Event information processing method and device, electronic equipment and nonvolatile storage medium

Abstract

The invention discloses an event information processing method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring event information to be processed; determining an event field corresponding to the to-be-processed event information, and obtaining historical event information corresponding to the event field in a historical database; determining a first similarity between the to-be-processed event information and the historical event information, and determining target event information corresponding to the to-be-processed event information in the historical event information according to the first similarity; and obtaining historical processing flow information corresponding to the target event information, determining a processing flow corresponding to the to-be-processed event information according to the historical processing flow information, and submitting the to-be-processed event information to a corresponding node flow according to the processing flow. According to the event information processing method and device, the technical problem that the event information processing efficiency is low due to the fact that the event information is transferred to the corresponding department to be processed in a manual judgment mode when the event information is processed in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular, to an event information processing method, device, electronic device and non-volatile storage medium. Background Art

[0002] As society develops, how to maximize the efficiency of social governance, so that various social problems can be discovered early beforehand, quickly and effectively handled and supervised during the process, and timely feedback after the event, has become an increasingly important issue. However, in related technologies, when processing event information, it is often necessary to manually determine the event information and transfer it to the corresponding department for processing, which leads to the technical problem of low efficiency in event information processing.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide an event information processing method, device, electronic device and non-volatile storage medium to at least solve the technical problem of low efficiency in event information processing due to the fact that the related technology uses manual judgment to transfer event information to the corresponding department for processing when processing event information.

[0005] According to one aspect of an embodiment of the present application, a method for processing event information is provided, including: obtaining event information to be processed, wherein the event information to be processed is information reported by staff to describe event tasks that need to be processed; determining an event field corresponding to the event information to be processed, and obtaining historical event information corresponding to the event field in a historical database, wherein the historical event information is event information received in a historical process; using natural language processing technology to determine a first similarity between the event information to be processed and the historical event information, and based on the first similarity, determining target event information corresponding to the event information to be processed in the historical event information; obtaining historical processing flow information corresponding to the target event information, and based on the historical processing flow information, determining the processing flow corresponding to the event information to be processed, and submitting the event information to be processed to the corresponding node flow according to the processing flow.

[0006] Optionally, the event information to be processed includes: event description information, address of occurrence, time of occurrence, degree of urgency, and scope of impact; determining the event domain corresponding to the event information to be processed includes: performing word segmentation on the event information to be processed, and determining the part of speech corresponding to each word obtained after word segmentation; performing syntactic analysis on the event information to be processed based on the part of speech corresponding to each word, and obtaining semantic structure information corresponding to the event information to be processed, wherein the semantic structure information is used to characterize the contextual association relationship between each word in the event information to be processed; determining keywords of the event information to be processed based on the semantic structure information, and calculating the second similarity between the keywords and the domain keywords corresponding to each event domain; determining the event domain corresponding to the event information to be processed based on the second similarity.

[0007] Optionally, based on the first similarity, determining the target event information corresponding to the event information to be processed in the historical event information includes: determining the word frequency of the keywords in the event information to be processed in the historical event information, and the inverse document frequency corresponding to the keywords, wherein the word frequency is used to characterize the number of times the keywords appear in the historical event information, and the inverse document frequency is used to characterize the number of historical event information containing the keywords; determining the first similarity between the event information to be processed and the historical event information based on the word frequency and the inverse document frequency; determining the historical event information whose first similarity exceeds a preset similarity threshold as candidate event information; using a natural language processing model to analyze the event information to be processed to obtain analysis results, and determining the target event information from the candidate event information based on the analysis results.

[0008] Optionally, based on the analysis results, determining the target event information in the candidate event information includes: using a natural language processing model to extract features of the event information to be processed to obtain text features; determining the analysis results based on the text features, wherein the analysis results include: the task intention type and emotional state corresponding to the event information to be processed, the emotional state being used to characterize the emotional tendency of the staff when reporting the event information to be processed; and determining the candidate event information whose task intention type and emotional state are consistent with those of the event information to be processed as the target event information.

[0009] Optionally, the natural language processing model is trained based on historical event information in a historical database and category labels corresponding to the historical event information, wherein the category labels are at least used to characterize the task intention type and emotional state corresponding to the historical event information; the training steps of the natural language processing model include: using an initial model to extract text features corresponding to the historical event information, and based on the text features, predicting category information corresponding to the historical event information, wherein the category information includes: task intention type and emotional state; determining a loss function value based on the category information predicted by the initial model and the category labels corresponding to the historical event information, and adjusting the model parameters in the initial model based on the loss function value to obtain a natural language processing model.

[0010] Optionally, determining the processing flow corresponding to the event information to be processed based on historical processing flow information includes: determining the process template corresponding to the event information to be processed based on the historical processing flow information, wherein the process template includes multiple process nodes and logical associations between each process node; determining the handling object information corresponding to the event information to be processed based on the incident address and incident time in the event information to be processed, wherein the handling object information is used to characterize the handling combination and / or handler responsible for handling the event task at the incident address within the incident time in the link corresponding to each process node; adjusting the process template based on the handling object information to obtain the processing flow corresponding to the event information to be processed.

[0011] Optionally, after submitting the event information to be processed to the corresponding node process according to the processing flow, the method also includes: obtaining the processing result returned after the node process corresponding to the event information to be processed is executed in the system; when the processing result indicates that the event task corresponding to the event information to be processed has been completed, the event information to be processed, as well as the category information and processing flow corresponding to the event information to be processed, are added to the historical database.

[0012] According to another aspect of the embodiment of the present application, an event information processing device is also provided, including: an information acquisition module, used to acquire event information to be processed, wherein the event information to be processed is information reported by staff to describe event tasks that need to be processed; a preliminary screening module, used to determine the event field corresponding to the event information to be processed, and acquire historical event information corresponding to the event field in the historical database, wherein the historical event information is event information received in the historical process; a target matching module, used to determine a first similarity between the event information to be processed and the historical event information using natural language processing technology, and based on the first similarity, determine target event information corresponding to the event information to be processed in the historical event information; an information submission module, used to acquire historical processing flow information corresponding to the target event information, and based on the historical processing flow information, determine the processing flow corresponding to the event information to be processed, and submit the event information to be processed to the corresponding node flow according to the processing flow.

[0013] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a memory and a processor, the processor being used to run a program stored in the memory, wherein the event information processing method is executed when the program is run.

[0014] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the event information processing method by running the computer program.

[0015] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which implements the steps of the event information processing method when the computer program is executed by a processor.

[0016] In an embodiment of the present application, the method of obtaining information on pending events is adopted, wherein the information on pending events is information reported by staff members for describing event tasks that need to be processed; determining the event field corresponding to the information on pending events, and obtaining historical event information corresponding to the event field in a historical database, wherein the historical event information is event information received in a historical process; using natural language processing technology, determining a first similarity between the information on pending events and the historical event information, and determining target event information corresponding to the information on pending events in the historical event information based on the first similarity; obtaining historical processing flow information corresponding to the target event information, and determining the processing flow corresponding to the information on pending events based on the historical processing flow information, and submitting the information on pending events to the corresponding node flow according to the processing flow, through natural language processing technology, effectively improves the degree of automation of event information processing, reduces the links involving manual participation, and achieves the purpose of improving processing efficiency, thereby solving the technical problem of low efficiency in event information processing caused by the fact that related technologies manually determine the flow of event information to the corresponding department for processing when processing event information. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 It is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for event information processing provided in an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of a method flow for event information processing provided according to an embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of a method flow for automatically submitting multi-dimensional field event information provided according to an embodiment of the present application;

[0021] Figure 4 It is a structural diagram of an event information processing device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In related technologies, when processing event information, it is often necessary to transfer the event information to the corresponding department for processing through manual judgment. The efficiency of event information processing is low. For the risk spread of comprehensive management events in multiple fields, it is necessary to further improve accurate and efficient prevention and control, and take preventive measures quickly. When faced with a large amount of event information in the same jurisdiction, reduce manual participation, automatically judge and submit the transfer, and improve the transfer efficiency.

[0025] In order to solve the above problems, relevant solutions are provided in the embodiments of the present application, which are described in detail below.

[0026] According to an embodiment of the present application, an embodiment of a method for processing event information is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or electronic device) for implementing an event information processing method. Figure 1As shown, the computer terminal 10 (or electronic device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also 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 BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the event information processing method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned event information processing method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0030] The transmission device 106 is used to receive or send data via a network. The specific example of the above network 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), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0032] In the above operating environment, the present application embodiment provides an event information processing method. Figure 2 is a schematic diagram of a method flow for event information processing provided according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0033] Step S202, obtaining information about pending events, wherein the pending event information is information reported by staff members and used to describe event tasks that need to be processed;

[0034] Step S204, determining the event field corresponding to the event information to be processed, and obtaining the historical event information corresponding to the event field in the historical database, wherein the historical event information is the event information received in the historical process;

[0035] Step S206, using natural language processing technology to determine a first similarity between the event information to be processed and the historical event information, and determining target event information corresponding to the event information to be processed in the historical event information based on the first similarity;

[0036] Step S208, obtaining historical processing flow information corresponding to the target event information, and determining the processing flow corresponding to the event information to be processed based on the historical processing flow information, and submitting the event information to be processed to the corresponding node flow according to the processing flow.

[0037] Through the above steps, natural language processing technology is used to effectively improve the degree of automation of event information processing, reduce the links of manual participation, and achieve the purpose of improving processing efficiency, thereby solving the technical problem of low efficiency in event information processing caused by the fact that related technologies use manual judgment when processing event information and transfer event information to the corresponding department for processing.

[0038] The event information processing method in steps S202 to S208 of the embodiment of the present application is further introduced below.

[0039] The embodiment of this application uses an automatic decision submission algorithm combined with natural semantic analysis model capabilities to conduct in-depth analysis of existing data resources, aggregate the information of the processing personnel and convert it into a linear vector. Once the data is hit, the links and processing information of the hit data will be used as a template for the current data, allowing the event data in the current corresponding field to be submitted and transferred to the processor autonomously, simplifying the submission decision. Provide a reference template for automatic data submission processing and output the corresponding model capabilities. Specifically, Figure 3 As shown, a detailed introduction is given below.

[0040] First, data collection is performed, that is, information on pending events is obtained. In this embodiment, the pending event information may be garbage disposal problems reported by community grid members through mobile terminals (grid APP) or smart devices (camera capture) or online platforms, such as garbage accumulation, littering, etc.

[0041] In some embodiments of the present application, after obtaining the event information to be processed, the time domain corresponding to the event information to be processed may be determined first, and the specific steps are as follows.

[0042] In some embodiments of the present application, the event information to be processed includes: event description information, address of occurrence, time of occurrence, degree of urgency, and scope of impact; determining the event domain corresponding to the event information to be processed includes the following steps: performing word segmentation on the event information to be processed, and determining the part of speech corresponding to each word obtained after word segmentation; performing syntactic analysis on the event information to be processed based on the part of speech corresponding to each word, and obtaining semantic structure information corresponding to the event information to be processed, wherein the semantic structure information is used to characterize the contextual association relationship between each word in the event information to be processed; determining keywords of the event information to be processed based on the semantic structure information, and calculating the second similarity between the keywords and the domain keywords corresponding to each event domain; determining the event domain corresponding to the event information to be processed based on the second similarity.

[0043] Through precise semantic analysis, the domain of the event can be identified more accurately, and then the historical event information corresponding to the event domain can be obtained from the historical database for subsequent analysis and processing, thereby improving the pertinence and efficiency of event processing. Especially when dealing with complex events, the correct processing department can be quickly located.

[0044] Among them, the event fields include but are not limited to community services, public safety, environmental protection, public health and other fields involved in grassroots governance. In this embodiment, taking garbage disposal in community services as an example, the subsequent automatic decision submission process and the prediction and classification process of garbage disposal events through natural language processing (Natural Language Processing, NLP) technology are further introduced.

[0045] In this embodiment, the system can use the pending event information obtained this time as metadata based on the problems and related data collected from various channels, including event description, incident address, incident time, urgency, scope of impact, etc., and perform classification matching in combination with similarity center rules and NLP text similarity analysis, as follows.

[0046] In some embodiments of the present application, determining target event information corresponding to the event information to be processed in the historical event information based on the first similarity includes the following steps: determining the word frequency of keywords in the event information to be processed in the historical event information, and the inverse document frequency corresponding to the keywords, wherein the word frequency is used to characterize the number of times the keywords appear in the historical event information, and the inverse document frequency is used to characterize the number of historical event information containing the keywords; determining the first similarity between the event information to be processed and the historical event information based on the word frequency and the inverse document frequency; determining the historical event information whose first similarity exceeds a preset similarity threshold as candidate event information; using a natural language processing model to analyze the event information to be processed, obtain analysis results, and determine the target event information from the candidate event information based on the analysis results.

[0047] Specifically, in this embodiment, a relational database can be used as a collection of historical event information. By aggregating, analyzing, matching, and range searching the event information to be processed, and utilizing analysis and calculation of the frequency of occurrence of term documents (term weight allocation, term frequency factor calculation), the correlation data of the event information to be processed in the historical event information collection can be calculated, and returned in descending order by similarity score (i.e., first similarity) to obtain candidate event information.

[0048] The calculation formula for determining the first similarity between the event information to be processed and the historical event information based on the word frequency and the inverse document frequency is as follows:

[0049] score(q,d)=coord(q,d)*queryNorm(q)*∑ t in q (tf(t in d)*idf(t)^2*t.getBoost()*

[0050] norm(t,d));

[0051] Among them, score(q,d) is the correlation score (i.e., the first similarity) between query q (i.e., the keywords in the event information to be processed) and document d (i.e., the historical event information); coord(q,d) is the coordination factor, which is used to process the distribution of query terms in the document. If a document contains all the terms in the query, this factor will give a higher score; queryNorm(q) is the normalization factor of query q, which is used to normalize the query to ensure that the scores between different queries are comparable; tf(t ind) is the term frequency of term t in document d; idf(t) is the inverse document frequency of term t; t.getBoost() is the weight boost factor of term t; norm(t,d) is the normalization factor of term t in document d, which is used to normalize the weight of the term and is usually related to the distribution of the term in the document.

[0052] After obtaining the candidate event information, a natural language processing model can be used to determine the target event information and the corresponding department flow process from the candidate event information. The specific steps are as follows.

[0053] In some embodiments of the present application, determining target event information in candidate event information based on analysis results includes the following steps: using a natural language processing model to extract features of the event information to be processed to obtain text features; determining analysis results based on the text features, wherein the analysis results include: the task intention type and emotional state corresponding to the event information to be processed, the emotional state being used to characterize the emotional tendency of the staff when reporting the event information to be processed; and determining candidate event information whose task intention type and emotional state in the candidate event information are consistent with those of the event information to be processed as target event information.

[0054] Specifically, for data that has been preliminarily assigned a match (i.e., candidate event information), a classification model algorithm (i.e., a natural language processing model) can be used to accurately analyze the data to identify event categories and potential solutions (based on the training historical data set processing steps).

[0055] In this embodiment, the above natural language processing model can be trained based on the data in the historical database, as follows.

[0056] In some embodiments of the present application, a natural language processing model is trained based on historical event information in a historical database and category labels corresponding to the historical event information, wherein the category labels are at least used to characterize the task intention type and emotional state corresponding to the historical event information; the training steps of the natural language processing model include: using an initial model to extract text features corresponding to the historical event information, and based on the text features, predicting category information corresponding to the historical event information, wherein the category information includes: task intention type and emotional state; determining a loss function value based on the category information predicted by the initial model and the category labels corresponding to the historical event information, and adjusting the model parameters in the initial model based on the loss function value to obtain a natural language processing model.

[0057] Specifically, a similarity rule engine can be used to make similarity rule judgments and corresponding thresholds according to key fields, decompose word roots, compare and update the word root library and parse word roots for historical data to complete the training and correction of the classification model, iteratively update the classification model, and provide more accurate classification result recommendations for subsequent new data.

[0058] For example, for data in the field of garbage disposal, the training and use steps of the model may include: data preprocessing: collect garbage disposal related text data reported by grid members, and perform preprocessing steps such as cleaning, word segmentation, and removal of stop words; feature extraction: use NLP technology to extract text features, such as event description, address of the incident, and urgency of the incident, and use NLP to perform sentiment analysis based on the description; model training: use recurrent neural network RNN ​​and support vector machine SVM deep learning models, and use the extracted features to train the model; event classification: the model classifies new garbage disposal events according to the training results, such as littering, garbage accumulation, etc.; application of prediction results: apply the classification results to the automatic decision submission process to achieve more accurate and efficient garbage disposal event processing and operation; continuous optimization: optimize the accuracy and efficiency of prediction classification by continuously collecting feedback and adjusting model parameters.

[0059] After determining the target event information and historical processing flow information corresponding to the pending event information, the departmental transfer process of the pending event information can be determined, and the business process can be automatically submitted to the next handling organization and handler. The specific steps are as follows.

[0060] In some embodiments of the present application, determining the processing flow corresponding to the event information to be processed based on historical processing flow information includes the following steps: determining the process template corresponding to the event information to be processed based on the historical processing flow information, wherein the process template includes multiple process nodes and logical associations between the process nodes; determining the handling object information corresponding to the event information to be processed based on the incident address and incident time in the event information to be processed, wherein the handling object information is used to characterize the handling combination and / or handler responsible for handling the event task at the incident address within the incident time in the link corresponding to each process node; adjusting the process template based on the handling object information to obtain the processing flow corresponding to the event information to be processed.

[0061] Specifically, the distribution intelligent engine rules can be used, combined with the system user system and the deployed business process system, to convert the flow process node information into a linear relationship through the rule engine according to the geographical information, and automatically distribute and submit the process according to the established rules within the linear relationship. For data sets that are not included in the linear relationship, the NLP semantic analysis model can be used for training to bring the non-linear data sets closer to the existing rules in the engine. Based on the analysis results, the system can automatically generate decision suggestions, such as recommending the next processing link: self-processing or upgraded processing, etc., and provide the relevant processing organization and processing personnel information under the corresponding processing for selection. The decision suggestions are recommended by the intelligent system and are self-processed or automatically submitted to the community manager or relevant department for further review and execution.

[0062] In addition, after submitting the event information to be processed to the corresponding node process according to the processing flow, the method also includes the following steps: obtaining the processing result returned after the node process corresponding to the event information to be processed is executed in the system; when the processing result indicates that the event task corresponding to the event information to be processed has been completed, the event information to be processed, as well as the category information and processing flow corresponding to the event information to be processed, are added to the historical database.

[0063] For example, after completing an automatic submission, the execution result is fed back to the system. By analyzing the execution result, the current data can be entered into the historical data set, the entries generated this time can be compared with the entry library, and the roots that are not in the root library can be updated and entered into the root library. This allows for automatic cyclic training and iterative update of the results into the relationship mapping set to optimize future decision-making processes.

[0064] In the embodiment of the present application, the algorithm rules can be configured and dynamically adjusted. Rules can be formulated according to the direction of the links, or according to the organizational users, and the link processing steps can be disassembled. In combination with the organizational user information in the system architecture, the handling organization and the handling personnel can be automatically found, and the prevention and control information can be reported and sent to the handler for processing. In combination with the dynamic message template, it can be automatically filled, and the collector no longer needs to manually select and submit it to the handler. Effectively shorten the data collection and submission cycle, clarify the division of labor in the disposal process of functional administrative departments, analyze the transition from mainly relying on manual labor to relying on existing data resource libraries, and let the data be submitted actively. Relieve the pressure of prevention and control of comprehensive management incidents in multiple fields at the grassroots level, reduce the number of reports of manual intervention, shorten the time difference caused by manual participation, and automatically determine and submit prevention and control information; ensure the security, efficiency and accuracy of data circulation.

[0065] This application scheme automatically identifies the field of event information to be processed and historical similar events through natural language processing technology, and then determines the processing flow of the current event according to the processing flow of historical events, thereby realizing the automation and intelligence of event processing. This method not only improves the efficiency of event processing and reduces manual errors, but also can continuously improve the accuracy and service quality of event processing through continuous learning and optimization, and provides an efficient and intelligent event information processing solution for organizations and institutions. In practical applications, this method and device can be widely used in various scenarios, such as emergency rescue, customer service, fault repair, legal consultation, medical diagnosis, intelligent customer service system, emergency event response platform, fault repair management system, enterprise internal event management system, public service platform, emergency response system of medical institutions, etc., which can not only significantly improve the efficiency and accuracy of event processing, but also provide more humane and effective services through the recognition of emotional state, and continuously improve the intelligent level of event processing through continuous learning and optimization, so as to provide users with a more efficient, intelligent and humane service experience. At the same time, the wide application of this method and device can also promote the development of related fields, promote the automation and intelligence of event processing, and provide strong support for the efficient operation and intelligent management of society.

[0066] According to an embodiment of the present application, an embodiment of an event information processing device is also provided. Figure 4 Schematic diagram of the structure of an event information processing device provided according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0067] The information acquisition module 40 is used to acquire information about pending events, wherein the pending event information is information reported by staff members and used to describe event tasks that need to be processed;

[0068] A preliminary screening module 42 is used to determine the event field corresponding to the event information to be processed, and obtain historical event information corresponding to the event field in the historical database, wherein the historical event information is event information received in the historical process;

[0069] The target matching module 44 is used to determine the first similarity between the event information to be processed and the historical event information by using natural language processing technology, and determine the target event information corresponding to the event information to be processed in the historical event information according to the first similarity;

[0070] The information submission module 46 is used to obtain the historical processing flow information corresponding to the target event information, and determine the processing flow corresponding to the event information to be processed based on the historical processing flow information, and submit the event information to be processed to the corresponding node flow according to the processing flow.

[0071] Optionally, the event information to be processed includes: event description information, address of occurrence, time of occurrence, degree of urgency, and scope of impact; determining the event domain corresponding to the event information to be processed includes: performing word segmentation on the event information to be processed, and determining the part of speech corresponding to each word obtained after word segmentation; performing syntactic analysis on the event information to be processed based on the part of speech corresponding to each word, and obtaining semantic structure information corresponding to the event information to be processed, wherein the semantic structure information is used to characterize the contextual association relationship between each word in the event information to be processed; determining keywords of the event information to be processed based on the semantic structure information, and calculating the second similarity between the keywords and the domain keywords corresponding to each event domain; determining the event domain corresponding to the event information to be processed based on the second similarity.

[0072] Optionally, based on the first similarity, determining the target event information corresponding to the event information to be processed in the historical event information includes: determining the word frequency of the keywords in the event information to be processed in the historical event information, and the inverse document frequency corresponding to the keywords, wherein the word frequency is used to characterize the number of times the keywords appear in the historical event information, and the inverse document frequency is used to characterize the number of historical event information containing the keywords; determining the first similarity between the event information to be processed and the historical event information based on the word frequency and the inverse document frequency; determining the historical event information whose first similarity exceeds a preset similarity threshold as candidate event information; using a natural language processing model to analyze the event information to be processed to obtain analysis results, and determining the target event information from the candidate event information based on the analysis results.

[0073] Optionally, based on the analysis results, determining the target event information in the candidate event information includes: using a natural language processing model to extract features of the event information to be processed to obtain text features; determining the analysis results based on the text features, wherein the analysis results include: the task intention type and emotional state corresponding to the event information to be processed, the emotional state being used to characterize the emotional tendency of the staff when reporting the event information to be processed; and determining the candidate event information whose task intention type and emotional state are consistent with those of the event information to be processed as the target event information.

[0074] Optionally, the natural language processing model is trained based on historical event information in a historical database and category labels corresponding to the historical event information, wherein the category labels are at least used to characterize the task intention type and emotional state corresponding to the historical event information; the training steps of the natural language processing model include: using an initial model to extract text features corresponding to the historical event information, and based on the text features, predicting category information corresponding to the historical event information, wherein the category information includes: task intention type and emotional state; determining a loss function value based on the category information predicted by the initial model and the category labels corresponding to the historical event information, and adjusting the model parameters in the initial model based on the loss function value to obtain a natural language processing model.

[0075] Optionally, determining the processing flow corresponding to the event information to be processed based on historical processing flow information includes: determining the process template corresponding to the event information to be processed based on the historical processing flow information, wherein the process template includes multiple process nodes and logical associations between each process node; determining the handling object information corresponding to the event information to be processed based on the incident address and incident time in the event information to be processed, wherein the handling object information is used to characterize the handling combination and / or handler responsible for handling the event task at the incident address within the incident time in the link corresponding to each process node; adjusting the process template based on the handling object information to obtain the processing flow corresponding to the event information to be processed.

[0076] Optionally, after submitting the event information to be processed to the corresponding node process according to the processing flow, it also includes: obtaining the processing result returned after the node process corresponding to the event information to be processed is executed in the system; when the processing result indicates that the event task corresponding to the event information to be processed has been completed, the event information to be processed, as well as the category information and processing flow corresponding to the event information to be processed, are added to the historical database.

[0077] It should be noted that the various modules in the above-mentioned event information processing device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0078] It should be noted that the event information processing device provided in this embodiment can be used to execute Figure 2 The event information processing method shown, therefore, the relevant explanations and instructions on the above-mentioned event information processing method are also applicable to the embodiments of the present application and will not be repeated here.

[0079] An embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following event information processing method by running the computer program: obtaining event information to be processed, wherein the event information to be processed is information reported by staff to describe event tasks that need to be processed; determining an event field corresponding to the event information to be processed, and obtaining historical event information corresponding to the event field in a historical database, wherein the historical event information is event information received in a historical process; using natural language processing technology to determine a first similarity between the event information to be processed and the historical event information, and based on the first similarity, determining target event information corresponding to the event information to be processed in the historical event information; obtaining historical processing flow information corresponding to the target event information, and determining the processing flow corresponding to the event information to be processed based on the historical processing flow information, and submitting the event information to be processed to the corresponding node flow according to the processing flow.

[0080] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the event information processing method described in each embodiment of the present application: obtaining event information to be processed, wherein the event information to be processed is information reported by staff to describe event tasks that need to be processed; determining the event field corresponding to the event information to be processed, and obtaining historical event information corresponding to the event field in a historical database, wherein the historical event information is event information received in the historical process; using natural language processing technology to determine a first similarity between the event information to be processed and the historical event information, and based on the first similarity, determining target event information corresponding to the event information to be processed in the historical event information; obtaining historical processing flow information corresponding to the target event information, and determining the processing flow corresponding to the event information to be processed based on the historical processing flow information, and submitting the event information to be processed to the corresponding node flow according to the processing flow.

[0081] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0082] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0085] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0087] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing event information, characterized in that: include: Obtaining pending event information, wherein the pending event information is information reported by staff to describe event tasks that need to be processed; Determine the event field corresponding to the event information to be processed, and obtain historical event information corresponding to the event field in a historical database, wherein the historical event information is event information received in a historical process; Using natural language processing technology, determine a first similarity between the event information to be processed and the historical event information, and determine target event information corresponding to the event information to be processed in the historical event information based on the first similarity; The historical processing flow information corresponding to the target event information is obtained, and the processing flow corresponding to the event information to be processed is determined based on the historical processing flow information, and the event information to be processed is submitted to the corresponding node flow according to the processing flow.

2. The event information processing method according to claim 1, characterized in that: The event information to be processed includes: event description information, address of occurrence, time of occurrence, degree of urgency, and scope of impact; determining the event field corresponding to the event information to be processed includes: Performing word segmentation on the event information to be processed, and determining the part of speech corresponding to each word obtained after the word segmentation; According to the part of speech corresponding to each word, the event information to be processed is subjected to syntactic analysis to obtain semantic structure information corresponding to the event information to be processed, wherein the semantic structure information is used to characterize the contextual association relationship between the words in the event information to be processed; Determine keywords of the event information to be processed according to the semantic structure information, and calculate a second similarity between the keywords and a domain keyword corresponding to each event domain; According to the second similarity, an event field corresponding to the event information to be processed is determined.

3. The event information processing method according to claim 2, characterized in that: According to the first similarity, Determining the target event information corresponding to the event information to be processed in the historical event information includes: Determine the word frequency of the keyword in the event information to be processed in the historical event information, and the inverse document frequency corresponding to the keyword, wherein the word frequency is used to represent the number of occurrences of the keyword in the historical event information, and the inverse document frequency is used to represent the number of historical event information containing the keyword; Determining a first similarity between the event information to be processed and the historical event information according to the word frequency and the inverse document frequency; Determine the historical event information whose first similarity exceeds a preset similarity threshold as candidate event information; A natural language processing model is used to analyze the event information to be processed to obtain an analysis result, and based on the analysis result, the target event information is determined in the candidate event information.

4. The event information processing method according to claim 3, characterized in that: Determining the target event information in the candidate event information according to the analysis result includes: Using the natural language processing model, extracting features from the event information to be processed to obtain text features; Determine the analysis result according to the text feature, wherein the analysis result includes: the task intention type and emotional state corresponding to the pending event information, wherein the emotional state is used to characterize the emotional tendency of the staff member when reporting the pending event information; The candidate event information whose task intention type and emotional state are consistent with the event information to be processed is determined as the target event information.

5. The event information processing method according to claim 3, characterized in that: The natural language processing model is trained based on the historical event information in the historical database and the category labels corresponding to the historical event information, wherein the category labels are at least used to characterize the task intention type and emotional state corresponding to the historical event information; the training steps of the natural language processing model include: Using an initial model, extracting text features corresponding to the historical event information, and predicting category information corresponding to the historical event information based on the text features, wherein the category information includes: the task intention type and the emotional state; The loss function value is determined based on the category information predicted by the initial model and the category label corresponding to the historical event information, and the model parameters in the initial model are adjusted based on the loss function value to obtain the natural language processing model.

6. The event information processing method according to claim 2, characterized in that: Determining the processing flow corresponding to the event information to be processed according to the historical processing flow information includes: Determine a process template corresponding to the event information to be processed according to the historical processing process information, wherein the process template includes multiple process nodes and logical associations between the process nodes; According to the address and time of occurrence in the event information to be processed, determine the handling object information corresponding to the event information to be processed, wherein the handling object information is used to represent the handling combination and / or handler responsible for handling the event task at the address and time of occurrence in the link corresponding to each process node; The process template is adjusted according to the processing object information to obtain the processing flow corresponding to the event information to be processed.

7. The event information processing method according to claim 1, characterized in that: After submitting the event information to be processed to the corresponding node process according to the processing process, the method further includes: Obtaining the processing result returned after the node process corresponding to the event information to be processed is executed in the system; When the processing result indicates that the event task corresponding to the event information to be processed has been completed, the event information to be processed, and the category information and processing flow corresponding to the event information to be processed are added to the historical database.

8. An event information processing device, characterized in that: include: An information acquisition module is used to acquire information about pending events, wherein the pending event information is information reported by staff members to describe event tasks that need to be processed; A preliminary screening module, used to determine the event field corresponding to the event information to be processed, and obtain historical event information corresponding to the event field in the historical database, wherein the historical event information is event information received in the historical process; a target matching module, configured to determine a first similarity between the event information to be processed and the historical event information by using a natural language processing technique, and to determine, in the historical event information, target event information corresponding to the event information to be processed; The information submission module is used to obtain the historical processing flow information corresponding to the target event information, and determine the processing flow corresponding to the event information to be processed based on the historical processing flow information, and submit the event information to be processed to the corresponding node flow according to the processing flow.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the event information processing method described in any one of claims 1 to 7 when running.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the event information processing method described in any one of claims 1 to 7 by running the computer program.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the event information processing method described in any one of claims 1 to 7 are implemented.

Images