Methods, systems, and computer-readable media for data processing

Abstract

The present disclosure provides a method, system and computer readable storage medium for data processing, relating to the technical field of data processing, the system comprising: an OCR system for obtaining data of multiple systems and performing OCR processing to obtain an OCR recognition result; a video monitoring system for analyzing monitoring videos obtained by real-time monitoring of the multiple systems to obtain semantic information represented by the monitoring videos; a natural language processing system for performing natural language processing on the OCR recognition result to obtain semantic information represented by data; an information processing system for judging the semantic information represented by the monitoring videos and the semantic information represented by the data; and when the semantic information represented by the monitoring videos matches the semantic information represented by the data, outputting the semantic information represented by the data to an information base.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and in particular, to a data processing method, system and computer readable storage medium. BACKGROUND

[0002] At present, an optical character recognition technology (OCR) is used to process an interface of a patrol inspection system of an oil and gas station to obtain a number of patrollers, and data obtained by using the OCR technology is inaccurate and needs to be improved. SUMMARY

[0003] To solve the problem of inaccurate data processed by the OCR, the present disclosure provides a data processing system, which comprises:

[0004] an OCR system, configured to acquire data of a plurality of systems and perform OCR processing to obtain an OCR recognition result;

[0005] a video monitoring system, configured to analyze a monitoring video obtained by monitoring the plurality of systems in real time to obtain semantic information represented by the monitoring video;

[0006] a natural language processing system, configured to perform natural language processing on the OCR recognition result to obtain semantic information represented by data;

[0007] an information processing system, configured to judge the semantic information represented by the monitoring video and the semantic information represented by the data, and output the semantic information represented by the data to an information base when the semantic information represented by the monitoring video matches the semantic information represented by the data.

[0008] In some embodiments, the information processing system is further configured to:

[0009] output the semantic information represented by the monitoring video to the information base when the semantic information represented by the monitoring video does not match the semantic information represented by the data.

[0010] In some embodiments, when the semantic information represented by the monitoring video matches the semantic information represented by the data, the information processing system is configured to output the semantic information represented by the data to the information base, including:

[0011] after judging that the semantic information represented by the monitoring video matches the semantic information represented by the data, customizing the semantic information represented by the data, associating the customized semantic information represented by the data with each other, and outputting the associated semantic information represented by the data to the information base for storage.

[0012] In some embodiments, the obtaining data of a plurality of systems and performing OCR processing to obtain an OCR recognition result comprises:

[0013] The data of the plurality of systems is cleaned and preprocessed;

[0014] The cleaned and preprocessed data is subjected to character positioning and recognition to obtain the OCR recognition result.

[0015] In some embodiments, the mutually associated semantic information of the customized data representation comprises:

[0016] The semantic information of the customized data representation is subjected to recognition cutting;

[0017] According to the recognition cutting result, the relevant semantic information of the data representation is mutually associated;

[0018] The system further comprises:

[0019] A display system for adjusting the distance between the associated semantic information of the data representation and presenting in vertical association and / or horizontal association.

[0020] In some embodiments, the relevant semantic information of the data representation comprises first data representation semantic information and second data representation semantic information;

[0021] When the first data representation semantic information and the second data representation semantic information are presented in an up-down form, the association is vertical association;

[0022] When the first data representation semantic information and the second data representation semantic information are presented in a left-right form, the association is horizontal association.

[0023] In some embodiments, the system further comprises:

[0024] An integration system for: identifying the associated semantic information of the data representation before outputting the associated semantic information of the data representation to an information library for storage, determining the corresponding relationship thereof; according to the corresponding relationship, performing data conversion and integration on the associated semantic information of the data representation.

[0025] In some embodiments, the system further comprises:

[0026] A model training system for performing model training on the associated semantic information of the data representation stored in the information library after outputting the associated semantic information of the data representation to the information library for storage.

[0027] The disclosure provides a data processing method, which comprises:

[0028] S1: obtaining data of multiple systems and performing OCR processing to obtain an OCR recognition result;

[0029] S2: analyzing a monitoring video obtained by real-time monitoring of the multiple systems to obtain semantic information represented by the monitoring video;

[0030] S3: performing natural language processing on the OCR recognition result to obtain semantic information represented by data and for display;

[0031] S4: judging the semantic information represented by the monitoring video and the semantic information represented by the data;

[0032] S5: when the semantic information represented by the monitoring video matches the semantic information represented by the data, outputting the semantic information represented by the data to an information base.

[0033] The disclosure provides a computer-readable storage medium storing computer executable instructions for executing the above-mentioned data processing method.

[0034] The disclosure provides a data processing method, system and computer-readable storage medium, relating to the technical field of data processing, the system comprising: an OCR system for obtaining data of multiple systems and performing OCR processing to obtain an OCR recognition result; a video monitoring system for analyzing a monitoring video obtained by real-time monitoring of the multiple systems to obtain semantic information represented by the monitoring video; a natural language processing system for performing natural language processing on the OCR recognition result to obtain semantic information represented by data; an information processing system for judging the semantic information represented by the monitoring video and the semantic information represented by the data; and when the semantic information represented by the monitoring video matches the semantic information represented by the data, outputting the semantic information represented by the data to an information base. The disclosure compares the semantic information obtained by using OCR processing and natural language processing on data of multiple systems with the semantic information obtained by analyzing a monitoring video obtained by real-time monitoring of the multiple systems, and when the semantic information represented by the monitoring video is consistent with the semantic information represented by the data, outputs the semantic information represented by the data, thereby improving the accuracy of OCR recognition and effectively solving the problem of inaccurate recognition results obtained by using only OCR to process data.

[0035] The above description is only a summary of the technical solutions of the present disclosure. In order to enable a clearer understanding of the technical means of the present disclosure, the contents of the specification can be implemented, and in order to enable the above and other purposes, features and advantages of the present disclosure to be more apparent and easy to understand, the specific embodiments of the present disclosure are described below. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the related art, the drawings needed to be used in the embodiments or related art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present disclosure, and those skilled in the art can also obtain other drawings according to these drawings without creative labor. It should be noted that the proportions in the drawings are only for illustration and do not represent the actual proportions.

[0037] Figure 1 The flowchart schematically shows a specific application of the embodiments of the present disclosure;

[0038] Figure 2 The schematic diagram schematically shows a specific application of the embodiments of the present disclosure;

[0039] Figure 3 The present disclosure shows a presentation form of information output to an information library;

[0040] Figure 4 The present disclosure shows another presentation form of information output to an information library;

[0041] Figure 5 The method flowchart of data processing provided by the present disclosure is schematically shown. DETAILED DESCRIPTION

[0042] In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be described clearly and completely in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present disclosure.

[0043] The present disclosure provides a data processing system, which comprises:

[0044] An OCR system is used to obtain data of multiple systems and perform OCR processing to obtain an OCR recognition result.

[0045] Exemplarily, the OCR system respectively performs optical character recognition (OCR) processing on the data of multiple systems, the OCR processing including data cleaning, data preprocessing, character positioning, and character recognition; wherein the main purpose of cleaning and preprocessing is to shield the useless patterns, page blocks, patterns, and other contents in the data that may be misrecognized as characters, so as to improve the accuracy and continuity of subsequent processing steps such as character positioning and recognition, natural language processing, etc.; the OCR system respectively performs character positioning and character recognition on the cleaned and preprocessed data to extract the characters in the data, specifically, the character positioning is to output the character position box in the data, and the character recognition is to output the specific character content in the image slice of the character position box.

[0046] For example, the system provided by the present disclosure is mounted on an AI oil and gas station digital platform or an AI oil depot digital platform, and the data of the sensor system of the oil depot, the valve control system of the oil depot, the attendance system of the oil and gas station, the personnel positioning system of the oil and gas station, the inspection system of the oil and gas station, etc. are collected, the data including images, videos, charts, etc. are transmitted to the Internet of Things platform of the oil and gas station or the oil depot, the Internet of Things platform receives the data and performs monitoring, and then the user can view the image or video data of the empty capacity, total capacity, and temperature of each oil tank, the image or video data of the combustible gas alarm, the image data of the opening or closing state of each oil depot valve, the chart data of the number of people on duty, the image, video, or chart data of the number of inspection personnel, the image or video data of personnel positioning, etc. on the Internet of Things platform in real time. Figure 1 The flowchart shows the specific application of the embodiment of the present disclosure. The sensor system of the oil depot, the valve control system of the oil depot, the attendance system of the oil and gas station, the personnel positioning system of the oil and gas station, the inspection system of the oil and gas station, etc. collect data, the data including images, videos, charts, etc. are transmitted to the Internet of Things platform of the oil and gas station or the oil depot, the Internet of Things platform receives the data and performs monitoring, and then the user can view the image or video data of the empty capacity, total capacity, and temperature of each oil tank, the image or video data of the combustible gas alarm, the image data of the opening or closing state of each oil depot valve, the chart data of the number of people on duty, the image, video, or chart data of the number of inspection personnel, the image or video data of personnel positioning, etc. on the Internet of Things platform in real time.

[0047] The OCR system performs OCR processing on all image, video, and chart data of the Internet of Things platform to obtain recognition results from the image, video, and chart data of multiple systems, for example, the character recognition result of "G1 oil tank diesel D1 oil tank gasoline 92# total capacity 300 tons total capacity 200 tons empty capacity 100 tons empty capacity 120 tons liquid level meter" from the image or video data transmitted by the liquid level meter, the character recognition result of "temperature 16℃ temperature 17℃" from the image or video data transmitted by the oil tank temperature transmitter, the character recognition result of "valve 1 closed, valve 2 closed" from the image data transmitted by the oil depot valve control system, the character recognition result of "number of people on duty" and "certain employee on duty" from the video or chart data transmitted by the attendance system, the character recognition result of "number of inspection personnel" and "certain employee on inspection" from the image, video, or chart data transmitted by the inspection system, and the character recognition result of "determined position of personnel" from the image or video data transmitted by the personnel positioning system.

[0048] A video monitoring system is used to analyze the monitoring video obtained by real-time monitoring of multiple systems to obtain semantic information representing the monitoring video.

[0049] Exemplarily, the monitoring video obtained by real-time monitoring of the device end of multiple systems is analyzed to obtain semantic information representing the monitoring video. In the system of the present disclosure, the device end of multiple systems is, for example, the liquid level meter of a sensor system, the gas sensor of a sensor system, and each valve of an oil depot valve control system. Take the liquid level meter as an example to describe the technical solution: for example, as shown in Figure 2 A monitoring device is built around the device end liquid level meter of the sensor system to monitor the display screen of the liquid level meter in real time. The video monitoring system analyzes the monitoring video obtained by the monitoring device to obtain the semantic information “G1 oil tank total capacity of diesel oil 300 tons, empty capacity 100 tons” and “D1 oil tank total capacity of 92# gasoline 200 tons, empty capacity 120 tons”.

[0050] A natural language processing system is used to perform natural language processing on the OCR recognition result to obtain semantic information representing the data.

[0051] Exemplarily, the OCR recognition result is processed by using natural language processing (Neuro-Linguistic Programming, NLP) to obtain semantic information representing the data, and the semantic information representing the data is output to the information processing system. For example, the key words and semantic information in the recognition result are extracted by using Word2Vec or BERT method, and then syntax analysis, entity recognition and relationship extraction operations are performed to obtain semantic information representing the data, so that the associated information can be better extracted from the recognition result for association.

[0052] For example, the text recognition result of "G1 oil tank diesel D1 oil tank gasoline 92# total capacity 300 tons total capacity 200 tons empty capacity 100 tons empty capacity 120 tons liquid level meter" is obtained from the image or video data transmitted from the liquid level meter, the text recognition result of "temperature 16℃ temperature 17℃" is obtained from the image or video data transmitted from the oil tank temperature transmitter; the text recognition result of "valve 1 closed, valve 2 closed" is obtained from the image data transmitted from the oil depot valve control system, the text recognition result of "attendance number" and "attendance of a certain employee" is obtained from the video or chart data transmitted from the attendance system, the text recognition result of "patrol number" and "a certain employee is on patrol" is obtained from the image, video or chart data transmitted from the patrol system, and the text recognition result of "determined position of personnel" is obtained from the image or video data transmitted from the personnel positioning system. The information of the core characters is obtained by NLP processing, such as the semantic information of G1, diesel, total capacity 300 tons, empty capacity 100 tons, temperature 16℃, attendance number, 6 people, personnel positioning, correct position, patrol number, 3 people, and all valves are closed.

[0053] The information processing system is configured to judge the semantic information represented by the monitoring video and the semantic information represented by the data, and output the semantic information represented by the data to the information base when the semantic information represented by the monitoring video matches the semantic information represented by the data.

[0054] For example, when the data processing of the sensor system obtains the semantic information represented by the data of "G1, diesel, total capacity 300 tons, empty capacity 100 tons", which matches the semantic information represented by the monitoring video of "G1 oil tank diesel total capacity 300 tons empty capacity 100 tons" obtained in real time, the information processing system outputs the semantic information represented by the data to the information base for storage, specifically, to the AI oil and gas station digital platform information base or the AI oil depot digital platform information base carried by the system provided by the present disclosure, so that the AI oil and gas station digital platform or the AI oil depot digital platform displays the semantic information represented by the data, facilitating the user to view in the digital platform.

[0055] The information processing system provided in the present disclosure compares the semantic information obtained by adopting OCR processing and natural language processing on the data of multiple systems with the semantic information obtained by analyzing the monitoring video monitored by the multiple systems in real time, and outputs the semantic information represented by the data when the semantic information represented by the monitoring video is consistent with the semantic information represented by the data, thereby improving the accuracy of OCR recognition and effectively solving the problem that the recognition result obtained by only adopting OCR to process the data is inaccurate.

[0056] In some embodiments, the information processing system is further configured to:

[0057] When the semantic information represented by the monitoring video does not match the semantic information represented by the data, the semantic information represented by the monitoring video is output to the information base.

[0058] For example, when the semantic information represented by the monitoring video does not match the semantic information represented by the data, it indicates that the semantic information obtained after the OCR processing and the natural language processing is inaccurate, and therefore the information processing system outputs the semantic information represented by the monitoring video obtained in real time to the information base.

[0059] In some embodiments, when the semantic information represented by the monitoring video matches the semantic information represented by the data, the method for outputting the semantic information represented by the data to the information base comprises:

[0060] When it is determined that the semantic information represented by the monitoring video matches the semantic information represented by the data, the semantic information represented by the data is customized, the customized semantic information represented by the data is associated with each other, and the associated semantic information represented by the data is output to the information base for storage.

[0061] For example, the customization is to define part or all of the semantic information represented by the data in multiple systems according to user needs.

[0062] For example, the data processing of multiple systems obtains the semantic information represented by the data such as "G1, diesel, total capacity 300 tons, empty capacity 100 tons, temperature 16°C, number of attendants, 6 people, personnel positioning, correct position, number of inspectors, 3 people, all valves are closed", and if the user needs to check whether the number of attendants, personnel positioning and number of inspectors are normal, the information processing system customizes part of the semantic information represented by the data in the semantic information represented by the data, i.e. "number of attendants, 6 people, personnel positioning, correct position, number of inspectors, 3 people", and defines it as "number of attendants, normal, personnel positioning, normal, intelligent inspection, normal". The associated information in the semantic information is associated, for example, "number of attendants" and "normal" are associated, "personnel positioning" and "normal" are associated, and "intelligent inspection" and "normal" are associated. The associated semantic information is output to the information base for storage. Figure 3 As shown in the figure, the semantic information is stored in the AI oil and gas station digital platform information base or the AI oil depot digital platform information base carried by the system provided by the present disclosure, so that the AI oil and gas station digital platform or the AI oil depot digital platform displays the semantic information, and the user can conveniently and quickly check the information such as the remaining capacity of each tank in the oil and gas station and the oil depot, whether the personnel positioning is normal, whether the inspection is normal, and whether the valves of each oil depot are opened or closed in the AI oil and gas station digital platform or the AI oil depot digital platform, so that the user can respond as soon as possible.

[0063] If the user requirement is to output the semantic information of the oil tank level instrument and the oil tank temperature transmitter, the information processing system will first customize part of the semantic information of the data representation, such as "G1, diesel, total capacity 300 tons, empty capacity 100 tons, 16°C, D1, gasoline 92#, total capacity 200 tons, empty capacity 120 tons, 17°C", for example, name "diesel" and "gasoline 92#" as oil products, name "G1" and "D1" as tank names, and name "300 tons" and "200 tons" as total tank capacities; then associate the customized semantic information with each other, associate "diesel" and "gasoline 92#" with "oil products", and associate "G1" and "D1" with "tank names"; and finally output the associated semantic information to the information base for storage, and the semantic information stored in the information base is as shown in Figure 4 Specifically, the information base is an AI oil and gas station digital platform information base or an AI oil depot digital platform information base carried by the system provided by the present disclosure.

[0064] In some embodiments, the associated semantic information of the customized data representation includes:

[0065] The customized data representation of the semantic information is identified and cut;

[0066] According to the result of the identification and cutting, the relevant data representation of the semantic information is associated with each other;

[0067] Since the recognition results obtained by the OCR processing lack connection, the recognition results are scattered. Therefore, the present disclosure uses NLP to process the OCR recognition results to obtain data representation of semantic information, which can better associate the OCR recognition results; and according to the user requirement, the customized data representation of the semantic information is identified and cut, and the associated data representation of the semantic information is presented in the information base in the form as shown in Figure 4

[0068] The system further includes:

[0069] The display system is used to adjust the distance between the associated data representation of the semantic information, and present in vertical association and / or horizontal association.

[0070] In some embodiments, the relevant data representation of the semantic information includes first data representation of the semantic information and second data representation of the semantic information;

[0071] ​When the semantic information of the first data representation and the semantic information of the second data representation are presented in an up-down form, the association is a vertical association;

[0072] When the semantic information of the first data representation and the semantic information of the second data representation are presented in a left-right form, the association is a horizontal association.

[0073] The semantic information of the first data representation is name or content semantic information, and the semantic information of the second data representation is content or name semantic information; when the semantic information of the first data representation is name semantic information, the semantic information of the second data representation is content semantic information; when the semantic information of the first data representation is content semantic information, the semantic information of the second data representation is name semantic information.

[0074] Exemplarily, the semantic information of the first data representation and the semantic information of the second data representation are presented separately, specifically, as shown in Figure 4 the semantic information of the first data representation and the semantic information of the second data representation are presented separately in a table form. Further, as shown in Figure 3 a circle can be used as an auxiliary expression of the association, so that the user can intuitively view.

[0075] Specifically, the semantic information of the first data representation can be above or below the presentation form, or left or right of the presentation form. For example, the vertical association is as shown in Figure 3 the semantic information of the first data representation and the semantic information of the second data representation are presented separately in a table form. Further, as shown in Figure 4 the semantic information of the first data representation and the semantic information of the second data representation are presented separately in a table form. Further, as shown in

[0076] In some embodiments, the system further comprises:

[0077] The integration system is configured to: identify the associated data representation semantic information and determine the corresponding relationship thereof before outputting the associated data representation semantic information to the information base for storage; and perform data conversion and integration of the associated data representation semantic information according to the corresponding relationship.

[0078] Exemplarily, the conversion and integration can be realized by data structure analysis, data matching and transposition technologies, and the data representation semantic information after the integration of the system is stored in the information base. For example, as shown in Figure 4The semantic information of the data table shown is converted and integrated. First, the table header information of the table is identified to determine the data correspondence. Then, the semantic information is appropriately converted according to the correspondence, so that the more corresponding semantic information is associated with each other to achieve the purpose of unified structure. Then, the spacing between the semantic information is adjusted to achieve the purpose of unified format.

[0079] In some embodiments, the system further comprises:

[0080] A model training system is configured to train the associated semantic information of the data table after outputting the associated semantic information of the data table to the information library for storage.

[0081] Exemplarily, the semantic information of the data table in different presentation forms is continuously learned and recognized by the model, and the features of multiple presentation forms are considered by continuously training the model, so as to better recognize and analyze the information. For example, the features of the table style shown are trained by the model. Figure 4

[0082] The present disclosure provides a data processing method, as shown in Figure 5 The method comprises:

[0083] S1: obtaining data of multiple systems and performing OCR processing to obtain an OCR recognition result;

[0084] S2: analyzing a monitoring video obtained by real-time monitoring of the multiple systems to obtain semantic information represented by the monitoring video;

[0085] S3: performing natural language processing on the OCR recognition result to obtain semantic information represented by the data and for display;

[0086] S4: judging the semantic information represented by the monitoring video and the semantic information represented by the data;

[0087] S5: when the semantic information represented by the monitoring video matches the semantic information represented by the data, outputting the semantic information represented by the data to an information library.

[0088] In the present disclosure, the semantic information obtained by performing OCR processing and natural language processing on the data of multiple systems is compared with the semantic information obtained by analyzing the monitoring video obtained by real-time monitoring of the multiple systems. When the semantic information represented by the monitoring video is consistent with the semantic information represented by the data, the semantic information represented by the data is outputted. Thus, the accuracy of OCR recognition is improved, and the problem that the recognition result obtained by only performing OCR processing on the data is inaccurate is effectively solved.

[0089] ​The present disclosure provides a computer readable storage medium storing computer executable instructions for performing the method of data processing.

[0090] Embodiments of the present disclosure are described with reference to the flowchart illustrations and / or block diagrams of the methods, systems, and computer program products according to embodiments of the present disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal devices to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal devices, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0091] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal devices to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal devices to cause a series of operational steps to be performed on the computer or other programmable terminal devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal devices provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0093] Although preferred embodiments of the present disclosure have been described, those skilled in the art will be able to make additional modifications and variations to the described embodiments without departing from the inventive concepts disclosed in the present disclosure. Accordingly, the appended claims are intended to cover all such modifications and variations as falling within the scope of the present disclosure.

[0094] Finally, it needs to be pointed out that, in this article, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or terminal device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of other identical elements in the process, method, article or terminal device including the element.

[0095] The above detailed description of the method, system and computer readable storage medium for data processing provided by the present disclosure is provided, the principle and implementation mode of the present disclosure are described in this article by applying specific examples, the above example description is only for helping to understand the method of the present disclosure and its core idea; At the same time, for those skilled in the art, according to the idea of the present disclosure, the specific implementation mode and application range will be changed; In view of the above, the content of the specification should not be understood as a limitation of the present disclosure.

Claims

1. A system for data processing, wherein, The system comprises: An OCR system for obtaining data of multiple systems and performing OCR processing to obtain OCR recognition results, and performing OCR processing on all image, video and chart data of an Internet of Things platform to obtain recognition results from image, video and chart data of the multiple systems; A video monitoring system for analyzing monitoring videos obtained by real-time monitoring of the multiple systems to obtain semantic information represented by the monitoring videos, and analyzing monitoring videos obtained by real-time monitoring of device ends of the multiple systems to obtain semantic information represented by the monitoring videos; A natural language processing system for performing natural language processing on the OCR recognition results to obtain semantic information represented by data; An information processing system for judging the semantic information represented by the monitoring videos and the semantic information represented by the data, and outputting the semantic information represented by the data to an information base when the semantic information represented by the monitoring videos matches the semantic information represented by the data.

2. The system of claim 1, wherein, The information processing system is further configured to: output the semantic information represented by the monitoring videos to the information base when the semantic information represented by the monitoring videos does not match the semantic information represented by the data.

3. The system of claim 1, wherein, output the semantic information represented by the data to the information base when the semantic information represented by the monitoring videos matches the semantic information represented by the data, including: after determining that the semantic information represented by the monitoring videos matches the semantic information represented by the data, customizing the semantic information represented by the data, correlating the customized semantic information represented by the data with each other, and outputting the correlated semantic information represented by the data to the information base for storage.

4. The system of claim 1, wherein, The obtaining of data of multiple systems and the performing of OCR processing to obtain OCR recognition results include: cleaning and preprocessing data of the multiple systems; text positioning and recognition of the cleaned and preprocessed data to obtain the OCR recognition results.

5. The system of claim 3, wherein, The correlation of the customized semantic information represented by the data with each other includes: identification cutting of the customized semantic information represented by the data; correlation of relevant semantic information represented by the data with each other according to the identification cutting results. The system further comprises: a display system for adjusting distances between the correlated semantic information represented by the data and presenting the distances in vertical correlation and / or horizontal correlation.

6. The system of claim 5, wherein, The relevant semantic information represented by the data includes first semantic information represented by data and second semantic information represented by data; when the first semantic information represented by data and the second semantic information represented by data are presented in an up-down form, the correlation is vertical correlation; when the first semantic information represented by data and the second semantic information represented by data are presented in a left-right form, the correlation is horizontal correlation.

7. The system of claim 3, wherein, The system further comprises: The integrated system is used for: identifying the associated semantic information of the data representation before outputting the associated semantic information of the data representation to the information base for storage, determining the corresponding relationship; according to the corresponding relationship, data conversion and integration of the associated semantic information of the data representation.

8. The system of claim 3, wherein, The system further comprises: The model training system is used for model training of the associated semantic information of the data representation stored in the information base after outputting the associated semantic information of the data representation to the information base for storage.

9. A method of data processing, wherein, The method comprises: Obtaining the data of multiple systems and performing OCR processing to obtain the OCR recognition result, performing OCR processing on all image, video and chart data of the Internet of Things platform to obtain the recognition result from the image, video and chart data of the multiple systems; Analyzing the monitoring video obtained by real-time monitoring of the multiple systems to obtain the semantic information represented by the monitoring video, and analyzing the monitoring video obtained by real-time monitoring of the device end of the multiple systems to obtain the semantic information represented by the monitoring video; For natural language processing of the OCR recognition result, obtaining the semantic information of the data representation and being used for display; Judging the semantic information represented by the monitoring video and the semantic information of the data representation; When the semantic information represented by the monitoring video matches the semantic information of the data representation, the semantic information of the data representation is output to the information base.

10. A computer readable storage medium storing computer executable instructions for executing the data processing method of claim 9.

Images