CN111324740B

CN111324740B - Dispute event identification method, identification device and identification system

Info

Publication number: CN111324740B
Application number: CN201811528340.6A
Authority: CN
Inventors: 马康炜
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-12-13
Filing date: 2018-12-13
Publication date: 2023-05-02
Anticipated expiration: 2038-12-13
Also published as: CN111324740A

Abstract

The application discloses a method, a device and a system for identifying dispute events. Wherein the method comprises the following steps: obtaining dispute description information of dispute events; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment. The method and the device solve the technical problem that the existing contradiction reconciliation system is inaccurate in identifying the dispute event.

Description

Dispute event identification method, identification device and identification system

Technical Field

The present invention relates to the field of computers, and in particular, to a method, an apparatus, and a system for identifying a dispute event.

Background

With the rapid development of computer technology, the internet brings convenience to all sides of people's life and work. In life, people can purchase goods without going out; in work, people can realize remote office. People can also mediate dispute events through the Internet. However, the existing contradiction reconciliation system has a plurality of entries, when people report dispute events through the contradiction reconciliation system, the same event may be reported multiple times through different entries, and for example, for the same contradiction event, the parties may report to the contradiction reconciliation system independently; alternatively, the same principal may repeatedly report to the conflict mediating system multiple times for the same contradictory event. In this way, in the dispute event reconciliation process, multiple departments reconcile the same event at the same time, so that dispute event identification is inaccurate.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the application provides a method, a device and a system for identifying dispute events, which are used for at least solving the technical problem that the existing contradiction reconciliation system is inaccurate in identifying the dispute events.

According to an aspect of an embodiment of the present application, there is provided a method for identifying a dispute event, including: obtaining dispute description information of dispute events; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment.

According to another aspect of the embodiments of the present application, there is also provided an apparatus for identifying a dispute event, including: the acquisition module is used for acquiring dispute description information of the dispute event; the determining module is used for determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and the sending module is used for sending the search result to the target object.

According to another aspect of the embodiments of the present application, there is also provided a system for identifying a dispute event, including: a communication module and a processor; the communication module is used for receiving a query request of a user and sending a search result of the processor to the user terminal equipment; the processor is used for acquiring dispute description information of the dispute event and a pre-constructed dispute knowledge graph under the triggering of the query request, wherein the dispute knowledge graph at least comprises entity elements in the historical dispute description information and logic relations among the entity elements in the historical dispute description information; and determining search results of the dispute event based on the dispute description information and the pre-constructed dispute knowledge graph.

According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program, wherein the program, when executed, controls a device in which the storage medium is located to perform the steps of: obtaining dispute description information of dispute events and a pre-constructed dispute knowledge graph; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment.

In the embodiment of the application, a manner of identifying the dispute event based on the knowledge graph is adopted, after dispute description information of the dispute event is obtained, a search result of the dispute event is determined based on the dispute description information and a pre-constructed dispute knowledge graph, and the search result is sent to user side equipment, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information.

In the process, the dispute knowledge graph comprises the entity elements and the logic relations among the entity elements, so that dispute events reported by the same event through different entrances can be automatically identified in a manner based on the dispute knowledge graph, the same department is ensured to process the same dispute event, the interference of irrelevant information is avoided, and the accuracy of search results of the dispute events is improved.

Therefore, the technical problem that the existing contradiction reconciliation system is inaccurate in identifying the dispute event can be solved by the scheme provided by the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

Fig. 1 is a hardware block diagram of a computer terminal for implementing a method for identifying a dispute event according to an embodiment of the present application;

FIG. 2 is a flow chart of a method of identifying a dispute event according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a display interface of an alternative client device according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an alternative dispute knowledge graph according to an embodiment of the present application;

FIG. 5 is a block diagram of an alternative dispute event based identification method according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a dispute event identification device according to an embodiment of the present application;

fig. 7 is a block diagram of a computer terminal according to an embodiment of the present application;

fig. 8 is a flowchart of a method for identifying a dispute event according to an embodiment of the present application. and

Detailed Description

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, partial terms or terminology appearing in describing embodiments of the present application are applicable to the following explanation:

entity relation extraction refers to extracting and marking out entities from natural texts and relations among the entities.

Knowledge Graph, also called scientific Knowledge Graph, refers to a semantic network obtained by aggregating entities and relationships among the entities

The graph path mode refers to a connection mode of nodes and edges in graph theory.

Example 1

In accordance with embodiments of the present application, there is also provided an embodiment of a method of identifying a dispute event, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer executable instructions, and, although a logical sequence is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in a different order than that illustrated herein.

The method embodiment provided in the first embodiment of the present application may be executed in a mobile terminal, a computer terminal or a similar computing device. Fig. 1 shows a hardware block diagram of a computer terminal (or mobile device) for implementing a method of identifying a dispute event. As shown in fig. 1, the computer terminal 10 (or mobile device 10) may include one or more (shown as 102a, 102b, … …,102 n) processors 102 (the processors 102 may include, but are not limited to, a microprocessor MCU, a programmable logic device FPGA, etc. processing means), a memory 104 for storing data, and a transmission means 106 for communication functions. In addition, the method may further include: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power supply, and/or a camera. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

It should be noted that the one or more processors 102 and/or other data processing circuits described above may be referred to generally herein as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Furthermore, the data processing circuitry may be a single stand-alone processing module, or incorporated, in whole or in part, into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination to interface).

The memory 104 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the method for identifying dispute events in the embodiments of the present application, and the processor 102 executes the software programs and modules stored in the memory 104, thereby executing various functional applications and data processing, that is, implementing the method for identifying dispute events described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission means 106 is arranged to receive or transmit data via a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).

It should be noted herein that in some embodiments, the computer device (or mobile device) shown in FIG. 1 described above has a touch display (also referred to as a "touch screen" or "touch display"). In some embodiments, the computer device (or mobile device) shown in fig. 1 above has a Graphical User Interface (GUI) with which a user may interact with by touching finger contacts and/or gestures on a touch-sensitive surface, where the human-machine interaction functionality optionally includes the following interactions: executable instructions for performing the above-described human-machine interaction functions, such as creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving electronic mail, talking interfaces, playing digital video, playing digital music, and/or web browsing, are configured/stored in a computer program product or readable storage medium executable by one or more processors.

In the above operating environment, the present application provides a method for identifying dispute events as shown in fig. 2. Fig. 2 is a flowchart of a method for identifying a dispute event according to a first embodiment of the present application, as can be seen from fig. 2, the method includes the following steps:

step S202, obtaining dispute description information of a dispute event.

The server can be used as an execution main body of the identification method of the dispute, wherein the server is communicated with the user side equipment, dispute description information of the dispute is input to the server through the user side equipment, and the server can acquire the dispute description information of the dispute through the user side equipment.

Optionally, the dispute event in the step S202 may include, but is not limited to, civil disputes (e.g., property disputes), administrative disputes (e.g., medical and health disputes), legal disputes, etc. The number of the dispute events is multiple, the dispute description information comprises description information of the plurality of dispute events, and the description information of the dispute events comprises, but is not limited to, time, place, case related person and content of the dispute events.

In addition, it should be further noted that, the user may input the description information of the dispute through the user side device, where the user side device may have multiple entries through which the user inputs the description information of the dispute, for example, as shown in fig. 3, on a display interface of the user side device, the user may input the description information of the dispute by clicking a "village dispute" control to enter into a corresponding interface, or may input the description information of the dispute by clicking a "noise harassment" control to enter into a corresponding interface. Optionally, after obtaining the dispute description information of the dispute event, the server may further store the dispute description information of the dispute event input by the user, where the dispute description information is stored in the data server or may be stored in a database of a device where the server is located, and the application does not limit a specific storage location.

Step S204, determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information.

It should be noted that, the pre-constructed dispute knowledge graph may be stored in a server, and after obtaining dispute description information, the server uses the dispute description information input by the user as input of the dispute knowledge graph to obtain a search result of the dispute knowledge graph.

Optionally, fig. 4 shows a schematic structural diagram of an optional dispute knowledge graph, where each node in fig. 4 represents an entity element in the dispute knowledge graph, a connection between nodes represents a logical relationship between the entity elements, for example, node A1 and node A2 are logically processed to obtain node A3, node A3 is logically processed to obtain node A4, nodes B1, B2, B3 and B4 are logically processed to obtain node B5, node B5 is logically processed to obtain node B6, and nodes A4 and node B6 are logically processed to obtain the search result S. In the above process, the logical relationships between the entity elements include, but are not limited to, delineating wages, village disputes, business associates, and the like. For example, in fig. 4, node A1 and node A2 are bonds, node A3 is a borrower, and the borrower borrows the bonds, and the logical relationship between node A3 and nodes A1 and A2 is debt. For another example, node A3 is a building material manufacturer, node A4 is a construction company, and the construction company pays out the material cost of the building material manufacturer, and the logical relationship between node A3 and node A4 is arrears.

In an alternative scheme, different types of dispute events correspond to different dispute knowledge maps. After obtaining the dispute description information input by the user, the server determines the dispute type of the dispute event according to the dispute description information, for example, the server extracts keywords from the dispute description information, and after obtaining the keywords, the server determines the dispute type of the dispute event according to the keywords and the semantics of the context of the keywords, wherein the dispute type of the dispute event comprises but is not limited to civil disputes, administrative disputes, legal prosecution disputes and the like. After the dispute types of the dispute are determined, the server determines a dispute knowledge graph corresponding to the dispute types according to the dispute types of the dispute, and further obtains search results of the dispute according to the dispute description information and the corresponding dispute knowledge graph.

Step S206, the search result is sent to the user terminal device.

It should be noted that, in step S206, the search result of the dispute event may include whether the plurality of dispute events are the same event and/or which dispute events are the same event.

In addition, the user terminal device may be a terminal device used by a user who inputs the history dispute description information of the dispute, or may be a terminal device used by a user who handles the dispute (for example, a worker who adjusts the dispute).

In an alternative scheme, after obtaining the search result of the dispute, the server sends relevant information of the dispute to the terminal equipment of the staff handling the dispute according to the search result, so that the staff can handle the dispute. Meanwhile, the server can also send the search result to terminal equipment used by the party generating the dispute so that the party can know relevant information of the dispute, such as departments for processing the dispute, properties of the dispute and the like.

Based on the scheme defined in the steps S202 to S206, it may be known that, after the historical dispute description information of the dispute is obtained by identifying the dispute based on the knowledge graph, a search result of the dispute is determined based on the dispute description information and the pre-constructed dispute knowledge graph, and the search result is sent to the client device, where the dispute knowledge graph at least includes entity elements in the historical dispute description information and a logical relationship between entity elements in the historical dispute description information.

It is easy to notice that, because the dispute knowledge graph includes entity elements in the historical dispute description information and logic relations among the entity elements, the dispute events reported by the same event through different entrances can be automatically identified in a manner based on the dispute knowledge graph, the same department is ensured to process the same dispute event, the interference of irrelevant information is avoided, and the accuracy of search results of the dispute events is improved.

In some embodiments of the present application, the above dispute description information may be structured information, where the structured information at least includes entity elements of the dispute description information and a logical relationship between entities, and the dispute knowledge graph is equivalent to a historical event library and at least includes structured information of all historical events.

In an alternative scheme, the server needs to determine the dispute knowledge graph before determining the search result of the dispute event based on the dispute description information and the pre-constructed dispute knowledge graph. Specifically, the server firstly extracts word features and character features from the historical dispute description information, then inputs the word features and the character features into a preset learning model for recognition, obtains entity elements of dispute events and logical relations among the entity elements, and finally constructs dispute knowledge maps based on the entity elements and the logical relations.

The dispute description information of the dispute event may be dispute description information input by the user, or dispute description information read by the server from a case set of historical dispute events. Optionally, the case set of historical dispute events is stored in a data server.

Alternatively, as shown in the architecture diagram of the dispute-based recognition method shown in fig. 5, the preset learning model may be, but is not limited to, a Bi-LSTM (Bi-directional Long Short-Term Memory) model, where Word and character features input to the Bi-LSTM model are Word and Char. After Word and Char casting are input to the Bi-LSTM model, the server processes the output result of the Bi-LSTM model through a CRF (Conditional Random Field Algorithm ) algorithm to obtain entity elements of the dispute event and logic relations among the entity elements, and three entities (namely entity 1, entity 2 and entity 3) and three logic relations (namely relation 1, relation 2 and relation 3) are obtained as shown in FIG. 5. After obtaining entity elements of the dispute event and the logic relations between the entity elements, the server constructs a dispute knowledge graph based on the entity elements and the logic relations, namely, the dispute knowledge graph is obtained through pattern matching.

In an alternative scheme, after determining a dispute knowledge graph and obtaining dispute description information of a dispute event, a server extracts at least one entity element and a logic relationship between the at least one entity element from the dispute description information, determines a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and the logic relationship between the at least one entity element, searches based on a common neighbor algorithm, determines neighbor nodes of the node, determines a candidate event set based on the node corresponding to the at least one entity element and the neighbor nodes, finally determines a target event from the candidate event set, and takes the target event as a search result of the dispute event.

In the above process, the entity elements include at least time, place, case related person, event content, etc. of the dispute event, and the logical relationship between the entity elements may include, but is not limited to, delineating wages, village disputes, enterprise responsible persons, etc. For example, node a is Zhang three, node B is Lifour, zhang three is the enterprise responsible for Lifour, then the enterprise responsible is the logical relationship between node a and node B. For another example, node C is the XX company, node D is the farmer, and the XX company delineating the wages of the farmer, then the logical relationship between node C and node D is the delinquent wages.

In an alternative scheme, as can be seen from fig. 5, before determining the node corresponding to the at least one entity element in the dispute knowledge graph based on the logic relationship between the at least one entity element and the at least one entity element, the server further performs normalization processing on the logic relationship between the at least one entity element and the at least one entity element to obtain normalized data, and inputs the normalized data into the dispute knowledge graph. The server matches at least one entity element and logic relation with data in a preset standard data set, and takes the matched data as standardized data.

It should be noted that, different types of entity elements have different standardized processing procedures, for example, for address entity elements, an address engine may be used to perform standardized processing on the address entity elements; for the organization entity, the spelling error correction mode can be adopted for carrying out standardization treatment.

In addition, after standardized data is obtained by performing a standardized process on the physical elements and the logical relationships between the physical elements, the server updates the dispute knowledge graph based on the obtained standardized data.

Optionally, after updating the dispute knowledge graph, the server determines a node corresponding to the entity element in the updated dispute knowledge graph, and combines the node with a neighbor node obtained through a common neighbor algorithm to obtain a candidate event set, for example, if the neighbor node of the node A is the node B, the dispute event formed by the node A and the node B is used as a candidate event; and if the neighbor node of the node C is the node D, using the dispute event formed by the node C and the node D as another candidate event. Wherein the plurality of candidate events forms a candidate event set.

Further, the server sorts the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element, and determines the target event based on the preset number of candidate events with the highest sorting. Specifically, for each candidate event, the server determines a first scoring index and a first weight of the event type, and a second scoring index and a second weight corresponding to the node type, then determines a final scoring index of each candidate event based on the first scoring index, the first weight, the second scoring index and the second weight, and finally ranks the candidate events in the candidate event set based on the final scoring index.

In the above process, each node in the dispute knowledge graph has a node characteristic, and the node characteristic includes an event type and a node type of the node, where the event type characterizes a type of the dispute event, for example, a village dispute and a noise disturbing civil dispute; the node type characterizes the specific content of the node, such as a cell phone number, business name, organization name, time date, etc. Optionally, the more accurate the node type corresponds to the greater the second weight, for example, the higher the weight of the cell phone number than the weight of the organization name.

In an alternative scheme, after obtaining the final score index of each candidate event according to the event type and the node type of each candidate event, the server ranks according to the size of the final score index of each candidate event, and determines the target event based on the preset number of candidate events with the highest ranking, for example, selects the first 10% of candidate events in the ranking as the target event.

Further, as shown in fig. 5, after the dispute knowledge graph is generated, the server also feeds back the search result obtained based on the dispute knowledge graph to the user terminal device, and the user views the search result and processes the dispute event according to the search result.

It should be noted that, through the above scheme provided by the application, the dispute events are identified through the dispute knowledge graph, so that the interference of stop words and key information of non-dispute events is avoided, and the accuracy rate of dispute event identification is improved. In addition, the key entity information of the dispute scene is subjected to standardized processing, and the recall rate of dispute event identification is improved.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

From the above description of the embodiments, it will be clear to those skilled in the art that the method for identifying dispute events according to the above embodiments may be implemented by means of software plus a necessary general purpose hardware platform, or may be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.

Example 2

According to an embodiment of the present application, there is also provided a dispute event recognition device for implementing the dispute event recognition method, as shown in fig. 6, the device 60 includes: acquisition module 601, determination module 603 and transmission module 605.

The acquiring module 601 is configured to acquire historical dispute description information of a dispute event; the determining module 603 is configured to determine a search result of the dispute event based on the historical dispute description information and a pre-constructed dispute knowledge graph, where the dispute knowledge graph at least includes entity elements in the historical dispute description information and a logical relationship between entity elements in the historical dispute description information; and a sending module 605, configured to send the search result to the target object.

Here, the acquiring module 601, the determining module 603, and the transmitting module 605 correspond to steps S202 to S206 in embodiment 1, and the three modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the first embodiment. It should be noted that the above-described module may be operated as a part of the apparatus in the computer terminal 10 provided in the first embodiment.

In an alternative, the determining module includes: the device comprises an extraction module, a first determination module, a second determination module, a third determination module and an identification module. The extraction module is used for extracting at least one entity element and a logic relationship between the at least one entity element from the dispute description information; the first determining module is used for determining nodes corresponding to at least one entity element in the dispute knowledge graph based on the logic relationship between the at least one entity element and the at least one entity element; the second determining module is used for searching based on a common neighbor algorithm and determining neighbor nodes of the nodes; the third determining module is used for determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and the identification module is used for determining a target event from the candidate event set and taking the target event as a search result of the dispute event.

In an alternative solution, the dispute identification device further includes: the processing module and the input module. The processing module is used for carrying out standardized processing on at least one entity element and the logic relationship between the at least one entity element to obtain standardized data; and the input module is used for inputting the standardized data into the dispute knowledge graph.

In an alternative, the processing module includes: and a matching module. The matching module is used for matching at least one entity element and logic relation with data in a preset standard data set, and taking the matched data as standardized data.

Optionally, the plurality of dispute events are multiple, and the historical dispute description information comprises description information of the plurality of dispute events.

In an alternative, the identification module includes: the first ordering module and the fourth determining module. The first ordering module is used for ordering the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element; and a fourth determining module, configured to determine a target event based on a preset number of candidate events with highest ranking.

In an alternative, the first sorting module includes: the fifth determining module, the sixth determining module and the second sorting module. The fifth determining module is used for determining a first scoring index and a first weight of the event type and a second scoring index and a second weight corresponding to the node type for each candidate event; a sixth determining module configured to determine a final score indicator for each candidate event based on the first score indicator, the first weight, the second score indicator, and the second weight; and the second ranking module is used for ranking the candidate events in the candidate event set based on the final scoring index.

In an alternative, the dispute knowledge graph is determined by: extracting word features and character features from the historical dispute description information; inputting word features and character features into a preset learning model for recognition to obtain entity elements of dispute events and logic relations among the entity elements; and constructing a dispute knowledge graph based on the entity elements and the logic relations.

Example 3

According to an embodiment of the present application, there is also provided a system for identifying a dispute event for implementing the method for identifying a dispute event, where the system includes: a communication module and a processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

The communication module is used for receiving a query request of a user and sending a search result of the processor to the user terminal equipment; the processor is used for acquiring dispute description information of the dispute event and a pre-constructed dispute knowledge graph under the triggering of the query request, wherein the dispute knowledge graph at least comprises entity elements in the historical dispute description information and logic relations among the entity elements in the historical dispute description information; and determining search results of the dispute event based on the dispute description information and the pre-constructed dispute knowledge graph.

It can be known from the above that, by adopting a manner of identifying the dispute event based on the knowledge graph, after obtaining the dispute description information of the dispute event, determining the search result of the dispute event based on the dispute description information and the pre-constructed dispute knowledge graph, and sending the search result to the client device, wherein the dispute knowledge graph at least comprises entity elements in the historical dispute description information and logic relations among the entity elements in the historical dispute description information.

It is easy to notice that because the dispute knowledge graph comprises entity elements and logic relations among the entity elements, dispute events reported by the same event through different inlets can be automatically identified in a manner based on the dispute knowledge graph, the same department is ensured to process the same dispute event, the interference of irrelevant information is avoided, and the accuracy of search results of the dispute events is improved.

In an alternative scheme, the processor further extracts at least one entity element and a logic relation between the at least one entity element from the dispute description information, determines a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and the logic relation between the at least one entity element, searches based on a common neighbor algorithm, determines neighbor nodes of the node, determines a candidate event set based on the node corresponding to the at least one entity element and the neighbor nodes, and finally determines a target event from the candidate event set, and takes the target event as a search result of the dispute event.

In an alternative scheme, before determining the node corresponding to the at least one entity element in the dispute knowledge graph based on the logic relationship between the at least one entity element and the at least one entity element, the processor further performs standardization processing on the logic relationship between the at least one entity element and the at least one entity element to obtain standardized data, and inputs the standardized data into the dispute knowledge graph.

The processor matches at least one entity element and logic relation with data in a preset standard data set, and takes the matched data as standardized data.

Optionally, the number of the dispute events is multiple, and the dispute description information includes description information of the plurality of dispute events.

In one alternative, after determining the candidate event set, the processor determines a target event from the candidate event set. Specifically, the processor sorts the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element, and determines the target event based on the preset number of candidate events with the highest sorting.

Optionally, the process of the processor sorting the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element is as follows. First, a processor determines a first scoring index and a first weight of an event type and a second scoring index and a second weight corresponding to a node type for each candidate event, then, the processor determines a final scoring index of each candidate event based on the first scoring index, the first weight, the second scoring index and the second weight, and ranks the candidate events in the candidate event set based on the final scoring index.

In one alternative, the processor may determine the dispute knowledge graph as follows. Specifically, the processor extracts word features and character features from the historical dispute description information, then inputs the word features and character features into a preset learning model for recognition, obtains entity elements of dispute events and logical relations among the entity elements, and finally builds a dispute knowledge graph based on the entity elements and the logical relations.

Example 4

Embodiments of the present application may provide a computer terminal, which may be any one of a group of computer terminals. Alternatively, in the present embodiment, the above-described computer terminal may be replaced with a terminal device such as a mobile terminal.

Alternatively, in this embodiment, the above-mentioned computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

In this embodiment, the computer terminal may execute the program code of the following steps in the method for identifying a dispute event: obtaining dispute description information of dispute events; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment.

Alternatively, fig. 7 is a block diagram of a computer terminal according to an embodiment of the present application. As shown in fig. 7, the computer terminal a may include: one or more (only one is shown) processors 702, memory 704, and transmission means 706.

The storage may be used to store a software program and a module, for example, a program instruction/module corresponding to the method and the device for identifying a dispute event in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software program and the module stored in the storage, so as to implement the method for identifying a dispute event. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory remotely located with respect to the processor, which may be connected to terminal a through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor may call the information and the application program stored in the memory through the transmission device to perform the following steps: obtaining dispute description information of dispute events; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment.

Optionally, the above processor may further execute program code for: extracting at least one entity element and a logic relation between the at least one entity element from dispute description information; determining a node corresponding to at least one entity element in the dispute knowledge graph based on the at least one entity element and the logic relationship between the at least one entity element; searching based on a common neighbor algorithm, and determining neighbor nodes of the nodes; determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and determining a target event from the candidate event set, and taking the target event as a search result of the dispute event.

Optionally, the above processor may further execute program code for: carrying out standardization processing on at least one entity element and a logic relationship between at least one entity element to obtain standardized data; and inputting the standardized data into the dispute knowledge graph.

Optionally, the above processor may further execute program code for: and matching at least one entity element and the logic relation with the data in the preset standard data set, and taking the matched data as standardized data.

Optionally, the above processor may further execute program code for: sorting the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element; and determining the target event based on the highest-ranking preset number of candidate events.

Optionally, the above processor may further execute program code for: for each candidate event, determining a first scoring index and a first weight of the event type, and a second scoring index and a second weight corresponding to the node type; determining a final scoring indicator for each candidate event based on the first scoring indicator, the first weight, the second scoring indicator, and the second weight; and sorting the candidate events in the candidate event set based on the final scoring index.

Optionally, the above processor may further execute program code for: extracting word features and character features from the historical dispute description information; inputting word features and character features into a preset learning model for recognition to obtain entity elements of dispute events and logic relations among the entity elements; and constructing a dispute knowledge graph based on the entity elements and the logic relations.

It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is only illustrative, and the computer terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm-phone computer, a mobile internet device (Mobile Internet Devices, MID), a PAD, etc. Fig. 7 is not limited to the structure of the electronic device. For example, the computer terminal a may also include more or fewer components (such as a network interface, a display device, etc.) than shown in fig. 7, or have a different configuration than shown in fig. 7.

Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program for instructing a terminal device to execute in association with hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.

Example 5

Embodiments of the present application also provide a storage medium. Alternatively, in this embodiment, the storage medium may be used to store program code executed by the dispute event recognition method provided in the first embodiment.

Alternatively, in this embodiment, the storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: obtaining dispute description information of dispute events; determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; and sending the search result to the user equipment.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: extracting at least one entity element and a logic relation between the at least one entity element from dispute description information; determining a node corresponding to at least one entity element in the dispute knowledge graph based on the at least one entity element and the logic relationship between the at least one entity element; searching based on a common neighbor algorithm, and determining neighbor nodes of the nodes; determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and determining a target event from the candidate event set, and taking the target event as a search result of the dispute event.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: carrying out standardization processing on at least one entity element and a logic relationship between at least one entity element to obtain standardized data; and inputting the standardized data into the dispute knowledge graph.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: and matching at least one entity element and the logic relation with the data in the preset standard data set, and taking the matched data as standardized data.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: sorting the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to at least one entity element; and determining the target event based on the highest-ranking preset number of candidate events.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: for each candidate event, determining a first scoring index and a first weight of the event type, and a second scoring index and a second weight corresponding to the node type; determining a final scoring indicator for each candidate event based on the first scoring indicator, the first weight, the second scoring indicator, and the second weight; and sorting the candidate events in the candidate event set based on the final scoring index.

Alternatively, in the present embodiment, the storage medium is configured to store program code for performing the steps of: extracting word features and character features from the historical dispute description information; inputting word features and character features into a preset learning model for recognition to obtain entity elements of dispute events and logic relations among the entity elements; and constructing a dispute knowledge graph based on the entity elements and the logic relations.

Example 6

According to an embodiment of the present application, there is further provided a method for identifying a dispute event, as shown in fig. 8, which includes the following steps

Step S802, obtaining dispute description information of a dispute event.

Alternatively, the dispute event may include, but is not limited to, civil disputes (e.g., property disputes), administrative disputes (e.g., medical and health disputes), legal prosecution disputes, and the like. The number of the dispute events is multiple, the dispute description information comprises description information of the plurality of dispute events, and the description information of the dispute events comprises, but is not limited to, time, place, case related person and content of the dispute events.

Step S804, determining search results of dispute events based on dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information.

Step S806, displaying the search result.

It should be noted that, the search result of the dispute event may include whether the plurality of dispute events are the same event and/or which dispute events are the same event.

In an alternative scheme, after obtaining the search result of the dispute event, the user side device may display the search result, where the display form of the search result may include, but is not limited to, text, graphics, and the like. Optionally, the search result is displayed to the user in the text form at the user terminal device, for example, the dispute event includes an event a and an event B, and the user terminal device is displayed to the user in the form of "event a and event B are the same dispute event". Optionally, when the user terminal device displays the search result in a graphic form, for example, when the number of dispute events is multiple, the same dispute events are represented in the same graphic or color, and different dispute events are represented in different graphics or colors.

Further, after the search results are displayed to the user, the server can also identify the dispute event, distribute the dispute event with the same identification to the terminal of the same responsible person in the same department, process the dispute event by the responsible person, and record the related information of the responsible person, so that the involved person in the dispute case can inquire the department for processing the dispute event, and the processing of the dispute event is more transparent and fair.

Based on the scheme defined in the steps S802 to S806, it can be known that, after the historical dispute description information of the dispute is obtained by adopting the manner of identifying the dispute based on the knowledge graph, the search result of the dispute is determined based on the dispute description information and the pre-constructed dispute knowledge graph, and the search result is displayed, wherein the dispute knowledge graph at least comprises entity elements in the historical dispute description information and logic relations among the entity elements in the historical dispute description information.

In addition, it should be noted that other relevant contents in the present embodiment are the same as those of the embodiment provided in embodiment 1, and are not described herein.

The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.

In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, such as the division of the units, is merely a logical function division, and may be implemented in another manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.

Claims

1. A method for identifying a dispute event, comprising:

obtaining dispute description information of dispute events;

determining a search result of the dispute event based on the dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information;

sending the search result to user equipment;

the determining the search result of the dispute event based on the dispute description information and a pre-constructed dispute knowledge graph comprises the following steps: extracting at least one entity element and a logic relation between the at least one entity element from the dispute description information; determining a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and a logical relationship between the at least one entity element; searching based on a common neighbor algorithm, and determining neighbor nodes of the nodes; determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and determining a target event from the candidate event set, and taking the target event as a search result of the dispute event.

2. The method of claim 1, wherein prior to determining a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and a logical relationship between the at least one entity element, the method further comprises:

performing standardization processing on the at least one entity element and the logic relationship between the at least one entity element to obtain standardized data;

and inputting the standardized data into the dispute knowledge graph.

3. The method of claim 2, wherein normalizing the logical relationship between the at least one physical element and the at least one physical element to obtain normalized data comprises:

and matching the at least one entity element and the logic relation with data in a preset standard data set, and taking the matched data as the standardized data.

4. The method of claim 2, wherein the dispute event is a plurality of, and the dispute description information comprises description information of a plurality of dispute events.

5. The method of claim 1, wherein determining a target event from the set of candidate events comprises:

Sorting the candidate events in the candidate event set according to the event type of each candidate event in the candidate event set and the node type corresponding to the at least one entity element;

and determining the target event based on the highest-ranking preset number of candidate events.

6. The method of claim 5, wherein ranking the candidate events in the candidate event set by an event type for each candidate event in the candidate event set and a node type for the at least one entity element comprises:

for each candidate event, determining a first scoring index and a first weight of the event type, and a second scoring index and a second weight corresponding to the node type;

determining a final scoring indicator for each candidate event based on the first scoring indicator, the first weight, the second scoring indicator, and the second weight;

and sequencing the candidate events in the candidate event set based on the final scoring index.

7. The method according to any one of claims 1 to 6, wherein the dispute knowledge graph is determined by:

extracting word features and character features from the historical dispute description information;

Inputting the word characteristics and the character characteristics into a preset learning model for recognition to obtain the entity elements of the dispute event and the logic relationship between the entity elements;

and constructing the dispute knowledge graph based on the entity elements and the logic relationship.

8. A method for identifying a dispute event, comprising:

obtaining dispute description information of dispute events;

displaying the search results;

9. An apparatus for identifying a dispute event, comprising:

the acquisition module is used for acquiring dispute description information of the dispute event;

the determining module is used for determining search results of the dispute event based on the dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in the historical dispute description information and logic relations among the entity elements in the historical dispute description information;

the sending module is used for sending the search result to the target object;

the determining module is further configured to: extracting at least one entity element and a logic relation between the at least one entity element from the dispute description information; determining a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and a logical relationship between the at least one entity element; searching based on a common neighbor algorithm, and determining neighbor nodes of the nodes; determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and determining a target event from the candidate event set, and taking the target event as a search result of the dispute event.

10. A system for identifying a dispute event, comprising: a communication module and a processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the communication module is used for receiving a query request of a user and sending a search result of the processor to user terminal equipment;

the processor is used for acquiring dispute description information of a dispute event and a pre-constructed dispute knowledge graph under the triggering of the query request, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; determining the search result of the dispute event based on the dispute description information and the pre-constructed dispute knowledge graph;

the processor is further configured to: extracting at least one entity element and a logic relation between the at least one entity element from the dispute description information; determining a node corresponding to the at least one entity element in the dispute knowledge graph based on the at least one entity element and a logical relationship between the at least one entity element; searching based on a common neighbor algorithm, and determining neighbor nodes of the nodes; determining a candidate event set based on the node corresponding to the at least one entity element and the neighbor node; and determining a target event from the candidate event set, and taking the target event as a search result of the dispute event.

11. A storage medium comprising a stored program, wherein the program, when run, controls a device on which the storage medium resides to perform the steps of:

obtaining dispute description information of dispute events and a pre-constructed dispute knowledge graph; determining a search result of the dispute event based on the dispute description information and a pre-constructed dispute knowledge graph, wherein the dispute knowledge graph at least comprises entity elements in historical dispute description information and logic relations among the entity elements in the historical dispute description information; sending the search result to user equipment;