WO2021136455A1

WO2021136455A1 - Method and apparatus for recognizing police emergency similarity, and device

Info

Publication number: WO2021136455A1
Application number: PCT/CN2020/141811
Authority: WO
Inventors: 陈建国; 孙占辉; 苏国锋; 陈涛; 袁宏永; 周正青; 田超; 郎燕侠; 郑晓娜; 张春霞; 邓欢
Original assignee: 清华大学; 北京辰安科技股份有限公司; 北京辰安信息科技有限公司
Priority date: 2019-12-31
Filing date: 2020-12-30
Publication date: 2021-07-08
Also published as: CN111382779A; CN111382779B

Abstract

A method and an apparatus for recognizing police emergency similarity, and a device. Said method comprises: analyzing current police emergency information and extracting current police emergency features (101); acquiring, according to the current police emergency features, all historical police emergency records satisfying a preset matching condition (102); performing similarity calculation on the current police emergency information and the historical police emergency records, and selecting, according to the calculation result, a target historical police emergency record similar to the current police emergency information (103). Thus, automatic determination of similar emergencies is implemented by acquiring the historical police emergency record similar to the current police emergency information during a police emergency dispatching process, improving the working efficiency of a dispatcher, and improving the determination accuracy.

Description

Method, device and equipment for identifying similarity of police situation

Cross-references to related applications

This application requires a Chinese patent submitted by Tsinghua University, Beijing Chenan Technology Co., Ltd., and Beijing Chenan Information Technology Co., Ltd. on December 31, 2019, with the title of the invention "Method, Device and Equipment for Recognizing Police Similarity" The priority of the application number "201911414920.7".

Technical field

This application relates to the field of machine learning technology, and in particular to a method, device and equipment for identifying similarity of police situation.

Background technique

In the process of receiving the alarm, the person who reports to the police shall describe the situation of the alarm to the person receiving the police by means of telephone alarm, SMS alarm, network alarm, etc. In view of the current situation where the alarm person repeats the alarm, the similarity judgment is of great significance. If the staff receiving and handling police do not make similar judgments, it will cause the same police situation to be dealt with repeatedly and waste police resources.

At present, the staff who receive and dispose of the police usually judge similar alarm conditions manually based on their experience, and the efficiency is low, and each alarm may generate new alarm information, which makes the judgment difficult and less accurate.

Summary of the invention

This application aims to solve one of the technical problems in the related technology at least to a certain extent.

To this end, this application proposes a method, device, equipment, and storage medium for identifying similarity of police conditions. By acquiring historical alarm records similar to the current alarm information in the process of receiving an alarm, it realizes automatic identification of similar police conditions and improves the work of police officers. Efficiency, improve the accuracy of discrimination.

The embodiment of the first aspect of the present application proposes a method for identifying similarity of police situation, including:

Analyze current alarm information to extract current alarm characteristics;

Acquiring all historical alarm records that meet preset matching conditions according to the current alarm characteristics;

The similarity calculation is performed on the current alarm information and each of the historical alarm records, and the target historical alarm records similar to the current alarm information are filtered according to the calculation result.

The method for identifying the similarity of the alarm situation according to the embodiment of the present application extracts the characteristics of the current alarm situation by analyzing the current alarm information, and further, obtains all historical alarm records that meet the preset matching conditions according to the current alarm situation characteristics. Further, the similarity calculation is performed on the current alarm information and each historical alarm record, and the target historical alarm records that are similar to the current alarm information are filtered according to the calculation result. As a result, by acquiring historical alarm records similar to the current alarm information during the alarm reception process, automatic identification of similar alarm conditions is realized, avoiding waste of police resources caused by repeated processing, and improving the work efficiency and accuracy of discrimination of the police. At the same time, the judgment is based on the text similarity, which improves the accuracy of similar warnings.

In addition, the alert similarity recognition method according to the foregoing embodiment of the present application may also have the following additional technical features:

Optionally, when the current alarm feature is an alarm number, obtaining all historical alarm records that meet a preset matching condition according to the current alarm feature includes: obtaining a preset period of time corresponding to the alarm number The first candidate historical alarm record; query the pre-stored alarm state corresponding to the first candidate historical alarm record, and obtain the unclosed first target from the first candidate historical alarm record according to the alarm state Historical alarm records.

Optionally, when the current alarm feature is an alarm address, the acquiring all historical alarm records that meet a preset matching condition according to the current alarm feature includes: obtaining the alarm information within a preset range of the alarm address The second candidate historical alarm record; the second target historical alarm record within a preset time period is obtained from the second candidate historical alarm record.

Optionally, when the current alarm situation feature is an alarm situation type, acquiring all historical alarm records that meet a preset matching condition according to the current alert situation feature includes: acquiring a preset corresponding to the alarm situation type The third candidate historical alarm record in the time period; the third target historical alarm record carrying a similar mark is obtained from the third candidate historical alarm record.

Optionally, the calculation of similarity between the current alarm information and each of the historical alarm records includes: extracting the first high-frequency word in the current alarm information and the second word of each historical alarm record High-frequency words, calculating the distance between the first high-frequency word and the second high-frequency word; calculating the semantic relationship similarity between the current alarm information and each of the historical alarm records; according to the first high The distance between the frequency word and the second high-frequency word and the similarity of the semantic relationship are calculated to calculate the similarity between the current alarm information and each of the historical alarm records.

The embodiment of the second aspect of the present application proposes an alert similarity recognition device, including:

The extraction module is used to analyze the current alarm information and extract the current alarm characteristics;

An obtaining module, configured to obtain all historical alarm records that meet preset matching conditions according to the current alarm characteristics;

The screening module is used to calculate the similarity between the current alarm information and each of the historical alarm records, and filter the target historical alarm records similar to the current alarm information according to the calculation result.

The alarm situation similarity recognition device of the embodiment of the present application obtains historical alarm records similar to the current alarm information during the alarm reception process, realizes automatic identification of similar alarm situations, avoids the waste of police resources caused by repeated processing, and improves the work efficiency of the police officer. And the accuracy of discrimination. At the same time, the judgment is based on the text similarity, which improves the accuracy of similar warnings.

In addition, the alert similarity recognition device according to the foregoing embodiment of the present application may also have the following additional technical features:

Optionally, when the current alarm feature is an alarm number, the obtaining module is specifically configured to: obtain the first candidate historical alarm record within a preset time period corresponding to the alarm number; A candidate historical alarm record corresponds to an alarm state respectively, and an unclosed first target historical alarm record is obtained from the first candidate historical alarm record according to the alarm state.

Optionally, when the current alarm information feature is an alarm information address, the acquiring module is specifically configured to: obtain a second candidate historical alarm record within a preset range of the alarm information address; from the second candidate history The historical alarm record of the second target within the preset time period is acquired from the alarm record.

Optionally, when the current alarm feature is an alarm type, the acquiring module is specifically configured to: obtain a third candidate historical alarm record within a preset time period corresponding to the alarm type; The third target historical alarm record carrying the similar mark is obtained from the candidate historical alarm record.

Optionally, the screening module is specifically configured to: extract the first high-frequency words in the current alarm information and the second high-frequency words in each of the historical alarm records, and calculate the difference between the first high-frequency words and the The distance of the second high-frequency word; calculating the similarity of the semantic relationship between the current alarm information and each of the historical alarm records; according to the distance between the first high-frequency word and the second high-frequency word and the According to the semantic relationship similarity, the similarity between the current alarm information and each historical alarm record is calculated.

An embodiment of the third aspect of the present application proposes a computer device, including a processor and a memory; wherein the processor reads the executable program code stored in the memory to run a computer corresponding to the executable program code. The program is used to implement the alert similarity recognition method as described in the embodiment of the first aspect.

The embodiment of the fourth aspect of the present application proposes a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for identifying similarity of the alarm situation as described in the embodiment of the first aspect is implemented.

The additional aspects and advantages of this application will be partly given in the following description, and some will become obvious from the following description, or be understood through the practice of this application.

Description of the drawings

FIG. 1 is a schematic flow chart of a method for identifying similarity of alarm conditions provided by an embodiment of the application;

FIG. 2 is a schematic flowchart of another method for identifying similarity of alarm conditions provided by an embodiment of the application;

FIG. 3 is a schematic flowchart of another method for identifying similarity of alarm conditions provided by an embodiment of the application;

FIG. 4 is a schematic flowchart of another method for identifying similarity of alarm conditions provided by an embodiment of the application;

FIG. 5 is a schematic structural diagram of an alarm situation similarity recognition device provided by an embodiment of the application.

Detailed ways

The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the drawings are exemplary, and are intended to explain the present application, but should not be understood as a limitation to the present application.

The following describes the alert similarity recognition method, device, and equipment of the embodiments of the present application with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a method for identifying similarity of alarm conditions provided by an embodiment of the application. As shown in Fig. 1, the method includes:

Step 101: Analyze current alarm information and extract current alarm features.

In this embodiment, when performing alarm similarity recognition, the current alarm information can be acquired first, and the current alarm information can be analyzed to extract the current alarm characteristics. Specifically, the alarm information includes the content of the voice call between the caller and the policeman. Through real-time voice recognition of the content of the voice call, the text information showing the content of the call between the two parties is obtained, and then semantic recognition analysis is performed based on the text information, and the current police situation features are extracted .

Among them, the characteristics of the alarm situation include the alarm number, the address of the alarm situation, and the type of the alarm situation.

Step 102: Acquire all historical alarm records that meet preset matching conditions according to the current alarm characteristics.

In this embodiment, matching conditions can be set for different alarm characteristics, and then processing is performed according to the current alarm characteristics and preset matching conditions to determine all historical alarm records that may be similar to the current alarm information.

In an embodiment of the present application, the current alarm feature is the alarm number, and all historical alarm records that meet the preset matching conditions are acquired according to the current alarm feature, including: obtaining the first candidate within the preset time period corresponding to the alarm number Historical alarm records. Furthermore, query the pre-stored alarm state respectively corresponding to the first candidate historical alarm record, and obtain the unclosed first target historical alarm record from the first candidate historical alarm record according to the alarm state.

In an embodiment of the present application, the current alarm feature is the alarm address, and all historical alarm records that meet the preset matching conditions are obtained according to the current alarm feature, including: obtaining the second candidate within the preset range of the alarm address The historical alarm record is used to obtain the second target historical alarm record within a preset time period from the second candidate historical alarm record.

In an embodiment of the present application, the current alarm feature is an alarm type, and all historical alarm records that meet the preset matching condition are acquired according to the current alarm feature, including: obtaining the first alarm record in the preset time period corresponding to the alarm type Three candidate historical alarm records, and further, obtain a third target historical alarm record carrying a similar mark from the third candidate historical alarm record.

Step 103: Perform similarity calculation on the current alarm information and each historical alarm record, and filter target historical alarm records similar to the current alarm information according to the calculation result.

In this embodiment, after obtaining all historical alarm records that meet the preset matching conditions according to the current alarm information, the similarity between the current alarm information and each historical alarm record is calculated, and the historical alarm records are filtered according to the calculated similarity , To determine the target historical alarm record similar to the current alarm information. Specifically, the similarity threshold can be preset, and the preset similarity threshold is compared with the calculated similarity. If the similarity of the historical alarm record is greater than the preset display threshold, the historical alarm record is determined to be the target historical alarm recording. Among them, the similarity threshold can be determined based on a large amount of experimental data, or can be set by itself according to actual needs, and there is no limitation here.

In an embodiment of the present application, calculating the similarity between the current alarm information and each historical alarm record includes: extracting the first high-frequency word in the current alarm information and the second high-frequency word in each historical alarm record, and calculating The distance between the first high-frequency word and the second high-frequency word. Furthermore, the semantic relationship similarity between the current alarm information and each historical alarm record is calculated, and the semantic relationship similarity between the current alarm information and each historical alarm record is calculated according to the distance between the first high-frequency word and the second high-frequency word and the semantic relationship similarity的similarity.

As an example, perform voice recognition on the current alarm call content to obtain text information, segment the text information and count the word frequency of each word, determine the first high-frequency word according to the word frequency, and determine the second word in each historical alarm record. High-frequency words, and calculate the distance between the first high-frequency word and the second high-frequency word through related algorithms. Furthermore, the vector representation of the current alarm information and each historical alarm record is obtained based on the language model, and the semantic relationship similarity between the current alarm information and each historical alarm record is calculated according to the vector representation. Further, according to the distance between the first high-frequency word and the second high-frequency word and the semantic relationship similarity, the similarity between the current alarm information and each historical alarm record is calculated by a weighted summation method.

In an embodiment of the present application, after the target historical alarm records similar to the current alarm information are filtered according to the calculation result, the target historical alarm records may be sorted and displayed in descending order according to the similarity corresponding to the target historical alarm records.

The method for identifying the similarity of the alarm situation according to the embodiment of the present application extracts the characteristics of the current alarm situation by analyzing the current alarm information, and further, obtains all historical alarm records that meet the preset matching conditions according to the current alarm situation characteristics. Further, the similarity calculation is performed on the current alarm information and each historical alarm record, and the target historical alarm records that are similar to the current alarm information are filtered according to the calculation result. As a result, by obtaining historical alarm records similar to the current alarm information during the alarm reception process, automatic identification of similar alarm conditions is realized, the waste of police resources caused by repeated processing is avoided, and the work efficiency and discrimination accuracy of the policemen are improved. At the same time, the judgment is based on the text similarity, which improves the accuracy of similar warnings.

Based on the foregoing embodiment, the following description will be given by taking the current alarm feature as the alarm number as an example.

Fig. 2 is a schematic flow chart of a method for identifying similarity of alarm conditions provided by an embodiment of the application. As shown in Fig. 2, the method includes:

Step 201: Obtain the first candidate historical alarm record within a preset time period corresponding to the alarm number.

As an example, record the alarm number, alarm content, and time each time an alarm is received, and then, for the current alarm information, obtain all historical alarm records of the current alarm number, and determine the history with the current time within a preset time period The alarm record serves as the first candidate historical alarm record. Among them, the preset time period can be set as needed.

Step 202: Query the pre-stored alarm state respectively corresponding to the first candidate historical alarm record, and obtain the unclosed first target historical alarm record from the first candidate historical alarm record according to the alarm state.

In this embodiment, an alarm status database can be set up in advance, and all alarm information and corresponding alarm statuses can be recorded in the database, where the alarm status includes unassigned, dispatched, arrived, closed, and so on. The alarm state corresponding to the first candidate historical alarm record is obtained by querying the database, and then the first target historical alarm record whose alarm state is not closed is filtered out according to the first candidate historical alarm record.

It is understandable that the historical alarm records in the closed state usually indicate that the processing has been completed. For the historical alarm records in the unclosed state, there may be situations in which the alarm person repeats the alarm or consults the processing progress. Therefore, according to the historical alarm records of the same alarm number, the historical alarm records of which the alarm status is not closed can be obtained, which can assist in judging whether the current alarm is an individual repeated alarm, so as to determine that the current alarm information may be similar to the current alarm information. Historical alarm records ensure the efficiency of similar alarm situations.

Based on the above-mentioned embodiment, the following description will be given by taking the current alarm feature as the alarm address as an example.

FIG. 3 is a schematic flow chart of a method for identifying similarity of alarm conditions provided by an embodiment of the application. As shown in FIG. 3, the method includes:

Step 301: Obtain a second candidate historical alarm record within a preset range of the alarm address.

As an example, the alarm address is recorded every time an alarm is received, and further, for the current alarm information, all historical alarm records of the current alarm address are acquired as the second candidate historical alarm record.

As another example, for the current alarm information, all historical alarm records of surrounding addresses within the radius r of the current alarm address may also be obtained as the second candidate historical alarm record.

Step 302: Obtain the second target historical alarm record within a preset time period from the second candidate historical alarm record.

As an example, according to the current time corresponding to the current alarm information and the historical time of each second candidate historical alarm record, the second candidate historical alarm record whose interval with the current time is less than the preset value is determined as the second target Historical alarm records.

In practical applications, there may be multiple people calling the police for an accident at the same location. For example, for the same traffic accident, two car owners may call the police at the same time. Therefore, according to the historical alarm records of the same police address, the preset time period is obtained The historical alarm record can assist in judging whether the current alarm is a repeated alarm, so as to determine the historical alarm record that may be similar to the current alarm information, and ensure the efficiency of similar alarm judgment.

Based on the above-mentioned embodiment, the following description will be made by taking the current alarm feature as an alarm type as an example.

Fig. 4 is a schematic flow chart of a method for identifying similarity of alarm conditions provided by an embodiment of the application. As shown in Fig. 4, the method includes:

Step 401: Obtain a third candidate historical alarm record within a preset time period corresponding to the type of alarm situation.

As an example, the alarm type is recorded every time an alarm is received, where the alarm type may include a fire alarm, a traffic accident, and the like. For the current alarm information, all historical alarm records of the same alarm type and within a preset time period are acquired as the third candidate historical alarm record. Among them, the preset time period can be determined according to the current alarm time.

Step 402: Obtain a third target historical alarm record carrying a similar mark from the third candidate historical alarm record.

In this embodiment, a similar mark may be set on the historical alarm record in advance, and the third target historical alarm record carrying the similar mark may be obtained from the third candidate historical alarm record. Optionally, the policeman may determine whether it is a major similar alarm when receiving the alarm, and if so, set the similarity flag, and then, for the current alarm information, obtain the third candidate historical alarm record, and determine from it that carries the similar flag The third target historical alarm record.

As an example, the policeman A receives a fire alarm 1, and the policeman A judges that it is a major similar alarm based on experience and marks the similar sign. The policeman B receives a fire alarm 2, and obtains the fire alarm 1 with a similar mark according to the type and time of the alarm, as a historical alarm record that may be similar to the current fire alarm 2.

It is understandable that for major alarm situations such as fire alarms, multiple people may repeatedly report to the police. Thus, by obtaining the third candidate historical alarm record within the preset time period corresponding to the type of alarm situation, and obtaining the third target historical alarm record carrying a similar mark from the third candidate historical alarm record, it is possible to receive the alarm information At the same time, it automatically obtains all major similar alarm situations marked by all police officers in the most recent period, improves the accuracy of the system's similar alarm situation identification, and ensures the efficiency of similar alarm situation identification.

In order to implement the above-mentioned embodiments, the present application also proposes an alert similarity recognition device.

FIG. 5 is a schematic structural diagram of a device for identifying similarity of alarm conditions provided by an embodiment of the application. As shown in FIG. 5, the device includes: an extraction module 10, an acquisition module 20, and a screening module 30.

Among them, the extraction module 10 is used to analyze the current alarm information and extract the current alarm characteristics.

The obtaining module 20 is configured to obtain all historical alarm records that meet the preset matching conditions according to the current alarm characteristics.

The screening module 30 is used to calculate the similarity between the current alarm information and each historical alarm record, and filter the target historical alarm records that are similar to the current alarm information according to the calculation result.

In an embodiment of the present application, the current alarm feature is an alarm number, and the obtaining module 20 is specifically configured to: obtain the first candidate historical alarm record within a preset time period corresponding to the alarm number; The first candidate historical alarm records respectively correspond to the alarm state, and the unclosed first target historical alarm record is obtained from the first candidate historical alarm record according to the alarm state.

In an embodiment of the present application, the current alarm feature is an alarm address, and the acquiring module 20 is specifically configured to: obtain a second candidate historical alarm record within a preset range of the alarm address; Acquire the historical alarm record of the second target within the preset time period from the historical alarm record.

In an embodiment of the present application, the current alarm feature is an alarm type, and the acquiring module 20 is specifically configured to: obtain a third candidate historical alarm record within a preset time period corresponding to the alarm type; From the three candidate historical alarm records, obtain a third target historical alarm record carrying a similar mark.

In an embodiment of the present application, the screening module 30 is specifically configured to: extract the first high-frequency word in the current alarm information and the second high-frequency word in each of the historical alarm records, and calculate the first high-frequency word The distance between the frequency word and the second high-frequency word; calculate the semantic relationship similarity between the current alarm information and each of the historical alarm records; according to the first high-frequency word and the second high-frequency word Calculate the similarity between the current alarm information and each historical alarm record.

The explanation of the method for identifying similarity of alert situation in the foregoing embodiment is also applicable to the apparatus for identifying similarity of alert situation in this embodiment, and will not be repeated here.

The alarm situation similarity recognition device of the embodiment of the present application extracts the current alarm situation characteristics by analyzing the current alarm information, and further, obtains all historical alarm records that meet the preset matching conditions according to the current alarm situation characteristics. Further, the similarity calculation is performed on the current alarm information and each historical alarm record, and the target historical alarm records that are similar to the current alarm information are filtered according to the calculation result. As a result, by obtaining historical alarm records similar to the current alarm information during the alarm reception process, automatic identification of similar alarm conditions is realized, the waste of police resources caused by repeated processing is avoided, and the work efficiency and discrimination accuracy of the policemen are improved. At the same time, the judgment is based on the text similarity, which improves the accuracy of similar warnings.

In order to implement the above-mentioned embodiments, this application also proposes a computer device, including a processor and a memory; wherein the processor reads the executable program code stored in the memory to run a program corresponding to the executable program code for use in The method for identifying similarity of alert situation as described in any of the foregoing embodiments is realized.

In order to implement the above-mentioned embodiments, this application also proposes a computer program product, which when the instructions in the computer program product are executed by a processor, realizes the alert similarity recognition method as described in any of the foregoing embodiments.

In order to implement the foregoing embodiments, the present application also proposes a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for identifying the similarity of the alert situation as described in any of the foregoing embodiments is implemented.

In the description of this specification, descriptions with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean specific features described in conjunction with the embodiment or example , The structure, materials, or characteristics are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples and the features of the different embodiments or examples described in this specification without contradicting each other.

In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless specifically defined otherwise.

Any process or method description in the flowchart or described in other ways herein can be understood as a module, segment or part of code that includes one or more executable instructions for implementing specific logical functions or steps of the process , And the scope of the preferred embodiments of the present application includes additional implementations, which may not be in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. This should It is understood by those skilled in the art to which the embodiments of the present application belong.

The logic and/or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logic functions, and can be embodied in any computer-readable medium, For use by instruction execution systems, devices, or equipment (such as computer-based systems, systems including processors, or other systems that can fetch and execute instructions from instruction execution systems, devices, or equipment), or combine these instruction execution systems, devices Or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, device, or device or in combination with these instruction execution systems, devices, or devices. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) with one or more wiring, portable computer disk cases (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable and editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because it can be used, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable media if necessary. The program is processed in a manner to obtain the program electronically, and then stored in the computer memory.

It should be understood that each part of this application can be implemented by hardware, software, firmware, or a combination thereof. In the foregoing embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if it is implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: Discrete logic circuits, application-specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

A person of ordinary skill in the art can understand that all or part of the steps carried in the method of the foregoing embodiments can be implemented by a program instructing relevant hardware to complete. The program can be stored in a computer-readable storage medium. When executed, it includes one of the steps of the method embodiment or a combination thereof.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

The aforementioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present application. A person of ordinary skill in the art can comment on the foregoing within the scope of the present application. The embodiment undergoes changes, modifications, substitutions, and modifications.

Claims

A method for identifying similarity of alert situation, which is characterized in that it comprises the following steps:

Analyze current alarm information to extract current alarm characteristics;

Acquiring all historical alarm records that meet preset matching conditions according to the current alarm characteristics;

The similarity calculation is performed on the current alarm information and each of the historical alarm records, and the target historical alarm records similar to the current alarm information are filtered according to the calculation result.
The method of claim 1, wherein when the current alarm feature is an alarm number, acquiring all historical alarm records that meet a preset matching condition according to the current alarm feature includes:

Acquiring the first candidate historical alarm record within a preset time period corresponding to the alarm number;

Query the pre-stored alarm state respectively corresponding to the first candidate historical alarm record, and obtain the unclosed first target historical alarm record from the first candidate historical alarm record according to the alarm state.
The method according to claim 1 or 2, wherein when the current alarm feature is an alarm address, the acquiring all historical alarm records that meet a preset matching condition according to the current alarm feature includes:

Acquiring a second candidate historical alarm record within a preset range of the alarm address;

Acquire the second target historical alarm record within a preset time period from the second candidate historical alarm record.
The method according to any one of claims 1 to 3, wherein when the current alarm feature is an alarm type, the acquisition of all historical alarm records that meet a preset matching condition according to the current alarm feature, include:

Acquiring a third candidate historical alarm record within a preset time period corresponding to the type of alarm situation;

Obtain a third target historical alarm record carrying a similar mark from the third candidate historical alarm record.
The method according to any one of claims 1 to 4, wherein the calculating the similarity between the current alarm information and each of the historical alarm records comprises:

Extracting the first high-frequency word in the current alarm information and the second high-frequency word in each of the historical alarm records, and calculating the distance between the first high-frequency word and the second high-frequency word;

Calculating the similarity of the semantic relationship between the current alarm information and each of the historical alarm records;

According to the distance between the first high-frequency word and the second high-frequency word and the semantic relationship similarity, the similarity between the current alarm information and each of the historical alarm records is calculated.
An alarm situation similarity recognition device, which is characterized in that it comprises:

The extraction module is used to analyze the current alarm information and extract the current alarm characteristics;

An obtaining module, configured to obtain all historical alarm records that meet preset matching conditions according to the current alarm characteristics;

The screening module is used to calculate the similarity between the current alarm information and each of the historical alarm records, and filter the target historical alarm records similar to the current alarm information according to the calculation result.
7. The device of claim 6, wherein when the current alarm feature is an alarm number, the acquiring module is specifically configured to:

Acquiring the first candidate historical alarm record within a preset time period corresponding to the alarm number;

Query the pre-stored alarm state respectively corresponding to the first candidate historical alarm record, and obtain the unclosed first target historical alarm record from the first candidate historical alarm record according to the alarm state.
The device according to claim 6 or 7, wherein when the current alarm feature is an alarm address, the acquiring module is specifically configured to:

Acquiring a second candidate historical alarm record within a preset range of the alarm address;

Acquire the second target historical alarm record within a preset time period from the second candidate historical alarm record.
8. The device according to any one of claims 6-8, wherein when the current alarm feature is an alarm type, the acquiring module is specifically configured to:

Acquiring a third candidate historical alarm record within a preset time period corresponding to the type of alarm situation;

Obtain a third target historical alarm record carrying a similar mark from the third candidate historical alarm record.
The device according to any one of claims 6-9, wherein the screening module is specifically configured to:

Extracting the first high-frequency word in the current alarm information and the second high-frequency word in each of the historical alarm records, and calculating the distance between the first high-frequency word and the second high-frequency word;

Calculating the similarity of the semantic relationship between the current alarm information and each of the historical alarm records;

According to the distance between the first high-frequency word and the second high-frequency word and the semantic relationship similarity, the similarity between the current alarm information and each of the historical alarm records is calculated.
A computer device characterized by comprising a processor and a memory;

Wherein, the processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to realize the alarm according to any one of claims 1-5. Recognition method of emotion similarity.
A computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to realize the method for identifying similarity of police situation according to any one of claims 1-5.