CN111858725A

CN111858725A - Event attribute determination method and system

Info

Publication number: CN111858725A
Application number: CN202010365398.4A
Authority: CN
Inventors: 刘纯一; 王鹏; 李奘
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-04-30
Filing date: 2020-04-30
Publication date: 2020-10-30

Abstract

The embodiment of the application discloses a method, a system, a device and a storage medium for determining event attributes. The method comprises the following steps: acquiring work order information generated according to event description of a target event, wherein the work order information at least comprises structural information and narrative information; obtaining a first characteristic according to the narrative information; obtaining a second characteristic according to the structural information; fusing the first feature and the second feature to obtain a fused feature; and obtaining the event attribute of the target event based on the fusion characteristic. The method and the device can improve the accuracy of determining the event attribute.

Description

Event attribute determination method and system

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and a system for determining an event attribute.

Background

With the development of the shared transport services industry, people are becoming more accustomed to handling security issues with customer service, but the ability of customer service to handle security events is limited. In addition, subjective factors have a great influence on the judgment result of the customer service, which may cause misjudgment of the security incident. Therefore, it is necessary to provide an event attribute determination method and system.

Disclosure of Invention

A first aspect of the present application provides an event attribute determination method. The event attribute detection and determination method comprises the following steps: acquiring work order information generated according to event description of a target event, wherein the work order information at least comprises structural information and narrative information; obtaining a first characteristic according to the narrative information; obtaining a second characteristic according to the structural information; fusing the first feature and the second feature to obtain a fused feature; and obtaining the event attribute of the target event based on the fusion characteristic.

A second aspect of the present application provides an event attribute determination system, comprising: the work order obtaining module is used for obtaining work order information generated according to the event description of the target event, and the work order information at least comprises structural information and narrative information; the first feature extraction module is used for obtaining a first feature according to the narrative information; the second feature extraction module is used for obtaining a second feature according to the structural information; the feature fusion module is used for fusing the first feature and the second feature to obtain a fusion feature; and the determining module is used for obtaining the event attribute of the target event based on the fusion characteristic.

In some embodiments, the work order information is generated by the customer service based on the event description and/or the results of processing the event.

In some embodiments, the structured information in the work order information includes at least one of: an order number, license plate number, phone number, whether to alarm, whether to set up a case for the police, whether to request processing by the user, and the urgency of the processing required; the narrative information in the work order information at least comprises at least one of the following information: the description of the user to the event, the description of the police processing result and the description of the customer service processing result.

In some embodiments, the first feature extraction module processes the narrative information using a text conversion model to obtain the first feature.

In some embodiments, the text conversion model includes at least one of the following deep learning models: fastext, HAN, Text CNN, Transformer, LR, and XG Boost.

In some embodiments, further comprising a training module to: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, and training the text conversion model by taking narrative information in the work order information as input and taking event attributes corresponding to the work order information given by customer service as identifiers.

In some embodiments, the second feature extraction module processes the structured information by extracting a model to generate the second feature.

In some embodiments, the extraction model employs rule and/or AC automata based methods for feature extraction.

In some embodiments, the feature fusion module directly splices the first feature and the second feature or processes the first feature and the second feature through a set algorithm to generate a combined feature, so as to obtain a fused feature.

In some embodiments, the determining module processes the fusion features using a classification model to obtain a classification result of the event attribute; the classification result of the event attribute comprises at least one of the following: whether the event is safe, whether the event is accurate, whether the event can be traced, and whether the event can be repeated.

In some embodiments, the classification model comprises at least one of the following deep learning models: XG Boost, GBDT, Adaboost, random forest.

In some embodiments, further comprising a training module to: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, the fusion characteristics corresponding to the work order information are used as input, the event attribute corresponding to the work order information given by customer service is used as an identifier, and the classification model is trained.

A third aspect of the present application provides an event attribute determination apparatus comprising at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the operations described above.

A fourth aspect of the present application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, perform the operations as described above.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Wherein:

FIG. 1 is a schematic diagram of an application scenario of an event attribute determination system according to some embodiments of the present application;

FIG. 2 is a schematic block diagram of an event attribute determination system shown in accordance with some embodiments of the present application;

FIG. 3 is an exemplary flow diagram of an event attribute determination method according to some embodiments of the present application; and

FIG. 4 is an example of common structured and narrative information in some embodiments according to the present application.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Although various references are made herein to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a vehicle client and/or server. The modules are merely illustrative and different aspects of the systems and methods may use different modules.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Further, while the systems and methods disclosed herein are primarily described with respect to transportation services, it should be understood that this is merely one exemplary embodiment. The system and method of the present invention may be applied to any other on-demand service, such as a housekeeping service, a take-away service, etc. In some embodiments, the systems and methods of the present application may be applied to different transportation systems, including terrestrial, marine, aerospace, and the like, or any combination of the above. The vehicles used in the transportation system may include taxis, private cars, windmills, buses, trains, railcars, highways, subways, ships, airplanes, space vehicles, hot air balloons, unmanned vehicles, and the like, or combinations thereof. The transport system may also include any suitable transport system for managing and/or distributing, for example, systems for transmitting and/or receiving courier items. The application scenarios of the system or method of the present application may further include a web page, a browser plug-in, a client terminal, a customization system, an internal analysis system, an artificial intelligence robot, etc., or any combination thereof.

It will be appreciated that in some practical scenarios, customer service is required to handle a large number of events occurring during the on-demand service every day and to give the processing results quickly. For example only, in a shared transportation service, users rely on customer service to handle security events, but the actual ability of customer service to handle security events is limited, e.g., a customer service may rate an event with a security risk as a normal event. In some embodiments, the related information of the security event subjected to customer service processing can be processed through a computer algorithm, whether the security event subjected to customer service processing has missed potential safety hazards or not is found, and the security event subjected to customer service processing is intervened to prevent a malignant bus taking accident from occurring. In some embodiments, the customer service processes the security event based on the event description provided by the user to obtain work order information, the related event description and the processing result of the customer service can be contained in the work order information corresponding to the event, the work order information is processed through a computer algorithm, and potential safety hazard detection can be performed again, so that the working pressure of the customer service is effectively reduced.

Fig. 1 is a schematic diagram of an application scenario of an event attribute determination system according to some embodiments of the present application.

As shown in fig. 1, an exemplary event attribute determination system 100 may include a server 110, a network 120, a user terminal 130, and a storage module 140.

In some embodiments, the server 110 may be used for event attribute determination. The server 110 may be a single server or a group of servers. A group of servers may be centralized, such as a data center. A server farm may also be distributed, such as a distributed system. The server 110 may be local or remote. In some embodiments, the server 110 may include a control processor 112 for executing instructions (program code) of the server 110. For example, the control processor 112 can execute the instructions of the event detection program, and then analyze the work order information by a certain algorithm to determine the detection result.

In some embodiments, the terminal 130 comprises a service requester terminal and/or a customer service terminal. For example only, the service requester may be an individual initiating a vehicle request. In some embodiments, the service requester may send an event description of a target event occurring during the transportation service to the service end or the customer service terminal through its terminal. In some embodiments, the customer service terminal may receive an event description of a target event sent by the service requester terminal, process the target event, and generate work order information and/or a processing result. In some embodiments, the work order information may include structured information generated based on the event description, narrative information, and/or event attributes of the customer's preliminary judgment. In some embodiments, the customer service terminal may return the processing results to the service requester terminal or send the work order information to the server 110 for further processing. The terminal 130 includes, but is not limited to, one or a combination of several of a mobile phone 130-1, a tablet computer 130-2, a notebook computer 130-3, and the like. The server 110 may access the work order information stored in the storage module 140 or may transmit the detection result to the user terminal 130 via the network 120.

In some embodiments, the storage module 140 may refer to a device having a storage function. The storage module 140 is mainly used to store the event description transmitted from the user terminal 130 and various data generated in the operation of the server 110. The storage module 140 may be local or remote. The connection or communication between the system database and other modules of the system may be wired or wireless. The network 120 may provide a conduit for the exchange of information. The network 120 may be a single network or a combination of networks. Network 120 may include, but is not limited to, one or a combination of local area networks, wide area networks, public networks, private networks, wireless local area networks, virtual networks, metropolitan area networks, public switched telephone networks, and the like. Network 120 may include a variety of network access points, such as wired or wireless access points, base stations (e.g., 120-1, 120-2), or network switching points, through which data sources connect to network 120 and transmit information through network 120.

It will be understood by those of ordinary skill in the art that when an element of the event attribute determination system 100 executes, the element may execute via electrical and/or electromagnetic signals. For example, when the user terminal 130 processes a task, such as when a user makes an event description, the user terminal 130 may operate logic circuits in its processor to process such task. When user terminal 130 issues an instruction to server 110, a processor of user terminal 130 may generate an electrical signal encoding the instruction. The processor of the user terminal 130 may then send the electrical signal to the output port. If user terminal 130 communicates with server 110 via a wired network, the output port may be physically connected to a cable, which further transmits the electrical signals to the input port of server 110. If user terminal 130 communicates with server 110 via a wireless network, the output port of user terminal 130 may be one or more antennas that convert electrical signals to electromagnetic signals. Similarly, the storage module 140 may process tasks by operation of logic circuits in its processor and receive instructions and/or information from the server 110 via electrical or electromagnetic signals. Within an electronic device, such as user terminal 130, storage module 140, and/or server 110, instructions and/or actions are performed by electrical signals when the processor processes the instructions, issues the instructions, and/or performs the actions. For example, when server 110 retrieves data from storage module 140, it may send an electrical signal to a reading device of the storage medium, which may read the structured or narrative information in the storage medium. The structured or narrative information can be transmitted to the processor in the form of electrical signals over a bus of an electronic device. Herein, an electrical signal may refer to one electrical signal, a series of electrical signals, and/or at least two discrete electrical signals.

FIG. 2 is a schematic block diagram of an event attribute determination system shown in accordance with some embodiments of the present application.

As shown in fig. 2, in some embodiments, the event attribute determination system 200 may include: a work order obtaining module 210, configured to obtain work order information generated according to an event description of a target event, where the work order information at least includes structural information and narrative information; a first feature extraction module 220, configured to obtain a first feature according to the narrative information; a second feature extraction module 230, configured to obtain a second feature according to the structural information; a feature fusion module 240, configured to fuse the first feature and the second feature to obtain a fused feature; and a determining module 250, configured to obtain an event attribute of the target event based on the fusion feature.

In some embodiments, the work order acquisition module 210 may be configured to perform step 301. In some embodiments, the work order information is generated by the customer service based on the event description and the results of the processing of the event.

In some embodiments, the structured information in the work order information may include at least one of: an order number, license plate number, phone number, whether to alarm, whether to set up a case for the police, whether to request processing by the user, and the urgency of the processing required; the narrative information in the work order information at least comprises at least one of the following information: the description of the user to the event, the description of the police processing result and the description of the customer service processing result. See step 301 for more pertinent information.

In some embodiments, the first feature extraction module 220 may be used to perform step 303. In some embodiments, the first feature extraction module may process the narrative information using a text conversion model to obtain the first feature. In some embodiments, the text conversion model may include at least one of the following deep learning models: fast Text, HAN, Text CNN, Transformer, LR, and XG Boost. In some embodiments, the method of training the text conversion model may include: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, and training the text conversion model by taking narrative information in the work order information as input and taking an event attribute corresponding to the work order information given by customer service as an identifier. See step 303 for more pertinent information.

In some embodiments, the second feature extraction module 230 may be used to perform step 305. In some embodiments, the second feature extraction module may process the structured information to generate the second feature by extracting a model. In some embodiments, the extraction model may employ rule and/or AC automata based methods for feature extraction. See step 305 for more pertinent information.

In some embodiments, the feature fusion module 240 may be used to perform step 307. In some embodiments, the feature fusion module may directly concatenate the first feature and the second feature or process the first feature and the second feature through a set algorithm to generate a combined feature, so as to obtain a fused feature. See step 307 for more pertinent information.

In some embodiments, the determination module 250 may be used to perform step 309. In some embodiments, the determination module may process the fused features using a classification model to obtain a classification result of the event attribute. In some embodiments, the classification result of the event attribute obtained by the determination module may include at least one of: whether the event is safe, whether the event is accurate, whether the event can be traced, and whether the event can be repeated. In some embodiments, the classification model may include at least one of the following deep learning models: XG Boost, GBDT, Adaboost, random forest. In some embodiments, the method of training the classification model may comprise: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, the fusion characteristics corresponding to the work order information are used as input, the event attribute corresponding to the work order information given by customer service is used as an identifier, and the classification model is trained. See step 309 for more pertinent information.

It should be understood that the system and its modules shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the system and its modules is merely for convenience of description and should not limit the present application to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. For example, in some embodiments, the work order obtaining module 210, the first feature extraction module 220, and the like disclosed in fig. 2 may be different modules in a system, or may be a module that implements the functions of two or more modules described above. For another example, each module may share one memory module 140, and each module may have its own memory module 140. Such variations are within the scope of the present application.

FIG. 3 is an exemplary flowchart illustrating implementation steps of an event attribute determination method according to some embodiments of the present application.

In further embodiments of the present application, a method of event attribute determination is provided, and the method 300 may include the steps of:

step 301, obtaining work order information generated according to an event description of a target event, where the work order information may include at least structured information and narrative information. In some embodiments, this step may be performed by the work order acquisition module 210 in the system 200.

In some embodiments, the event description may include a user-provided description of the event. In some embodiments, the manner in which the user provides the event description includes, but is not limited to, video, voice, text, and the like. And obtaining work order information by customer service processing the event description. In some embodiments, the processing of the event description by the customer service may be manual or semi-automated, and semi-automated may refer to the use of various software and hardware to assist the customer service in processing information.

In some embodiments, the work order information may include structured information and narrative information. Structured information may refer to information that is parsed into a plurality of interrelated components, each of which has a distinct hierarchical structure. The use and maintenance of the structured information can be managed through a database and have certain operation specifications. For example, structured information may be represented and stored using a relational database, represented as data in two dimensions. Data is in row units, one row of data represents information of one entity, and the attribute of each row of data is the same. The data is regularly stored and arranged, so that subsequent operations such as query and modification are facilitated. Structured information may be applied to, for example, enterprise ERP, financial systems, medical HIS databases, all-purpose educational cards, government administration approval, and other core databases. The storage scheme for the structured information may include high-speed storage application requirements, data backup requirements, data sharing requirements, and data disaster tolerance requirements.

In some embodiments, the structured information may include an order number, a license plate number, a phone number and whether to dial 110, whether the police officer has settled, etc. related to the event, which may be expressed as "yes or no", and may also refer to information having a hierarchical level, such as whether the user requests processing and how urgent the processing is required. In some embodiments, the structured information may not conform to the form of a relational database or other data table, but contain relevant tags to separate semantic elements and to stratify records and fields. Thus, structured information is also referred to as a self-describing structure. Structured information belongs to the same class of entities but may have different attributes, even if they are grouped together, the order of which is not important. Common structured information includes XML and JSON, among others. The structured information may be applied to mail systems, WEB clusters, teaching resource libraries, data mining systems, archive systems, and the like. The storage scheme of the structured information can comprise basic storage requirements such as data storage, data backup, data sharing and data archiving.

In some embodiments, narrative information may refer to unstructured data that is irregular or incomplete in data structure, does not have a predefined data model, and is not conveniently represented in a database two-dimensional logical table. Narrative information can include office documents, text, pictures, various types of reports, images, and audio/video information in all formats, and the like. Narrative information is in a wide variety of formats, standards, and technically unstructured information is more difficult to standardize and understand than structured information. Therefore, more intelligent information technologies such as mass storage, intelligent retrieval, knowledge mining, content protection, value-added development and utilization of information, and the like are needed for storage, retrieval, distribution and utilization. The storage scheme of the narrative information can include data storage, data backup, data sharing and the like.

In some embodiments, narrative information may refer to customer service records of user descriptions of events, police processing results descriptions, customer service processing results descriptions, and the like. For example, the user question is described as "car scratch", the customer service process is "arrange specialist and feedback traffic police", and the result is "user approval". Narrative information can be obtained by recording, saving video, saving call records, and the like.

In some embodiments, the work order information may be generated by the customer service based on the event description and the results of the processing of the event. In some embodiments, work order information may refer to information that a user reflects an event to a customer service and that the event results from a preliminary processing of the customer service. The work order information is converted into structured information and/or narrative information in a customer service manual or semi-automatic mode. For example, the user's process of communicating with the customer service is recorded, and based on the recording, structured and/or narrative information is converted.

In some embodiments, the structured information in the work order information includes at least one of: order numbers, license plate numbers, telephone numbers, whether to alarm, whether to set up a case by police, whether to request processing by a user, the degree of urgency of the processing required, and the like, which are related to the event; the narrative information in the work order information at least comprises at least one of the following information: the description of the user on the event, the description of the police processing result, the description of the customer service processing result and the like.

As shown in FIG. 4, the customer service presents the work order information as structured and/or narrative information based on the event description. The resulting narrative includes: 1. the user question is described as: the user feeds back to receive the passenger by himself, the passenger touches the car door on the bicycle when getting on the car and driving the car to cause the car door to be scraped, and the passenger is asked for 100 yuan of cost to worry about the complaint of the passenger. 2. Customer service processing: the apology gives you bad experience, the problem of feedback is very important, the control on passengers is strengthened, the problem is fed back to relevant departments immediately, relevant customer service personnel can contact with you for processing within 2 hours, and you keep the call smooth. 3. As a result: and (4) approval by the user. The resulting structured information may include information whether the user is advised to dial 110 as "none", the police treatment outcome is "unknown", the user complaint is "required to treat", whether the vehicle is maliciously damaged as "unknown", and so on.

Step 303, obtaining a first feature according to the narrative information. In some embodiments, this step may be performed by the first feature extraction module 220 in the system 200.

In some embodiments, deriving the first characteristic from the narrative information comprises: and processing the narrative information by using a text conversion model to obtain the first characteristic. The text conversion model comprises at least one of the following deep learning models: fast Text, HAN, Text CNN, Transformer, LR, XG Boost, and the like.

Fast text is a Fast text classifier. Text classification refers to the classification of documents into one or more categories, which may be rating scores, criticality, urgency, nuisance information, etc. To build a classifier, tag data needs to be acquired. Tag data refers to data and the category (i.e., identification or tag) to which the data corresponds. For example, after customer service processing, the customer service manually gives each work order a label of whether there is a danger. Wherein the data with the category label is historical data for a longer time. A sequence of words (a piece of text or a sentence) is input to the Fast text model, which outputs the probability that the sequence of words belongs to different categories. The words and phrases in the sequence constitute a feature vector, the feature vector is mapped to the hidden layer through linear transformation, and the hidden layer is mapped to the label. Fast text classifies narrative information in this way.

Han (hierarchy Attention network) is a hierarchical Attention-based (Attention) mechanism representation for modeling the importance of words, sentences in sentences and documents, respectively. The model corresponds to the hierarchy of the document: the words constitute sentences, which constitute documents, so the model also constructs text vector expressions in two parts. Secondly, different words and sentences have different information contents and cannot be simply treated uniformly, so that an Attention mechanism is introduced. The introduction of the Attention mechanism can improve the accuracy of the model, and can also analyze and visualize the importance of words and sentences, thereby enhancing the interpretability. The HAN may include a word sequence encoder, an entry layer at the word level, a sentence sequence encoder, an entry layer at the sentence level, and the like.

The Transformer can process all words or symbols in the sequence in parallel while using the self-attention (self-attention) mechanism to combine context with more distant words. The self-attention mechanism refers to an attention mechanism that associates different positions of a single sequence. By processing all words in parallel and letting each word notice other words in the sentence in a number of processing steps.

LR (logistic regression) or XG Boost (extreme gradient boosting) may assign a specific weight value to each word or phrase of the text of the training sample according to the corresponding classification. For example, in training an XG Boost with training samples, the XG Boost may give a weight value for a word or phrase in the sample to indicate how important each word or phrase is to model training.

In some embodiments, the method of training the text conversion model comprises: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, and training the text conversion model by taking narrative information in the work order information as input and taking an event attribute corresponding to the work order information given by customer service as an identifier. Wherein the event attribute given by the customer service may include at least one of: whether the event is safe, whether the event is accurate, whether the event is traceable, whether the event is repeatable, whether the event is urgent, whether the event can be early-warned, and the like. In Fast text, a sample set is labeled narrative information. The sample set may be narrative information that is very large in classification category and the data set is large enough to avoid overfitting. The narrative information is input into a model, which can output probabilities that the narrative information belongs to different categories. The model may also output the most probable tag class for the narrative. In HAN, a sample set is labeled narrative information. The processor may input the word vector sequence into the model by preprocessing the tagged narrative information to convert it into a word vector sequence. Preprocessing refers to the preliminary processing of tagged narrative information. In some embodiments, preprocessing may include unifying lowercase, removing garbled codes, removing abbreviations and numbers, removing stop words, and the like. Stop words refer to words that occur frequently and do not contribute much to the classification, and stop words that occur in the text can be removed according to the stop word list. In the training process, the model trains the weight of words in sentences, trains the weight of sentences in documents, and outputs vector representation of texts. In some embodiments, the entire text may also be classified using a softmax classifier. The softmax classifier may output probabilities to which the corresponding information respectively belongs. The model may output the most probable label category for the narrative. In the Transformer, the sample set is labeled narrative information. Entering narrative information into the model. And outputting the probability of the narrative information corresponding to different categories. And outputting the label type with the maximum probability corresponding to the narrative information. In Logistic Regression (LR) or XG Boost, the set of samples is labeled narrative information. And inputting narrative information into the model, endowing each word or phrase of the training sample in the sample set with a specific weight value, and outputting the label category with the maximum weight corresponding to the narrative information.

Step 305, obtaining a second feature according to the structured information. In some embodiments, this step may be performed by the second feature extraction module 230 in the system 200.

In some embodiments, deriving the second feature from the structured information comprises: the second feature is generated by extracting model processing structured information. For example, "whether the user is advised to dial 110". If no, the extraction mode is as follows: "none" → feature _110_0 → a feature _110_0 corresponding dimension of 1; if yes, the extraction mode is as follows: "has" → feature _110_1 → the feature _110_1 corresponds to a dimension of 1. In some embodiments, the extraction model may employ rule and/or AC automata based methods for feature extraction. AC automata is a string search algorithm for matching substrings in a finite set of "dictionaries" in an input string of characters. The dictionary refers to a set of some elements, some elements may include words and sentences in the work order information, for example, "user processing", the user processing corresponds to feature _120, and if "processing is required", the extraction mode is: "has" → feature _120_1 → has a dimension of 1 in feature _120_ 1; if "do not require processing", the extraction manner is no "→ feature _120_0 → the corresponding dimension in feature _120_0 is 1. The AC automaton can match all strings simultaneously.

And 307, fusing the first feature and the second feature to obtain a fused feature. In some embodiments, this step may be performed by feature fusion module 240 in system 200.

In some embodiments, the method of fusing the first feature and the second feature to obtain a fused feature comprises: and processing the first feature and the second feature directly or through a set algorithm to generate a combined feature. In some embodiments, methods of generating combined features include, but are not limited to: feature combination, feature dimension reduction, feature intersection and the like. The feature combination means that a new feature is obtained through some linear superposition or nonlinear superposition of features. A common feature combination method may be a cartesian product method. For example, a is {0,1}, B is {0,1}, and a × B is { (0,0), (0,1), (1,0), (1,1) }. The feature combination mode can also adopt a decision tree + LR mode. In some embodiments, a gradient lifting tree + logistic regression (GBDT + LR) approach may be employed. Gradient lifting tree + logistic regression (GBDT + LR) is an automatic way of feature extraction. The GBDT is a gradient lifting decision tree, a decision tree is constructed firstly, a decision tree is constructed again on the residual error between the existing model and the actual sample output, iteration is carried out continuously, each iteration generates a classification feature with a large gain, therefore, the obtained feature space is large according to the number of leaf nodes of the decision tree constructed by the GBDT, and the feature is used as the input of an LR model. Decision trees are represented in the form of a tree of nodes, each node making a binary decision based on the characteristics of the data, and each leaf node of the tree containing a prediction.

The feature combination method can also be realized based on the principle of Principal Component Analysis (PCA), feature dimension reduction of Singular Value Decomposition (SVD), feature intersection based on a factor decomposition Machine (FM), and the like. PCA refers to the process of synthesizing multiple indexes into a few independent synthetic indexes (i.e., principal components), wherein each principal component can reflect most of the information of the original variable and contains no duplication of information. The Principal Component Analysis (PCA) principle is to project the sample data in a matrix into a new space. For a matrix, it is diagonalized, i.e., the process of generating the eigenroots and eigenvectors, and the process of projecting it on an orthonormal basis. The characteristic direction reflects the distribution state of the information, and the characteristic value defines the length of the direction. For example, the larger the feature value, the longer the length of the feature direction, and the more information of the original data in the direction. Singular Value Decomposition (SVD) is an important matrix decomposition method. SVD may be applied to data types that are numerical, and the original data set may be represented by a smaller data set. A Factorizer (FM) can solve the problem of feature combinations in the case of sparse data.

Step 309, based on the fusion characteristics, obtaining the event attribute of the target event. In some embodiments, this step may be performed by the determination module 250 in the system 200.

In some embodiments, the obtaining a classification result of the event attribute based on the fused feature includes: and processing the fusion characteristics by using a classification model to obtain a classification result of the event attributes. In some embodiments, the classification result of the event attribute comprises at least one of: whether the event is safe, whether the event is accurate, whether the event can be traced, and whether the event can be repeated. In some embodiments, the event attribute classification may not be limited to the above four categories, and may further include whether the event is urgent, whether the event can be early-warned, and the like. In some embodiments, the output result of the classification result may be a two-classification result, i.e., only two results, i.e., safe or unsafe, are output, or a multi-classification result, i.e., a probability that the output event is a safety event. For example, the result of the binary classification is specifically represented as a safe output 1 and an unsafe output 0. For another example, the multi-classification result is specifically represented by a probability output of a security event of 0.8, a probability of an unsafe event of 0.1, and a probability of an nuisance event of 0.1. The classification model includes at least one of the following deep learning models: XG Boost, GBDT, Adaboost, random forest.

Adaboost is a lifting tree, different weak classifiers are trained aiming at the same training set, and a strong classifier is constructed through Adaboost. The lifting of the tree refers to lifting of the weak learning algorithm into the strong learning algorithm. A classifier is a function or model that maps data records in a database to one of a given class and thus can be applied to data prediction. The classifier is a general term of a method for classifying samples in data mining, and at least comprises algorithms such as decision trees, logistic regression, naive Bayes, neural networks and the like. There are two weights in the Adaboost algorithm, one is the weight of the data, and the other is the weight of the weak classifier. The weight of the data is mainly used for the weak classifier to search the decision point with the minimum classification error, the weight of the weak classifier is calculated by using the minimum classification error after the decision point is found, and the larger the weight of the classifier is, the larger the weight of the weak classifier is in the final decision.

Random Forest (RF) refers to a classifier that trains and predicts samples using a plurality of trees. The class of its output is determined by the mode of the class of the individual tree output.

In some embodiments, the method of training the classification model comprises: and acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information, the fusion characteristics corresponding to the work order information are used as input, the event attribute corresponding to the work order information given by customer service is used as an identifier, and the classification model is trained.

In the training process of the Adaboost model, firstly, the weak classifier is trained, and the trained weak classifier participates in the next iteration. In the Nth iteration, N weak classifiers exist in total, wherein N-1 weak classifiers are trained in the front, various parameters of the weak classifiers are not changed any more, and the Nth classifier is trained at this time. The weak classifiers are related in such a way that the Nth weak classifier is more likely to classify the data which is not classified by the first N-1 weak classifiers, and the final classification output depends on the comprehensive effect of the N classifiers. Adaboost generally uses a single-level decision tree as its weak classifier. It should be noted that even if the sample set has multidimensional features, the single-level decision tree can only select one dimension to make a decision. In the neural network, classified data is converted into a vector form and input into the neural network for classification.

It should be noted that the above description of the flow is for illustration and description only and does not limit the application scope of the present application. Various modifications and alterations to the flow may occur to those skilled in the art, given the benefit of this disclosure. However, such modifications and variations are intended to be within the scope of the present application. For example, decision tree + logistic regression may take forms other than LBDT + LR (e.g., RF + LR, XG Boost + LR, etc.).

In still other embodiments of the present application, there is provided an event attribute determination apparatus comprising at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the operations described above.

In still other embodiments of the present application, a computer-readable storage medium for event attribute determination is provided that stores computer instructions that, when executed by a processor, implement the operations described above.

It should be noted that the above description is merely for convenience and should not be taken as limiting the scope of the present application. It will be understood by those skilled in the art that various changes and modifications in form and detail may be made in the implementation of the above-described processes without departing from the principles of the present application. However, such changes and modifications do not depart from the scope of the present application.

The beneficial effects that may be brought by the embodiments of the present application include, but are not limited to: (1) the work order information comprises narrative information and structural information, the narrative information can reflect the processing result of the customer service on the event to a certain extent, and the event attribute is obtained by combining the processing results of the two kinds of information, so that the accuracy of determining the event attribute is improved; (2) the narrative information and the structural information are respectively processed and input into the model, and the two kinds of information do not need to be subjected to related conversion, so that the processing efficiency is improved.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

The foregoing describes the present application and/or some other examples. The present application can be modified in various ways in light of the above. The subject matter disclosed herein can be implemented in various forms and examples, and the present application can be applied to a wide variety of applications. All applications, modifications and variations that are claimed in the following claims are within the scope of this application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment," or "one embodiment," or "an alternative embodiment," or "another embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, the different system components described above are implemented by hardware devices, but may also be implemented by software solutions only. For example: the system is installed on an existing server. Further, the location information disclosed herein may be provided via a firmware, firmware/software combination, firmware/hardware combination, or hardware/firmware/software combination.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication enables loading of software from one computer device or processor to another. For example: from a management server or host computer of the radiation therapy system to a hardware platform of a computer environment, or other computer environment implementing the system, or similar functionality associated with providing information needed to determine wheelchair target structural parameters. Thus, another medium capable of transferring software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic waves, etc., propagating through cables, optical cables, or the air. The physical medium used for the carrier wave, such as an electric, wireless or optical cable or the like, may also be considered as the medium carrying the software. As used herein, unless limited to a tangible "storage" medium, other terms referring to a computer or machine "readable medium" refer to media that participate in the execution of any instructions by a processor.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service using, for example, software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numbers describing attributes, quantities, etc. are used in some embodiments, it being understood that such numbers used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, articles, and the like, cited in this application is hereby incorporated by reference in its entirety. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, embodiments of the present application are not limited to those explicitly described and depicted herein.

Claims

1. A method for event attribute determination, the method being implemented by at least one processor, the method comprising:

Acquiring work order information generated according to event description of a target event, wherein the work order information at least comprises structural information and narrative information;

obtaining a first characteristic according to the narrative information;

obtaining a second characteristic according to the structural information;

fusing the first feature and the second feature to obtain a fused feature;

and obtaining the event attribute of the target event based on the fusion characteristic.

2. The method of claim 1, wherein the work order information is generated by a customer service based on the event description and/or results of processing an event.

3. The method of claim 2, wherein the structured information in the work order information comprises at least one of: an order number, license plate number, phone number, whether to alarm, whether to set up a case for the police, whether to request processing by the user, and the urgency of the processing required; the narrative information in the work order information at least comprises at least one of the following information: the description of the user to the event, the description of the police processing result and the description of the customer service processing result.

4. The method of claim 2, wherein said deriving a first feature from said narrative information comprises: processing the narrative information by using a text conversion model to obtain the first characteristic; the first feature reflects a first determination result of an event attribute of the target event.

5. The method of claim 4, wherein the text conversion model comprises at least one of the following deep learning models: fast Text, HAN, Text CNN, Transformer, LR, and XG Boost.

6. The method of claim 4 or 5, wherein the method of training the text conversion model comprises:

acquiring a sample set, wherein the sample set comprises a plurality of pieces of work order information;

and training the text conversion model by taking the narrative information in the work order information as input and taking the event attribute corresponding to the work order information given by the customer service as an identifier.

7. The method of claim 1, wherein the deriving the second feature from the structured information comprises: the second feature is generated by extracting model processing structured information.

8. The method of claim 7, wherein the extraction model performs feature extraction using a rule and/or AC automata based approach.

9. The method of claim 1, wherein fusing the first and second features to obtain a fused feature comprises: and processing the first feature and the second feature directly or through a set algorithm to generate a combined feature.

10. The method of claim 1, wherein the deriving the event attribute of the target event based on the fused feature comprises: processing the fusion characteristics by using a classification model to obtain a classification result of the event attributes; the classification result of the event attribute comprises at least one of the following: whether the event is safe, whether the event is accurate, whether the event can be traced, and whether the event can be repeated.

11. The method of claim 10, wherein the classification model comprises at least one of the following deep learning models: XG Boost, GBDT, Adaboost, random forest.

12. The method of claim 10 or 11, wherein the method of training the classification model comprises:

and taking the fusion characteristics corresponding to the work order information as input, taking the event attribute corresponding to the work order information given by the customer service as an identifier, and training the classification model.

13. An event attribute determination system, comprising:

the work order obtaining module is used for obtaining work order information generated according to the event description of the target event, and the work order information at least comprises structural information and narrative information;

The first feature extraction module is used for obtaining a first feature according to the narrative information;

the second feature extraction module is used for obtaining a second feature according to the structural information;

the feature fusion module is used for fusing the first feature and the second feature to obtain a fusion feature; and

and the determining module is used for obtaining the event attribute of the target event based on the fusion characteristic.

14. An event attribute determination apparatus, comprising at least one processor and at least one memory;

the at least one memory is for storing computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the operations of any of claims 1 to 12.

15. A computer-readable storage medium for event attribute determination, the storage medium storing computer instructions which, when executed by a processor, perform operations according to any one of claims 1 to 12.