A method, device, medium and electronic device for deduplication identification of urban cases

Abstract

The embodiments of the present application disclose a method, device, medium and electronic device for deduplication identification of urban cases. The method includes: obtaining the current content identification result of the current urban case; the content identification result is obtained based on the identification of at least one information dimension by intelligent identification technology; reading the historical content identification results from the similarity reference library for comparison, if there is a target content identification result with a similarity greater than a set threshold with the current content identification result, then determining that the current urban case and the target urban case corresponding to the target content identification result are duplicate cases; merging the current urban case and the target urban case. This technical solution can solve the defect of the smart urban management platform in the prior art that relies on manual deduplication, realize the automated operation mechanism of case content identification and case deduplication process, improve the efficiency of daily case handling in the city, and thus improve the operation efficiency of the city.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of de-duplication identification of urban cases, and in particular to a method, device, medium and electronic equipment for de-duplication identification of urban cases. Background Art

[0002] With the continuous development of society and the rapid expansion of cities, daily urban management is facing tremendous pressure, and the number of daily urban cases is also increasing day by day.

[0003] Intelligent urban management has emerged as a result of demand. It is not only a need for the development of modern society, but also a need for the innovation of traditional urban management methods. The smart city management system is a tool and means of intelligent urban management. It uses advanced technologies such as image algorithms, data mining, and scheduling algorithms to improve the efficiency of solving urban management problems. With the construction of smart urban management in large, medium and small cities, a large number of urban management cases have been quickly acquired on the smart urban management platform, but the continuous repetition and accumulation of a large number of cases have increased the difficulty of urban management.

[0004] However, case identification and deduplication are mostly done manually by personnel under the platform, which has the disadvantages of poor deduplication screening accuracy, high labor costs, small coverage, unclear rule formulation, and non-standard content comparison standards. It greatly affects the efficiency of handling daily cases in cities and urgently needs to be improved. Summary of the invention

[0005] The embodiments of the present application provide a method, device, medium and electronic device for de-duplication identification of urban cases, so as to realize intelligent de-duplication identification of urban cases and improve the efficiency of urban case processing.

[0006] In a first aspect, an embodiment of the present application provides a method for de-duplication identification of urban cases, the method comprising:

[0007] Obtaining a current content recognition result of a case in a current city; the content recognition result is obtained based on recognition of at least one information dimension using intelligent recognition technology;

[0008] Read historical content recognition results from a similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, determine that the current city case and the target city case corresponding to the target content recognition result are duplicate cases;

[0009] The current city cases and the target city cases are merged for processing.

[0010] In a second aspect, an embodiment of the present application provides a device for deduplication identification of urban cases, the device comprising:

[0011] The recognition result acquisition module is used to obtain the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology;

[0012] The recognition result comparison module is used to read the historical content recognition results from the similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case corresponding to the target content recognition result are determined to be duplicate cases;

[0013] The city case merging module is used to merge the current city case and the target city case.

[0014] On the third aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method for de-duplication identification of urban cases as described in the embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for de-duplication identification of urban cases as described in the embodiment of the present application is implemented.

[0016] The embodiments of the present application provide a method, device, medium and electronic device for deduplication and identification of urban cases. By obtaining the current content identification result of the current urban case, the historical content identification result is read from a similar reference library for comparison. If there is a target content identification result whose similarity with the current content identification result is greater than a set threshold, the current urban case and the target urban case are merged for processing. This solves the defect of the smart urban management platform in the prior art that relies on manual deduplication, realizes the automated operation mechanism of case content identification and case deduplication process, improves the efficiency of daily case handling in the city, thereby improving the operation efficiency of the city, and provides a new idea for deduplication and identification of urban cases. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for deduplication identification of urban cases provided in an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of a duplicate removal and identification process of urban cases provided in an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a duplicate removal and identification process of urban cases provided in an embodiment of the present application;

[0020] Figure 4 It is a structural schematic diagram of a device for deduplication identification of urban cases provided in an embodiment of the present application;

[0021] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0023] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0024] Embodiment 1

[0025] Figure 1 It is a flow chart of the method for de-duplication identification of urban cases provided in the first embodiment of the present application. This embodiment can be applied to the situation where a large number of urban cases are accumulated and repeated to deduplicate urban cases. The method can be executed by the device for de-duplication identification of urban cases provided in the embodiment of the present application. The device can be implemented by software and / or hardware, and can be integrated into electronic devices such as smart terminals for urban case management.

[0026] like Figure 1 As shown in the figure, the de-duplication identification methods for urban cases include:

[0027] S110, obtaining the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology.

[0028] Urban cases are cases related to urban management, and may include cases related to motor vehicles, shared bicycles, small advertisements, trash cans, electric motorcycles, road fences, drains, and manhole covers, but are not limited to these, and this application does not make specific limitations here. In the urban case management system, urban case content is pre-stored. To obtain the current content recognition result of the current urban case, it is necessary to first receive the current urban case and obtain the identification information of the current urban case. The identification information may be determined based on the result of the urban case information input, and may be at least one of text information, image information, and video information. Among them, the identification information has at least one information dimension, and the information dimension may include the case title, occurrence time, occurrence location, content description, and attachments. In other words, the identification information includes at least one of the case title, occurrence time, occurrence location, content description, and attachments.

[0029] In this embodiment, the identification information may be record information, statistical information, etc. of urban management events involved in the urban case management system, or may be Internet public opinion data information on information platforms such as WeChat and Weibo obtained by the urban case management system. On the one hand, since the information data contained in Internet data has a large dimension, the corresponding public opinion data may indicate urban events that have occurred or will occur. On the other hand, since Internet data is highly real-time, it can reflect the corresponding urban events that have occurred at the first time. Therefore, Internet public opinion data information can also be used as identification information. Preferably, when obtaining Internet public opinion data information, web crawler technology can be used to extract Internet public opinion data from wired networks and / or wireless networks at a preset frequency.

[0030] After obtaining the identification information of the current city case, an intelligent identification method is used to perform keyword recognition, image recognition, and video information recognition on the identification information. Finally, the obtained identification result is determined as the content recognition result of the current city case, thereby completing the acquisition of the current content recognition result of the current city case.

[0031] S120, reading historical content recognition results from a similar reference library for comparison, if there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, determining that the current city case and the target city case corresponding to the target content recognition result are duplicate cases.

[0032] The similar reference library stores the content recognition results of historical city cases. Historical city cases can be processed in the form of a queue. It is understandable that the first historical city case can be directly stored in the library after the content recognition result is recognized. Starting from the second historical city case, after obtaining the content recognition result, it is necessary to compare it with the content recognition results of historical city cases in the similar reference library to determine whether the case currently being recognized is repeated with other cases. Among them, the historical content recognition results may partially overlap with the current content recognition results.

[0033] In the case where the historical content recognition results partially overlap with the current content recognition results, the two can be compared to obtain the similarity between the historical content recognition results and the current content recognition results. Based on the similarity between the two and the set threshold, it is determined whether the current city case is a duplicate case. When the similarity is greater than the threshold, the corresponding historical content recognition result is the target content recognition result.

[0034] Specifically, if there is no target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current content recognition result is stored in the similar reference library. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case corresponding to the target content recognition result are determined to be duplicate cases.

[0035] S130. Combine the current city case and the target city case.

[0036] If it is determined that the current city case and the target city case corresponding to the target content recognition result are duplicate events, the current city event and the target city event are merged. Optionally, the information resources of the current city case and the target city case can be integrated to obtain a merged case, and the current city case and the target city case can be deleted. Alternatively, the current city case can be directly deleted and the next content recognition result of the next city case can be obtained. The specific method of handling duplicate cases is not specifically limited in this embodiment.

[0037] The technical solution provided in this embodiment obtains the current content recognition result of the current city case, reads the historical content recognition result from the similar reference library for comparison, and if there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case are merged for processing. This solves the defect of the smart urban management platform in the prior art that relies on manual deduplication, realizes the automated operation mechanism of case content recognition and case deduplication process, improves the efficiency of daily case handling in the city, thereby improving the operation efficiency of the city, and provides a new idea for deduplication and identification of urban cases.

[0038] Embodiment 2

[0039] Figure 2 This is a schematic diagram of the de-duplication identification process of the city case in the second embodiment of the present invention. The second embodiment is further optimized on the basis of the first embodiment. The specific optimization is: a specific introduction on how to obtain the current content identification result of the current city case is given.

[0040] For details of the contents not described in detail in this embodiment, please refer to Embodiment 1. Figure 2 As shown, the method comprises the following steps:

[0041] S210. Obtain identification information of the current city case, where the identification information includes at least one of the case title, occurrence time, occurrence location, content description, and attachments.

[0042] The case title, time of occurrence, location of occurrence, content description, and attachments represent multiple dimensions of identification information. Among them, the case title and location of occurrence are necessary information and are indispensable; and the attachments specifically include pictures, videos and other information. For example, the identification information can be that at 15:28 on December 28, 2020, the shared bicycles were parked in chaos at the intersection of Lumo Road and Luoyu Road; or at 12:50 on December 24, 2020, a car driver drove under the influence of alcohol in the middle section of Dazhi Road and crashed into the fence.

[0043] Urban cases are cases related to urban management and may include motor vehicles, shared bicycles, small advertisements, trash cans, electric motorcycles, road fences, drains and manhole covers, but are not limited to these. This application does not make specific limitations here.

[0044] S220: Using an intelligent recognition method to identify the identification information, perform keyword recognition, image recognition, and video information recognition.

[0045] After obtaining the identification information of the current city case, an intelligent recognition method is used to perform keyword recognition, image recognition, and video information recognition.

[0046] Optionally, keyword recognition can be performed on the identification information. Specifically, it is necessary to obtain the text information to be recognized, segment the text information to obtain a vocabulary set; calculate the frequency of each word in the vocabulary set, split the vocabulary set to obtain a sub-vocabulary set and the association between each word in the sub-vocabulary set, and obtain a total vocabulary table with characteristic values ​​based on the frequency of each word in the sub-vocabulary set and the association between each word, wherein the characteristic value reflects the criticality of the word in the text information; arrange the words in the total vocabulary table according to the characteristic value, and set the words whose characteristic value exceeds the preset characteristic threshold as keywords.

[0047] Furthermore, OCR (Optical Character Recognition) technology can be used to perform image recognition on the picture to obtain the character information contained in the picture, or feature vectors can be extracted from the picture, and the case information contained in the picture can be identified based on the extracted feature vectors, where the case information can include at least one of the case title, occurrence time, and occurrence location.

[0048] S230: Determine the obtained recognition result as the content recognition result of the current city case.

[0049] After using intelligent recognition methods to identify the information, perform keyword recognition, image recognition, and video information recognition, the obtained recognition results are determined as the content recognition results of the current city case.

[0050] S240, reading historical content recognition results from a similar reference library for comparison, if there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, determining that the current city case and the target city case corresponding to the target content recognition result are duplicate cases.

[0051] S250. Combine the current city case and the target city case.

[0052] The technical solution of this embodiment provides a specific introduction to the current content recognition result of the current city case, obtains the recognition information of the current city case, and performs keyword recognition, image recognition and video information recognition on it to obtain the recognition result, and determines the content recognition result of the current city case. The solution of this embodiment provides a variety of intelligent recognition solutions to determine the content recognition result of the current city case, improves the accuracy of content recognition, and provides a guarantee for the accuracy of subsequent comparison.

[0053] Embodiment 3

[0054] Figure 3 Schematic diagram of the de-duplication identification process of city cases in the third embodiment of the present invention. The third embodiment is further optimized on the basis of the first and second embodiments. The specific optimization is: a specific introduction on how to merge the current city case and the target city case is given.

[0055] Among them, the contents not described in detail in this embodiment are detailed in Embodiment 1 and Embodiment 2. Figure 3 As shown, the method comprises the following steps:

[0056] S310, obtaining the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology.

[0057] S320, reading historical content recognition results from a similar reference library for comparison, if there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, determining that the current city case and the target city case corresponding to the target content recognition result are duplicate cases.

[0058] S330, integrating information resources of the current city case and the target city case to obtain a merged case, and deleting the current city case and the target city case.

[0059] If it is determined that the current city case and the target city case corresponding to the target content recognition result are duplicate events, the current city event and the target city event are merged. Specifically, the information resources of the current city case and the target city case can be integrated to obtain a merged case, and the current city case and the target city case are deleted.

[0060] Furthermore, the target content recognition result of the case in the target city can be used as a benchmark to determine whether the current content recognition result has additional information that is not included in the target content recognition result; if so, the additional information is recorded in the target content recognition result, the target content recognition result obtained after recording is stored in the similar reference library, and the target content recognition result before recording in the similar reference library is deleted. If not, the next content recognition result of the case in the next city is obtained, and the current content recognition result is deleted.

[0061] The technical solution of this embodiment provides a specific introduction to the merging of the current city case and the target city case. When it is determined that the target city case is a duplicate event, the information resources of the current city case and the target city case are integrated, and the current city case and the target city case are deleted. If there is additional information, the additional information is added to the target content recognition result. If there is no additional information, the next content recognition result of the next city case is obtained, and the next city case recognition and deduplication is started. The solution of this embodiment can improve the city case information in the city case management system and the similar reference library, realize fully intelligent multi-case deduplication, and reduce the duplication rate of city cases.

[0062] Embodiment 4

[0063] Figure 4 It is a structural schematic diagram of the deduplication identification device for urban cases provided in Example 4 of the present application. The device is suitable for executing the deduplication identification method for urban cases provided in the embodiment of the present invention, which can realize intelligent case deduplication and improve the efficiency of urban case handling.

[0064] like Figure 4 As shown, the device includes a recognition result acquisition module 410, a recognition result comparison module 420 and a city case merging module 430.

[0065] The recognition result acquisition module 410 is used to obtain the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology;

[0066] The recognition result comparison module 420 is used to read the historical content recognition results from the similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, it is determined that the current city case and the target city case corresponding to the target content recognition result are duplicate cases;

[0067] The city case merging module 430 is used to merge the current city case and the target city case.

[0068] The technical solution of this embodiment obtains the current content recognition result of the current city case, reads the historical content recognition result from the similar reference library for comparison, and if there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case are merged for processing. This solves the defect of the smart urban management platform in the prior art that relies on manual deduplication, realizes the automated operation mechanism of case content recognition and case deduplication process, improves the efficiency of daily case handling in the city, thereby improving the operation efficiency of the city, and provides a new idea for deduplication and identification of urban cases.

[0069] Preferably, the recognition result comparison module 420 is also used to store the current content recognition result in the similar reference library after reading the historical content recognition results from the similar reference library for comparison if there is no target content recognition result with a similarity with the current content recognition result greater than a set threshold.

[0070] Preferably, the information dimensions include case title, occurrence time, occurrence location, content description and attachments. Correspondingly, the recognition result acquisition module 410 includes: an information acquisition unit, an information identification unit and a result determination unit. Among them, the information acquisition unit is used to obtain the identification information of the current city case, and the identification information includes at least one of the case title, occurrence time, occurrence location, content description and attachments; the information identification unit is used to use an intelligent recognition method to perform keyword recognition, image recognition and video information recognition on the identification information; the result determination unit is used to determine the obtained recognition result as the content recognition result of the current city case. Among them, the recognition information is determined based on the city case information entry result.

[0071] Preferably, the city case merging module 430 is specifically used to: integrate information resources of the current city case and the target city case to obtain a merged case, and delete the current city case and the target city case.

[0072] Preferably, the city case merging module 430 is further used to: after merging the current city case and the target city case, use the target content recognition result of the target city case as a reference to determine whether the current content recognition result has additional information that is not included in the target content recognition result; if so, record the additional information in the target content recognition result; store the target content recognition result obtained after recording in a similar reference library, and delete the target content recognition result before recording in the similar reference library. If not, obtain the next content recognition result of the next city case and delete the current content recognition result.

[0073] The above-mentioned device can execute the deduplication identification method of urban cases provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0074] Embodiment 5

[0075] The present application also provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to perform a method for de-duplication identification of urban cases when executed by a computer processor, the method comprising:

[0076] Obtaining the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology;

[0077] Read the historical content recognition results from the similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case corresponding to the target content recognition result are determined to be duplicate cases;

[0078] The current city cases and the target city cases will be processed together.

[0079] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0080] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application, whose computer executable instructions are not limited to the de-duplication identification operation of urban cases as described above, can also execute related operations in the de-duplication identification method of urban cases provided in any embodiment of the present application.

[0081] Embodiment 6

[0082] An embodiment of the present application provides an electronic device, in which the device for deduplication identification of urban cases provided by the embodiment of the present application can be integrated. Figure 5 Schematic diagram of the structure of an electronic device provided in Embodiment 5 of the present application. Figure 5 As shown, this embodiment provides an electronic device 500, which includes: one or more processors 520; a storage device 510, which is used to store one or more programs. When the one or more programs are executed by the one or more processors 520, the one or more processors 520 implement the method for de-duplication identification of urban cases provided in the embodiment of the present application, and the method includes:

[0083] Obtaining the current content recognition result of the current city case; the content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology;

[0084] Read the historical content recognition results from the similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case corresponding to the target content recognition result are determined to be duplicate cases;

[0085] The current city cases and the target city cases will be processed together.

[0086] Of course, those skilled in the art will appreciate that the processor 520 also implements the technical solution of the method for de-duplication identification of urban cases provided in any embodiment of the present application.

[0087] Figure 5 The electronic device 500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0088] like Figure 5 As shown, the electronic device 500 includes a processor 520, a storage device 510, an input device 530, and an output device 540; the number of the processor 520 in the electronic device can be one or more. Figure 5 A processor 520 is taken as an example; the processor 520, the storage device 510, the input device 530 and the output device 540 in the electronic device can be connected via a bus or other means. Figure 5 The connection via bus 550 is taken as an example.

[0089] The storage device 510, as a computer-readable storage medium, can be used to store software programs, computer executable programs and module units, such as program instructions corresponding to the de-duplication identification method for urban cases in the embodiment of the present application.

[0090] The storage device 510 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the storage device 510 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 510 may further include a memory remotely arranged relative to the processor 520, and these remote memories may be connected 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 combinations thereof.

[0091] The input device 530 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 540 may include electronic devices such as a display screen and a speaker.

[0092] The electronic device provided in the embodiment of the present application can achieve the purpose of improving the de-duplication identification speed and processing effect of urban cases.

[0093] The deduplication identification device, storage medium, and electronic device provided in the above embodiments can execute the deduplication identification method for urban cases provided in any embodiment of the present application, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not fully described in the above embodiments, please refer to the deduplication identification method for urban cases provided in any embodiment of the present application.

[0094] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for de-duplication identification of urban cases, characterized in that: The method is performed by a city case management system, and comprises: Obtaining the current content recognition result of the case in the current city; the current content recognition result is obtained based on the recognition of at least one information dimension using intelligent recognition technology; the information dimension includes the case title, occurrence time, occurrence location, content description and attachments; Read historical content recognition results from a similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, determine that the current city case and the target city case corresponding to the target content recognition result are duplicate cases; Merging the current city case and the target city case, including: integrating information resources of the current city case and the target city case to obtain a merged case, and deleting the current city case and the target city case; or directly deleting the current city case and continuing to obtain the next content recognition result of the next city case; Wherein, obtaining the current content recognition result of the current city case includes: Obtain identification information of the current city case, wherein the identification information includes at least one of the case title, occurrence time, occurrence location, content description, and attachments; Using intelligent recognition methods to identify keywords, images, and video information for the identification information; Determine the obtained recognition result as the content recognition result of the current city case; The keyword recognition is specifically performed as follows: obtaining text information to be recognized, segmenting the text information to obtain a vocabulary set; calculating the frequency of each word in the vocabulary set, splitting the vocabulary set to obtain a sub-vocabulary set and the association relationship between each word in the sub-vocabulary set; obtaining a total vocabulary table with characteristic values ​​according to the frequency of each word in the sub-vocabulary set and the association relationship between each word, arranging the words in the total vocabulary table according to the characteristic values, and setting the words whose characteristic values ​​exceed a preset characteristic threshold as keywords; the characteristic values ​​reflect the criticality of the words in the text information.

2. The method according to claim 1, characterized in that After reading the historical content recognition results from the similar reference library for comparison, the method further includes: If there is no target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current content recognition result is stored in a similar reference library.

3. The method according to claim 1, characterized in that The identification information is determined based on the city case information input results.

4. The method according to claim 1, characterized in that: After merging the current city case and the target city case, the method further includes: Taking the target content recognition result of the case in the target city as a benchmark, determining whether the current content recognition result has additional information that is not included in the target content recognition result; If yes, recording the additional information into the target content recognition result; The target content recognition result obtained after recording is stored in the similar reference library, and the target content recognition result before recording in the similar reference library is deleted.

5. The method according to claim 4, characterized in that After determining whether the current content recognition result has additional information that is not included in the target content recognition result, the method further includes: If not, the next content recognition result of the next city case is obtained, and the current content recognition result is deleted.

6. A device for de-duplication identification of urban cases, characterized in that: The device comprises: The recognition result acquisition module is used to obtain the current content recognition result of the current city case; the current content recognition result is obtained based on the recognition of at least one information dimension by intelligent recognition technology; the information dimension includes the case title, occurrence time, occurrence location, content description and attachments; The recognition result comparison module is used to read the historical content recognition results from the similar reference library for comparison. If there is a target content recognition result whose similarity with the current content recognition result is greater than a set threshold, the current city case and the target city case corresponding to the target content recognition result are determined to be duplicate cases; A city case merging module, used for merging the current city case and the target city case; The city case merging module is specifically used to integrate the information resources of the current city case and the target city case to obtain the merged case, and delete the current city case and the target city case; or directly delete the current city case and continue to obtain the next content recognition result of the next city case; Wherein, the recognition result acquisition module includes: An information acquisition unit, used to acquire identification information of the current city case; the identification information includes at least one of the case title, occurrence time, occurrence location, content description and attachments; An information recognition unit, used to use an intelligent recognition method to perform keyword recognition, image recognition, and video information recognition on the recognition information; A result determination unit, used to determine the obtained recognition result as the content recognition result of the current city case; The keyword recognition is specifically performed as follows: obtaining text information to be recognized, segmenting the text information to obtain a vocabulary set; calculating the frequency of each word in the vocabulary set, splitting the vocabulary set to obtain a sub-vocabulary set and the association relationship between each word in the sub-vocabulary set; obtaining a total vocabulary table with characteristic values ​​according to the frequency of each word in the sub-vocabulary set and the association relationship between each word, arranging the words in the total vocabulary table according to the characteristic values, and setting the words whose characteristic values ​​exceed a preset characteristic threshold as keywords; the characteristic values ​​reflect the criticality of the words in the text information.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the method for de-duplication identification of urban cases as described in any one of claims 1-5.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the method for de-duplication identification of urban cases as described in any one of claims 1-5.

Images