An event automatic handling method, device and system based on semantic analysis

Abstract

This invention provides an automatic event handling method, apparatus, and system based on semantic analysis, relating to the field of semantic analysis technology. The method includes: acquiring reported information; determining semantic integrity features, event urgency features, and reporting time features based on the reported information; determining recall priority parameters based on the semantic integrity features and event urgency features; determining a correction strategy based on the relationship between the semantic integrity features and a integrity threshold; determining coarse-ranking priority parameters based on the correction strategy and the recall priority parameters; determining target priority parameters based on the coarse-ranking priority parameters and the reporting time features; and determining an event handling sequence based on the target priority parameters. This method introduces a comprehensive judgment of the semantic integrity and accuracy of the reported information, overcoming the shortcomings of related technologies that rely solely on urgency assessment, thereby improving the accuracy and comprehensiveness of information processing.

Description

Technical Field

[0001] This invention relates to the field of semantic analysis technology, and in particular to an automatic event handling method, apparatus and system based on semantic analysis. Background Technology

[0002] With social development and the advancement of information technology, the demand for automated handling of various emergency events, such as natural disasters, public safety incidents, and sudden technical failures, is constantly growing. Rapid response and effective handling of these events are crucial for ensuring social stability. However, due to the diversity and complexity of reported information, relying solely on manual methods for receiving, analyzing, and prioritizing events is inefficient and carries a high risk of misjudgment. Therefore, utilizing artificial intelligence and semantic analysis technologies to automate event handling has become a key focus of research and development.

[0003] When processing reported events, related technologies typically rely on simple keyword matching and preset rules to determine the type and urgency of the event. This method often falls short when faced with complex or ambiguous information, struggling to accurately prioritize events and leading to response delays and mishandling. In other words, most of the handling methods in these technologies can only determine the urgency of an event based on the reported information; they cannot simultaneously assess the accuracy and completeness of the reported information, nor can they adjust event handling strategies or sequences according to the reporting time, easily resulting in delays and mishandling.

[0004] Therefore, there is an urgent need for an automatic event handling method, device, and system based on semantic analysis. Summary of the Invention

[0005] This invention provides an automatic event handling method based on semantic analysis, comprising:

[0006] Obtain and report information;

[0007] Based on the reported information, semantic integrity features, event urgency features, and reporting time features are determined.

[0008] Based on semantic integrity features and event urgency features, recall priority parameters are determined;

[0009] The correction strategy is determined based on the relationship between semantic integrity features and integrity threshold.

[0010] Based on the correction strategy and recall priority parameters, determine the coarse ranking priority parameters;

[0011] Based on the coarse-sorting priority parameters and the reporting time characteristics, the target priority parameters are determined;

[0012] The sequence of events to be handled is determined based on the target priority parameter.

[0013] Furthermore, based on the relationship between semantic integrity features and the integrity threshold, a correction strategy is determined, including:

[0014] When the semantically complete feature is less than the completeness threshold;

[0015] Based on the reported information, supplementary information is obtained according to the large language model;

[0016] Based on the supplementary information, the first correction parameter is determined;

[0017] Based on the first correction parameter and the recall priority parameter, determine the coarse ranking priority parameter;

[0018] When the semantically complete feature is greater than or equal to the completeness threshold;

[0019] Based on the reported information, subjective evaluation information is obtained according to the large language model;

[0020] The second correction parameter is determined based on subjective evaluation information;

[0021] Based on the second correction parameter and the recall priority parameter, the coarse ranking priority parameter is determined.

[0022] Furthermore, supplementary information includes time information, location information, and event information;

[0023] Based on the supplementary information, the first correction parameter is determined, including:

[0024] The time difference factor is determined based on the difference between the time information and the characteristics of the reported time.

[0025] Based on location information, location score factors are determined according to a pre-set location list map;

[0026] Based on event information and according to a preset event list map, the event score factor is determined;

[0027] Based on the time difference factor, location score factor, and event score factor, the first correction parameter is determined, wherein,

[0028]

[0029] In the formula, The first correction parameter, For time difference factor, Location score factor, As an event score factor, These are their respective weight values.

[0030] Furthermore, subjective evaluation information includes timeliness score factors and impact score factors;

[0031] Based on subjective evaluation information, the second correction parameter is determined, including:

[0032] The second correction parameter is determined based on the average of the timeliness score factor and the influence score factor.

[0033] Furthermore, based on the reported information, semantically complete features are determined, including:

[0034] Based on the reported information, and according to the coding model, the coding information is obtained;

[0035] Based on the encoding information, the decoding information is obtained according to the decoding model associated with the encoding model;

[0036] Semantic similarity is determined based on decoded and encoded information;

[0037] Based on the preset language standard structure and the reported information, the semantic completeness is determined;

[0038] Semantic integrity features are determined based on semantic similarity and semantic completeness.

[0039] Furthermore, the default language standard structure includes time, person, location, and event fields;

[0040] Based on a pre-defined language standard structure and the reported information, semantic completeness is determined, including:

[0041] Extract keywords based on the reported information;

[0042] Determine the matching degree set of keywords in the time field, person field, location field, and event field respectively;

[0043] Based on the matching degree set, the semantic completeness is determined.

[0044] Furthermore, based on the reported information, the urgency characteristics of the incident are determined, including:

[0045] Construct an event handling knowledge graph based on historical reported information and historical handling results;

[0046] Based on the reported information, and according to the event handling knowledge graph, the relevant reported information that matches it is determined;

[0047] Based on the information reported in connection with the case, the outcome of the related action is determined.

[0048] Based on the results of related handling, the urgency characteristics of the incident were determined.

[0049] Furthermore, based on the coarse-sorting priority parameters and the reporting time characteristics, the target priority parameters are determined, including:

[0050] The time interval is determined based on the difference between the characteristics of the reported time and the current time;

[0051] Based on the coarse-sorting priority parameters, the event handling plan cycle is determined, which includes low interval cycle, medium interval cycle and high interval cycle;

[0052] The time adjustment factor is determined based on the ratio of the time interval to the event handling plan cycle;

[0053] The target priority parameters are determined based on the coarse-sorting priority parameters and the time adjustment factor.

[0054] The present invention also provides an automatic event handling device based on semantic analysis, which applies the above-mentioned automatic event handling method based on semantic analysis, including:

[0055] The acquisition module is used to acquire reported information;

[0056] The analysis module is used to determine semantic integrity features, event urgency features, and reporting time features based on reported information; it is also used to determine recall priority parameters based on semantic integrity features and event urgency features; it is also used to determine correction strategies based on the relationship between semantic integrity features and integrity thresholds; it is also used to determine coarse ranking priority parameters based on correction strategies and recall priority parameters; and it is also used to determine target priority parameters based on coarse ranking priority parameters and reporting time features.

[0057] The handling module is used to determine the event handling sequence based on the target priority parameters.

[0058] The present invention also provides an automatic event handling system based on semantic analysis, including a processor and a memory communicatively connected to the processor. The memory stores instructions that can be executed by the processor. When the instructions are executed by the processor, they implement the steps of the automatic event handling method based on semantic analysis described above.

[0059] Compared with existing technologies, the automatic event handling method, apparatus, and system based on semantic analysis provided by this invention have at least the following beneficial effects:

[0060] 1. This semantic analysis-based automatic event handling method not only judges the urgency of events based on reported information, but also introduces a comprehensive judgment on the semantic completeness and accuracy of reported information, making up for the shortcomings of related technologies that rely solely on urgency assessment, thereby improving the accuracy and comprehensiveness of information processing. At the same time, by combining the characteristics of the reporting time, this method can adjust the event handling strategy and priority order according to the reporting time, ensuring that events that have not been processed for a long time receive a different priority level than those initially determined, avoiding the improper handling or omissions caused by time delays in traditional methods.

[0061] 2. In this semantic analysis-based automatic event handling method, by comparing semantic integrity features with integrity thresholds, the system can automatically select different correction strategies, thereby adapting to various complex event types and incomplete information situations, further improving the accuracy of the method in event handling. Attached Figure Description

[0062] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0063] Figure 1 This is a flowchart illustrating an automatic event handling system based on semantic analysis, according to some embodiments of this specification.

[0064] Figure 2 This is a structural block diagram of an automatic event handling device based on semantic analysis, as shown in some embodiments of this specification.

[0065] Figure 3 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0066] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0067] Figure 1 This is a flowchart illustrating an automatic event handling system based on semantic analysis, as shown in some embodiments of this specification. Figure 1 As shown, an automatic event handling method based on semantic analysis may include the following steps. Each step will be described in detail below.

[0068] Step S100: Obtain reported information; where reported information refers to information uploaded by users on the user terminal. For example, when the application is used in high-risk scenarios such as mines, the reported information uploaded by users may be: "At 8 pm last night, water seepage occurred at the No. 3 emergency supplies storage site."

[0069] Step S200: Based on the reported information, determine the semantic integrity feature, the event urgency feature, and the reporting time feature. It is understood that the semantic integrity feature, event urgency feature, and reporting time feature can be determined separately from the reported information, and there is no difference in the order of their determination. Furthermore, the semantic integrity feature is used to characterize the completeness and accuracy of the reported information, the event urgency feature is used to characterize the degree of urgency of the event, and the reporting time feature refers to the moment when the user reports the information.

[0070] The step of determining semantically complete features based on reported information may include:

[0071] Step S210: Based on the reported information, obtain the encoding information according to the encoding model.

[0072] Specifically, the reported information is input into an encoding model, such as BERT or other deep learning-based pre-trained models. This model transforms the reported information into a multi-dimensional vector V1 (i.e., encoded information), which captures the semantic features of the text. In this process, the encoding model performs word embedding and semantic modeling on the phrase "At 8 PM last night, water seepage occurred at emergency supplies storage site No. 3," generating the aforementioned multi-dimensional vector V1 representing the text, for example, [0.32, -0.47, 0.58, ...], where each dimension represents a different semantic feature.

[0073] Step S211: Based on the encoding information, obtain the decoding information according to the decoding model associated with the encoding model.

[0074] Specifically, the encoded information can be decoded using a decoding model to obtain a decoded statement. This decoded statement can be in another language, such as the English statement corresponding to the reported information. Then, this English statement can be re-encoded to obtain a new multidimensional vector V2 (referring to the decoded information).

[0075] Step S212: Determine semantic similarity based on decoded and encoded information.

[0076] Specifically, semantic similarity can be determined using the cosine similarity method, which is the way to calculate the angle between two vectors, as shown in the following formula:

[0077]

[0078] in, and These represent the magnitudes of the vectors.

[0079] It is worth noting that by comparing the original information (reported information) and the reconstructed information (decoded statements) to verify semantic similarity, we can determine the accuracy of the reported information in terms of textual expression, thereby avoiding the occurrence of inaccurate semantic analysis due to ambiguity in textual expression during the user's reporting process.

[0080] Step S213: Based on the preset language standard structure, determine the semantic completeness according to the reported information.

[0081] It is worth noting that the default language standard structure includes a time field, a person field, a location field, and an event field.

[0082] Step S213 may include:

[0083] Step S2131: Extract keywords based on the reported information.

[0084] Specifically, for example, when the reported information is "At 8 pm last night, water seepage occurred at Emergency Supplies Storage Site No. 3", the keywords can be extracted as "last night", "Emergency Supplies Storage Site No. 3" and "water seepage".

[0085] Step S2132: Determine the matching degree set of the keywords in the time field, person field, location field, and event field respectively. It can be understood that "last night" can match the time field, "Emergency Supplies Storage Location No. 3" can match the location field, and "seepage" can match the event field. Therefore, at this time, the matching degree set can be [1, 0, 1, 1].

[0086] Step S2133: Determine semantic completeness based on the matching degree set.

[0087] Specifically, in one implementation, the time field, person field, location field and event field can be preset to have the same weight. In this case, the semantic completeness can be determined from the matching degree set [1, 0, 1, 1] as 3 / 4 = 0.75.

[0088] Step S2134: Determine semantic integrity features based on semantic similarity and semantic integrity.

[0089] In this embodiment, the semantic integrity feature can be represented by the product of semantic similarity and semantic integrity. At this time, the value range of the semantic integrity feature is (0,1). The semantic accuracy and semantic integrity it represents can well reflect the accuracy and comprehensiveness of the reported information, making it more intelligent and capable of decision-making when applied to automatic event processing scenarios.

[0090] The step of determining the urgency characteristics of an event based on reported information may include:

[0091] Step S220: Based on historical reported information and historical handling results, construct an event handling knowledge graph. Specifically, the knowledge graph can include various types of events (such as "water seepage", fire, equipment failure, etc.), the location and time of the event, as well as the corresponding historical handling methods and their urgency.

[0092] Step S221: Based on the reported information, determine the relevant related reported information according to the event handling knowledge graph. Understandably, when the reported information is "At 8 PM last night, water seepage occurred at Emergency Supplies Storage Site No. 3," matching related information can be found in the knowledge graph. The keywords "Emergency Supplies Storage Site No. 3" and "water seepage" are used to search the knowledge graph for similar historical events. For example, the related reported information could be the previously recorded "Water seepage problems have occurred multiple times at Emergency Supplies Storage Sites No. 1 and No. 3, resulting in damage to supplies and environmental impact."

[0093] Step S222: Determine the associated handling results based on the associated reported information. Specifically, the found associated reported information will link to historical handling results, such as "In a certain month of a certain year, a water seepage incident occurred at Emergency Supplies Storage Site No. 3. Supplies transfer measures and environmental monitoring measures were taken, and no major safety impact was caused. The post-incident emergency score was 3 points." It can also be understood that the post-incident emergency score can be an artificially defined score based on the event outcome, with a range of 0-10 points.

[0094] Step S223: Based on the associated handling results, determine the urgency characteristics of the event. It is understood that in this embodiment, the urgency characteristics of the event can be directly represented by a post-event urgency score.

[0095] Step S300: Determine recall priority parameters based on semantic integrity features and event urgency features.

[0096] It is worth noting that the recall priority parameter can be the product of semantically complete features and event urgency features.

[0097] Step S400: Determine the correction strategy based on the relationship between semantic integrity features and integrity threshold.

[0098] Specifically, step S400 may include the following steps:

[0099] Step S410: In response to the semantic integrity feature being less than the integrity threshold, supplementary information is obtained based on the reported information and the large language model. The supplementary information may include time information, location information, and event information, where the time information refers to the time the event occurred. The large language model can be a language model from existing technologies, which can obtain the supplementary information through a question-and-answer dialogue.

[0100] It is worth noting that the complete threshold in this embodiment can be 0.3. When the semantic completeness feature is less than the complete threshold, it means that the semantics of the reported information are incomplete and inaccurate. It is impossible to obtain the accurate event status based on the reported information. Therefore, information supplementation is required to improve the accuracy of event handling.

[0101] Step S411: Determine the first correction parameter based on the supplementary information.

[0102] Specifically, the time difference factor can be determined based on the difference between the time information and the reported time characteristics. The time difference factor ranges from 0 to 10. The larger the difference between the time information and the reported time characteristics, the larger the time difference factor, indicating that more correction of the recall priority parameters is needed at this time.

[0103] Based on location information and a preset location list map, location score factors are determined. The preset location list map defines different locations according to different security levels; for example, if the aforementioned "Emergency Supplies Storage Location No. 3" is a high-security location, its corresponding location score factor will be a higher value.

[0104] Based on event information and a preset event list map, event score factors are determined. The preset event list map defines different events according to different security levels; for example, if the aforementioned "water seepage" is a low-security event, its corresponding location score factor will be a lower value.

[0105] Then, based on the time difference factor, location score factor, and event score factor, the first correction parameter is determined.

[0106] In the formula, The first correction parameter, For time difference factor, Location score factor, As an event score factor, These are their respective weight values.

[0107] Step S412: Determine the coarse ranking priority parameters based on the first correction parameter and the recall priority parameter. The coarse ranking priority parameters can be determined using the following formula.

[0108]

[0109] in, It is a constant, which is usually 1. The difference between the maximum value and the minimum value of the recall priority parameter, in this embodiment, , As a priority parameter for recall, These are parameters for coarse-sorting priority.

[0110] Step S420: In response to the semantic integrity feature being greater than or equal to the integrity threshold, subjective evaluation information is obtained based on the reported information and the large language model. Specifically, the subjective evaluation information includes timeliness score factor and impact score factor, which can be evaluated by the user at the input end.

[0111] It is worth noting that when the semantics are sufficiently complete (i.e., when the semantic completeness feature is greater than or equal to the completeness threshold), by supplementing subjective evaluation information, the system can better consider the user's subjective cognition and the user's judgment on the harm of the reported event, thereby enhancing the accuracy of event handling.

[0112] Step S421: Determine the second correction parameter based on subjective evaluation information. Specifically, determine the second correction parameter based on the average of the timeliness score factor and the influence score factor.

[0113] Step S422: Determine the coarse ranking priority parameters based on the second correction parameter and the recall priority parameter. It is understood that this formula is similar to the formula in step S412, and will not be repeated here.

[0114] Step S500: Based on the correction strategy and recall priority parameters, determine the coarse ranking priority parameters. Specifically, the application status of this step under different conditions has been described in steps S412 and S422.

[0115] Step S600: Determine the target priority parameters based on the coarse sorting priority parameters and the reporting time characteristics.

[0116] Step S600 may include steps S610-S640.

[0117] Step S610: Determine the time interval based on the difference between the reported time characteristics and the current time;

[0118] Step S620: Based on the coarse-ranking priority parameters, determine the event handling plan cycle, which includes a low-interval cycle, a medium-interval cycle, and a high-interval cycle. Specifically, when the coarse-ranking priority parameter is less than the first priority threshold, the corresponding event handling plan cycle is a high-interval cycle, and the reported event is a non-urgent event; when the coarse-ranking priority parameter is less than the second priority threshold but greater than or equal to the first priority threshold, the corresponding event handling plan cycle is a medium-interval cycle, and the reported event is a normal event; when the coarse-ranking priority parameter is greater than or equal to the second priority threshold, the corresponding event handling plan cycle is a low-interval cycle, and the reported event is an urgent event. The low-interval cycle can be 24 hours, the medium-interval cycle can be 72 hours, and the high-interval cycle can be 144 hours.

[0119] Step S630: Determine the time adjustment factor based on the ratio of the time interval to the event response plan cycle. For example, if the time interval is 12 hours, and the reported information "At 8 PM last night, water seepage occurred at emergency material storage site No. 3" is a high interval, then the time adjustment factor can be determined to be 12 / 144=0.8333.

[0120] Step S640: Determine the target priority parameters based on the coarse ranking priority parameters and the time adjustment factor.

[0121] It is worth noting that the target priority parameter can be determined by weighting the coarse-ranking priority parameter with a time adjustment factor. Furthermore, the target priority parameter in this embodiment can be automatically updated after a preset period of time, using the target priority parameter from the previous update time as the coarse-ranking priority parameter for the current update time, thus achieving the purpose of automatic system update of the target priority parameter.

[0122] Step S700: Determine the event handling sequence based on the target priority parameters. Specifically, the system may receive multiple reported messages at a certain moment. By obtaining the target priority parameters corresponding to the multiple reported messages at the current moment and sorting them according to their magnitude, the event handling sequence can be determined. This allows for prioritizing the handling of more urgent events and avoiding resource waste.

[0123] Figure 2 This is a structural block diagram of an automatic event handling device based on semantic analysis, as shown in some embodiments of this specification. Figure 2 As shown, an automatic event handling device based on semantic analysis may include: an acquisition module for acquiring reported information; an analysis module for determining semantic integrity features, event urgency features, and reporting time features based on the reported information; further for determining recall priority parameters based on semantic integrity features and event urgency features; further for determining a correction strategy based on the relationship between semantic integrity features and integrity thresholds; further for determining coarse ranking priority parameters based on the correction strategy and recall priority parameters; further for determining target priority parameters based on coarse ranking priority parameters and reporting time features; and a handling module for determining an event handling sequence based on the target priority parameters.

[0124] An automatic event handling device based on semantic analysis can apply an automatic event handling method based on semantic analysis. For more details on an automatic event handling device based on semantic analysis, please refer to the relevant description of an automatic event handling method based on semantic analysis, which will not be repeated here.

[0125] Figure 3 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 3The computer system 300 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0126] like Figure 3 As shown, the computer system 300 includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 302 or programs loaded from storage portion 308 into Random Access Memory (RAM) 303. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0127] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0128] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs various functions defined in the system of this application.

[0129] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0132] Another aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer's processor, causes the computer to perform the method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0133] Another aspect of this application provides an automatic event handling system based on semantic analysis, including a processor and a memory communicatively connected to the processor. The memory stores instructions that can be executed by the processor. When the instructions are executed by the processor, they implement the steps of the automatic event handling method based on semantic analysis described above.

[0134] The above embodiments are merely preferred embodiments provided to fully illustrate this application, and the scope of protection of this application is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on this application are all within the scope of protection of this application.

Claims

1. An automatic event handling method based on semantic analysis, characterized in that, include: Obtain and report information; Based on the reported information, semantic integrity features, event urgency features, and reporting time features are determined; Based on the semantic integrity feature and the event urgency feature, the recall priority parameters are determined; The correction strategy is determined based on the relationship between semantic integrity features and integrity threshold. Based on the correction strategy and the recall priority parameters, determine the coarse ranking priority parameters; Based on the coarse-sorting priority parameters and the reporting time characteristics, the target priority parameters are determined; Based on the target priority parameters, determine the event handling sequence; The step of determining the target priority parameters based on the coarse-sorting priority parameters and the reporting time characteristics includes: The time interval is determined based on the difference between the reported time characteristics and the current time; Based on the coarse-sorting priority parameters, the event handling plan cycle is determined, wherein the event handling plan cycle includes a low interval cycle, a medium interval cycle, and a high interval cycle; A time adjustment factor is determined based on the ratio of the time interval to the event handling plan cycle; The target priority parameter is determined based on the coarse ranking priority parameter and the time adjustment factor.

2. The automatic event handling method based on semantic analysis according to claim 1, characterized in that, The step of determining the correction strategy based on the relationship between semantic integrity features and the integrity threshold includes: When the semantic integrity feature is less than the integrity threshold; Based on the reported information, supplementary information is obtained according to the large language model; Based on the supplementary information, the first correction parameter is determined; The coarse-sorting priority parameter is determined based on the first correction parameter and the recall priority parameter; When the semantically complete feature is greater than or equal to the completeness threshold; Based on the reported information, subjective evaluation information is obtained according to the large language model; Based on the subjective evaluation information, the second correction parameter is determined; The coarse ranking priority parameter is determined based on the second correction parameter and the recall priority parameter.

3. The automatic event handling method based on semantic analysis according to claim 2, characterized in that, The supplementary information includes time information, location information, and event information; Determining the first correction parameter based on the supplementary information includes: The time difference factor is determined based on the difference between the time information and the characteristics of the reported time. Based on location information, location score factors are determined according to a pre-set location list map; Based on event information and according to a preset event list map, the event score factor is determined; Based on the time difference factor, location score factor, and event score factor, the first correction parameter is determined, wherein, In the formula, The first correction parameter, For time difference factor, Location score factor, As an event score factor, These are their respective weight values.

4. The automatic event handling method based on semantic analysis according to claim 2, characterized in that, The subjective evaluation information includes timeliness score factors and impact score factors; The step of determining the second correction parameter based on the subjective evaluation information includes: The second correction parameter is determined based on the average of the timeliness score factor and the influence score factor.

5. The automatic event handling method based on semantic analysis according to claim 1, characterized in that, The determination of semantically complete features based on the reported information includes: Based on the reported information, the encoding information is obtained according to the encoding model; Based on the encoding information, decoding information is obtained according to the decoding model associated with the encoding model; Based on the decoded information and the encoded information, the semantic similarity is determined; Based on the preset language standard structure, the semantic completeness is determined according to the reported information; The semantic integrity feature is determined based on the semantic similarity and the semantic integrity.

6. The automatic event handling method based on semantic analysis according to claim 5, characterized in that, The preset language standard structure includes a time field, a person field, a location field, and an event field; The determination of semantic completeness based on the reported information, according to a preset language standard structure, includes: Based on the reported information, keywords are extracted; Determine the matching degree set of the keywords in the time field, person field, location field, and event field respectively; The semantic completeness is determined based on the matching degree set.

7. The automatic event handling method based on semantic analysis according to claim 1, characterized in that, The process of determining the urgency characteristics of the event based on the reported information includes: Construct an event handling knowledge graph based on historical reported information and historical handling results; Based on the reported information, and according to the event handling knowledge graph, determine the associated reported information that matches it; Based on the reported information, the associated handling result is determined; Based on the results of the associated handling, the urgency characteristics of the event are determined.

8. An automatic event handling device based on semantic analysis, characterized in that, An automatic event handling method based on semantic analysis, as described in any one of claims 1-7, includes: The acquisition module is used to acquire reported information; The analysis module is used to determine semantic integrity features, event urgency features, and reporting time features based on the reported information; it is also used to determine recall priority parameters based on the semantic integrity features and the event urgency features; it is also used to determine a correction strategy based on the relationship between the semantic integrity features and the integrity threshold; it is also used to determine coarse-ranking priority parameters based on the correction strategy and the recall priority parameters; and it is also used to determine target priority parameters based on the coarse-ranking priority parameters and the reporting time features. The determination of the target priority parameters based on the coarse-ranking priority parameters and the reporting time features includes: determining a time interval based on the difference between the reporting time features and the current time; determining an event handling plan cycle based on the coarse-ranking priority parameters, wherein the event handling plan cycle includes a low-interval cycle, a medium-interval cycle, and a high-interval cycle; determining a time adjustment factor based on the ratio of the time interval to the event handling plan cycle; and determining the target priority parameters based on the coarse-ranking priority parameters and the time adjustment factor. The handling module is used to determine the event handling sequence based on the target priority parameters.

9. An automatic event handling system based on semantic analysis, characterized in that, The method includes a processor and a memory communicatively connected to the processor, the memory storing instructions executable by the processor, the instructions being executed by the processor to implement the steps of a semantic analysis-based automatic event handling method as described in any one of claims 1 to 7.

Images