and the plurality of normalized terms, and The specific legal issue of the plurality of legal issue texts of the cited reasons is assigned to the pioneering case as the pioneering issue.

8. The system of claim 7, wherein the selected citation is the centroid of at least one of the seminal issues in the seminal case.

9. The system of claim 7, wherein: The semantic distance is determined by calculating a cosine similarity between the set of normalized key terms and the plurality of normalized terms for each of the plurality of citation reasons, and For each of the plurality of citation reasons, the selected term of the plurality of normalized terms is a closest vector to the set of normalized key terms.

10. A method for identifying one or more seminal cases that address a particular legal issue, the method comprising: Retrieving, by a processing device, an electronic legal document from a repository, the electronic legal document comprising a plurality of texts; searching, by the processing device, the plurality of texts of the electronic legal document for a plurality of citations including a plurality of legal issue texts; searching, by the processing device, the plurality of citation reasons to identify a plurality of seminal clues based on indicators of importance and / or influence that the authoring judge had on particular legal provisions discussed in the plurality of legal issue texts; generating, by the processing device, from the plurality of cited reasons, a data list identifying a plurality of potential groundbreaking cases through the plurality of groundbreaking clues; filtering, by the processing device, the data list containing the plurality of potential seminal cases to identify only seminal cases based on the calculated seminal reference frequencies and generating a working corpus from the filtered data list; mining, by the processing device, the plurality of legal issue texts from the plurality of cited reasons of all the seminal cases in the working corpus to establish sentence data, the sentence data comprising a plurality of sentences including a plurality of legal discussions of the plurality of legal issue texts from the seminal cases in the working corpus; assigning, by the processing device, a unique identifier to each of the plurality of sentences that reference the seminal case; collecting, by the processing device, for each of the seminal cases in the working corpus, each of the plurality of sentences from the sentence data and storing the collected sentences from the sentence data as temporary sentence data; applying, by the processing device, a text clustering algorithm to the temporary sentence data to create a plurality of text clusters; selecting, by the processing device, a top cluster from the plurality of text clusters, wherein the top cluster includes one or more sentences surrounding the plurality of legal discussions and the plurality of legal issue texts identified with each of the seminal cases; as well as Data corresponding to the seminal cases from the working corpus is output to a user display device such that when one or more of the seminal cases are returned as a result of a search, the data enables the user display device to distinguish the seminal cases.

11. The method of claim 10, wherein the calculated seminal reference frequency is determined by a predetermined set of rules configured to determine the number of times a particular case is cited as a seminal case to establish the frequency. The method according to claim 10 , wherein the citation reason text is a summary text.

13. The method of claim 10, wherein selecting the top cluster from the plurality of text clusters of the temporary sentence data removes the sentences that are not focused on the plurality of legal issue texts identified with seminal cases from the citation text.

14. The method according to claim 10, further comprising: generating, by the processing device, a set of normalized key terms from the one or more sentences of the top cluster, the set of normalized key terms representing seminal issues identified with each seminal case; collecting, by the processing device, the plurality of citations associated with each seminal case; Scanning and extracting, by the processing device, a plurality of normalized terms for each of the plurality of citation reasons; comparing, by the processing device, the set of normalized key terms with the plurality of normalized terms for each of the plurality of citation reasons; determining, by the processing device, a semantic distance between the set of normalized key terms and the plurality of normalized terms; selecting, by the processing device, a specific citation reason based on the semantic distance between the set of normalized key terms and the plurality of normalized terms; as well as By means of the processing device, the specific legal issue of the plurality of legal issue texts of the cited reasons is assigned to the pioneering case as the pioneering issue.

15. The method of claim 14, wherein the selected citation is a centroid of at least one of the plurality of legal issues in the seminal case.

16. The method of claim 14, wherein: calculating the semantic distance by calculating the cosine similarity between the set of normalized key terms and the plurality of normalized terms for each of the plurality of citation reasons, and Wherein for each of the plurality of citation reasons, the term of the plurality of normalized terms is a vector closest to the set of normalized key terms.

17. A non-transitory computer-readable storage medium operable by a computer to identify one or more seminal cases that address a particular legal issue, the non-transitory computer-readable storage medium comprising one or more programming instructions stored thereon for causing a processing device to: Retrieving an electronic legal document from a repository, the electronic legal document comprising a plurality of texts, searching the plurality of texts of the electronic legal document for a plurality of citations comprising a plurality of legal issue texts, searching the plurality of citations to identify a plurality of seminal leads, and generating from the plurality of citations a data list identifying a plurality of potential seminal cases through the plurality of seminal leads, the plurality of seminal leads being based on indicators that the authoring judges attributed importance and / or influence to particular legal provisions discussed in the plurality of legal issue texts, filtering the data list containing the plurality of potential seminal cases to identify only seminal cases based on the calculated seminal reference frequencies and generating a working corpus from the filtered data list, and Data corresponding to the seminal cases from the working corpus is output such that when one or more of the seminal cases are returned as a result of a search, the data enables an external device to distinguish the seminal cases.

18. The non-transitory computer-readable storage medium of claim 17, further comprising one or more programming instructions stored thereon for causing the processing device to: mining the plurality of legal issue texts from the plurality of cited reasons of all the seminal cases in the working corpus to establish sentence data, the sentence data comprising a plurality of sentences including a plurality of legal discussions of the plurality of legal issue texts from the seminal cases in the working corpus, assigning a unique identifier to each of the plurality of sentences that reference the seminal case in the working corpus, collecting each of the plurality of sentences from the sentence data, storing the collected sentences from the sentence data as temporary sentence data for the pioneering case in the working corpus, applying a text clustering algorithm to the temporary sentence data to create a plurality of text clusters, and A top cluster is selected from the plurality of text clusters, wherein the top cluster includes one or more sentences surrounding the plurality of legal issue texts identified using seminal cases.

19. The non-transitory computer-readable storage medium of claim 18, wherein the instructions are configured to cause the processing device to select the top cluster from the plurality of text clusters of the temporary sentence data to remove the sentences that are not focused on the plurality of legal issue texts identified using seminal cases from the temporary sentence data.

20. The non-transitory computer-readable storage medium of claim 18, further comprising one or more programming instructions stored thereon for causing the processing device to: generating a set of normalized key terms from the one or more sentences of the top cluster, the set of normalized key terms representing seminal issues identified with the seminal cases, collecting said plurality of citations associated with said seminal case, For each of the plurality of citation reasons, scanning and extracting a plurality of normalized terms, comparing the set of normalized key terms to the plurality of normalized terms, determining a semantic distance between the set of normalized key terms and the plurality of normalized terms, and A citation reason is selected based on the semantic distance between the set of normalized key terms and the plurality of normalized terms, and the specific legal issue of the plurality of legal issue texts of the reasons of the citation reason is assigned to the seminal case as the seminal issue.

Images