Multi-source heterogeneous data fusion method and device, electronic equipment and readable medium

Abstract

The embodiment of the invention discloses a multi-source heterogeneous data fusion method and device, electronic equipment and a readable medium. A specific embodiment of the method comprises the following steps: acquiring infectious disease monitoring data; generating infectious disease structured data; generating infectious disease label structured data; standardized infectious disease monitoring data are generated; performing data cleaning processing on the infectious disease monitoring standardized data to obtain infectious disease monitoring cleaning data; performing similarity matching on every two pieces of infectious disease cleaning data meeting a preset matching condition in each piece of infectious disease cleaning data; generating target infectious disease structured data; determining information of each person to be prompted; and sending preset prompt information to each terminal corresponding to each piece of to-be-prompted personnel information. According to the embodiment, computing resources consumed during data fusion can be reduced, and the processing efficiency during data fusion can be improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a multi-source heterogeneous data fusion method, device, electronic device, and readable medium. Background Art

[0002] Multi-source heterogeneous data fusion can be a method for fusing data from different data sources and different data structures. At present, when fusing multi-source heterogeneous data, the method usually adopted is: first, different data are fused by rule matching. Then, the information of each person is determined by the fused data. Then, prompt information is sent to the terminal of each person information.

[0003] However, when the above method is used to fuse multi-source heterogeneous data, the following technical problems often occur: When data is integrated through rule matching, computing resources are needed to process the data one by one, which easily leads to greater computational complexity in data processing, and in turn leads to greater computing resources consumed in data processing, resulting in lower processing efficiency in data processing. Summary of the invention

[0004] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0005] Some embodiments of the present disclosure propose a multi-source heterogeneous data fusion method, apparatus, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0006] In a first aspect, some embodiments of the present disclosure provide a multi-source heterogeneous data fusion method, the method comprising: acquiring infectious disease monitoring data, wherein the infectious disease monitoring data comprises infectious disease monitoring structured data, infectious disease monitoring semi-structured data and infectious disease monitoring unstructured data; generating infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data; generating infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data; generating infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data; and performing data fusion on the infectious disease monitoring standardized data. Cleaning processing is performed to obtain infectious disease monitoring cleaning data, wherein the infectious disease monitoring cleaning data includes various infectious disease cleaning data, and each infectious disease cleaning data in the various infectious disease cleaning data corresponds to a data source and an update time; based on the various infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on every two infectious disease cleaning data in the various infectious disease cleaning data that meet preset matching conditions to obtain various similarity matching results; based on the various similarity matching results and the various infectious disease cleaning data, target infectious disease structured data is generated; based on the target infectious disease structured data, information on each person to be prompted is determined; and the preset prompt information is sent to each terminal corresponding to the information on each person to be prompted.

[0007] In a second aspect, some embodiments of the present disclosure provide a multi-source heterogeneous data fusion device, the device comprising: an acquisition unit, configured to acquire infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data and infectious disease monitoring unstructured data; a first generation unit, configured to generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data; a second generation unit, configured to generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data; a third generation unit, configured to generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data; a data cleaning unit, configured to clean the infectious disease monitoring standard The data is cleaned and processed to obtain infectious disease monitoring cleaning data, wherein the infectious disease monitoring cleaning data includes various infectious disease cleaning data, and each infectious disease cleaning data in the various infectious disease cleaning data corresponds to a data source and an update time; the matching unit is configured to perform similarity matching on every two infectious disease cleaning data that meet the preset matching conditions in the various infectious disease cleaning data included in the above infectious disease monitoring cleaning data, to obtain various similarity matching results; the fourth generating unit is configured to generate target infectious disease structured data based on the above various similarity matching results and the above various infectious disease cleaning data; the determining unit is configured to determine each person information to be prompted based on the above target infectious disease structured data; the sending unit is configured to send the preset prompt information to each terminal corresponding to the above each person information to be prompted.

[0008] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0009] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0010] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the multi-source heterogeneous data fusion method of some embodiments of the present disclosure, the consumption of computing resources during data processing can be reduced and the data processing efficiency can be improved. Specifically, the reason for the large computing resources consumed during data processing and the low data processing efficiency is that when the data is fused by rule matching, computing resources need to be consumed to process the data one by one, which easily leads to a large computational complexity during data processing, and then leads to a large computing resource consumed during data processing, resulting in a low processing efficiency during data processing. Based on this, the multi-source heterogeneous data fusion method of some embodiments of the present disclosure, first, obtains infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data and infectious disease monitoring unstructured data. Thus, data from different data sources and different data structures that need to be processed can be obtained. Secondly, based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data, infectious disease structured data is generated. Thus, semi-structured data can be converted into structured data. Then, based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data, infectious disease label structured data is generated. Thus, unstructured data can be converted into structured data. Then, based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data, infectious disease monitoring standardized data is generated. Thus, all the generated structured data can be fused, and all the structured data can be standardized. Then, the infectious disease monitoring standardized data is cleaned to obtain infectious disease monitoring cleaned data, wherein the infectious disease monitoring cleaned data includes each infectious disease cleaning data, and each infectious disease cleaning data in the above infectious disease cleaning data corresponds to a data source and an update time. Thus, infectious disease monitoring cleaned data can be obtained. Then, based on each infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on each two infectious disease cleaning data that meet the preset matching conditions in the above infectious disease cleaning data to obtain each similarity matching result. Thus, the two infectious disease cleaning data with higher similarity in the above infectious disease cleaning data can be fused into one data. Then, based on the above similarity matching results and the above infectious disease cleaning data, target infectious disease structured data is generated. Thus, target infectious disease structured data can be obtained. Then, based on the above target infectious disease structured data, the information of each person to be prompted is determined. Thus, the personnel to whom the prompt information needs to be sent can be determined according to the obtained target infectious disease structured data. Finally, the preset prompt information is sent to each terminal corresponding to each of the above-mentioned personnel information to be prompted.Also, because data from different data sources and different data structures can be converted into structured data before being fused, the computing resources consumed when fusing the data can be reduced, and the data processing efficiency during data fusion can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0012] Figure 1 is a flowchart of some embodiments of the multi-source heterogeneous data fusion method according to the present disclosure; Figure 2 is a schematic diagram of the structure of some embodiments of the multi-source heterogeneous data fusion device according to the present disclosure; Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0013] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0014] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0015] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0016] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0017] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0018] With regard to the collection, storage, and use of user personal information (such as user portraits and historical user behaviors) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] Figure 1 The process 100 of some embodiments of the multi-source heterogeneous data fusion method according to the present disclosure is shown. The multi-source heterogeneous data fusion method includes the following steps: Step 101, obtaining infectious disease monitoring data.

[0021] In some embodiments, the execution subject (e.g., a computing device) of the multi-source heterogeneous data fusion method may obtain infectious disease monitoring data. The infectious disease monitoring data may be data related to infectious diseases. The infectious disease monitoring data may include infectious disease monitoring structured data, infectious disease monitoring semi-structured data, and infectious disease monitoring unstructured data. The infectious disease monitoring structured data may be structured data for characterizing relevant information of infectious diseases. For example, the infectious disease monitoring structured data may be tabular data for characterizing relevant information of infectious diseases. The infectious disease monitoring structured data may include various fields and various infectious disease monitoring row data. The various fields may include, but are not limited to, at least one of the following: name, age, personnel identity information, symptoms, whether to wear a mask, and activity path. The personnel identity information may be a unique identification code corresponding to the personnel. The personnel may be a resident of an infectious disease prevention and control area. The activity path may characterize a location that the personnel has reached. For example, the activity path may be "March 10, 2025, Building 3, Community 12, 1234". Each infectious disease monitoring row data in the various infectious disease monitoring row data may be row data in the infectious disease monitoring structured data. The row data may be a row of data in the structured data. Each of the infectious disease monitoring row data in the above-mentioned infectious disease monitoring row data may include each field value corresponding to each of the above-mentioned fields. As an example, when each of the above-mentioned fields is "name, age, and personnel identity information", the infectious disease monitoring row data may be "Zhang San, 23, 123456". The above-mentioned infectious disease monitoring semi-structured data may be semi-structured data for characterizing relevant information of infectious diseases. For example, the above-mentioned infectious disease monitoring semi-structured data may be a JSON file containing relevant information of infectious diseases. The above-mentioned infectious disease monitoring unstructured data may be unstructured data containing relevant information of infectious diseases. The above-mentioned infectious disease monitoring unstructured data may include infectious disease text data sets, infectious disease image data sets, infectious disease audio data sets, and infectious disease image data sets. Each infectious disease text data in the above-mentioned infectious disease text data sets may be text data for recording relevant information of infectious diseases. Each infectious disease text data in the above-mentioned infectious disease text data sets corresponds to personnel identity information and update time. The above-mentioned infectious disease image data sets may be image data for recording relevant information of infectious diseases. Each infectious disease image data in the above-mentioned infectious disease image data sets corresponds to personnel identity information and update time. Each infectious disease audio data in the above-mentioned infectious disease audio data sets may be an audio file for recording relevant information of infectious diseases. Each infectious disease audio data in the infectious disease audio data set has corresponding person identity information and update time. Each infectious disease image data in the infectious disease image data set may be medical-related image data corresponding to a person undergoing medical imaging examination.For example, the infectious disease image data may be a CT image (Computed Tomography) corresponding to a person. Each infectious disease image data in the infectious disease image data set corresponds to the identity information of the person and the update time. The update time may be used to characterize the time point corresponding to the last update of the data. The execution subject may be a server. In practice, first, the execution subject may obtain the infectious disease monitoring structured data from a preset infectious disease monitoring structured database. Then, the infectious disease monitoring semi-structured data may be obtained from a preset infectious disease monitoring semi-structured database. Then, the infectious disease monitoring unstructured data may be obtained through a preset infectious disease monitoring unstructured database. Among them, the infectious disease monitoring structured database may be a database for storing infectious disease monitoring structured data. The infectious disease monitoring semi-structured database may be a database for storing infectious disease monitoring semi-structured data. The infectious disease monitoring unstructured database may be a database for storing infectious disease monitoring unstructured data. Among them, the infectious disease monitoring structured database, the infectious disease monitoring semi-structured database and the infectious disease monitoring unstructured database may be respective data sources.

[0022] Step 102: Generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data.

[0023] In some embodiments, the execution subject may generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data, wherein the infectious disease structured data may be structured data obtained by converting the infectious disease monitoring semi-structured data.

[0024] In some optional implementations of some embodiments, the execution subject may generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data through the following steps: The first step is to perform data parsing on the above-mentioned infectious disease monitoring semi-structured data to obtain each infectious disease field data set. Among them, each infectious disease field data in the above-mentioned infectious disease field data set can be text data obtained after parsing the above-mentioned infectious disease monitoring semi-structured data. Each infectious disease field data set in the above-mentioned infectious disease field data set corresponds to personnel identity information. Each infectious disease field data set in the above-mentioned infectious disease field data set can include the above-mentioned fields and each infectious disease field data. Each infectious disease field data in the above-mentioned infectious disease field data can be a field value corresponding to any one of the above-mentioned fields. For example, when the above-mentioned fields are "name, age, personnel identity information", the infectious disease field data set can be "name: Li Si, age: 56, personnel identity information: 987654". In practice, the above-mentioned execution subject can perform data parsing on the above-mentioned infectious disease monitoring semi-structured data through a parsing library function to obtain each infectious disease field data set. Among them, the above-mentioned parsing library function can be a library function that can parse semi-structured data. For example, the above-mentioned parsing library function can be a Fastjson library.

[0025] In the second step, for each infectious disease field data set in the above infectious disease field data sets, data conversion processing is performed on the above infectious disease field data sets to obtain infectious disease field structured data.

[0026] The infectious disease field structured data may be structured data corresponding to an infectious disease field data set. In practice, for each infectious disease field data set in each of the infectious disease field data sets, the execution subject may convert the infectious disease field data set into a structured table through a data processing tool to obtain infectious disease field structured data. The data processing tool may be Pandas.

[0027] The third step is to integrate and process the obtained structured data of each infectious disease field to obtain infectious disease structured data. The infectious disease structured data can be structured data obtained by combining the structured data of each infectious disease field. In practice, the execution entity can combine the structured data of each infectious disease field into infectious disease structured data.

[0028] Step 103: Generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data.

[0029] In some embodiments, the above-mentioned execution entity can generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the above-mentioned infectious disease monitoring data.

[0030] In some optional implementations of some embodiments, the execution subject may generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data through the following steps: The first step is to perform data conversion processing on each infectious disease audio data included in the infectious disease audio data set based on the infectious disease monitoring unstructured data, so as to obtain an audio text data set. Among them, each audio text data in the audio text data set can be text data obtained by converting the corresponding infectious disease audio data. Each audio text data in the audio text data set corresponds to personal identity information. In practice, the execution subject can convert each infectious disease audio data in the infectious disease audio data set into corresponding text data through an audio conversion library function to obtain an audio text data set. Among them, the audio conversion library function can be a function that can convert an audio file into text data. For example, the audio conversion library function can be a Whisper library.

[0031] The second step is to integrate the audio text data set and the infectious disease text data set included in the infectious disease monitoring unstructured data to obtain an infectious disease text integrated data set. The infectious disease text integrated data in the infectious disease text integrated data set may be the audio text data in the audio text data set or the infectious disease text data in the infectious disease text data set. In practice, the execution entity may combine the individual audio text data in the audio text data set and the individual infectious disease text data in the infectious disease text data into one data set as an infectious disease text integrated data set.

[0032] In the third step, for each infectious disease text integration data in the above infectious disease text integration data set, keyword extraction processing is performed on the above infectious disease text integration data to obtain a keyword data set. Among them, each keyword data in the above keyword data set can be a keyword existing in the infectious disease text integration data and contained in a preset keyword extraction table. The above keyword extraction table can be a table file used to characterize each keyword to be extracted. In practice, for each infectious disease text integration data in the above infectious disease text integration data set, the above execution subject can extract each keyword corresponding to the above fields from the above infectious disease text integration data through a keyword extraction model to obtain a keyword data set corresponding to the above infectious disease text integration data. Among them, the above keyword extraction model can be a neural network model that takes the infectious disease text integration data as input and takes the keyword data set corresponding to the infectious disease text integration data as output. The above keyword extraction model can be a pre-trained BERT model (Bidirectional Encoder Representations from Transformers). The above pre-training process can be to fine-tune the BERT model using the labeled infectious disease text integration data set and the cross entropy loss function.

[0033] The fourth step is to generate infectious disease text structured data based on the obtained keyword data sets. The infectious disease text structured data may be structured data corresponding to the above-mentioned keyword data sets. In practice, for each keyword data set in the above-mentioned keyword data sets, the execution subject may convert the above-mentioned keyword data set into a structured table as infectious disease text structured sub-data through the above-mentioned data processing tool. Finally, the obtained infectious disease text structured sub-data may be combined into infectious disease text structured data.

[0034] The fifth step is to perform image recognition processing on the infectious disease image data set included in the above-mentioned infectious disease monitoring unstructured data to obtain an image recognition result data set. Among them, each image recognition result data in the above-mentioned image recognition result data set can be a label used to characterize whether the person in the corresponding infectious disease image data wears a mask. For example, the above-mentioned image recognition result data can be "wearing a mask" or "not wearing a mask". In practice, for each infectious disease image data in the above-mentioned infectious disease image data set, the above-mentioned execution entity can perform image recognition processing on the above-mentioned infectious disease image data through an image recognition model to obtain image recognition result data. Among them, the above-mentioned image recognition model can be a neural network model with infectious disease image data as input and image recognition result data as output. For example, the above-mentioned image recognition model can be a pre-trained YOLOv5 model. The above-mentioned pre-training process can be a process of fine-tuning the YOLOv5 model using the labeled infectious disease image data set and the cross entropy loss function.

[0035] The sixth step is to generate infectious disease image structured data based on the infectious disease image data set and the image recognition result data set. The infectious disease image structured data may be structured data corresponding to the infectious disease image data set and the image recognition result data set. The infectious disease image structured data may include structured row data of each infectious disease image. Each infectious disease image structured row data in the structured row data of each infectious disease image may be row data in the structured data of the infectious disease image. The infectious disease image structured data corresponds to a "personnel identity information" field and a "whether to wear a mask" field. In practice, for each infectious disease image data in the infectious disease image data set, first, the execution subject may determine the image recognition result data corresponding to the infectious disease image data in the image recognition result data set as the target image recognition result data. Secondly, the execution subject may determine the personnel identity information corresponding to the infectious disease image data as the field value corresponding to the "personnel identity information" field. Then, the update time corresponding to the target image recognition result data and the infectious disease image data may be combined into the image recognition result data to be determined, and the image recognition result data to be determined may be determined as the field value corresponding to the "whether to wear a mask" field. Thus, the image recognition result data to be determined and the personal identity information corresponding to the infectious disease image data can be combined into infectious disease image structured row data. Finally, the combined infectious disease image structured row data can be combined into infectious disease image structured data.

[0036] In the seventh step, the infectious disease image data set included in the above-mentioned infectious disease monitoring unstructured data is identified and processed to obtain an image recognition result data set. Among them, each image recognition result data in the above-mentioned image recognition result data set can be a label for characterizing the symptoms present in the corresponding infectious disease image data. For example, the above-mentioned image recognition result data may include but are not limited to: "asymptomatic", "pneumonia", "pancreatitis". In practice, for each infectious disease image data in the above-mentioned infectious disease image data set, the above-mentioned execution subject may input the above-mentioned infectious disease image data into the image recognition model to obtain the image recognition result data. Finally, the obtained individual image recognition result data can be determined as an image recognition result data set. Among them, the above-mentioned image recognition model can be a neural network that takes infectious disease image data as input and image recognition result data corresponding to the infectious disease image data as output. The above-mentioned image recognition model can be a pre-trained COVID-Net network. The above-mentioned pre-training can be fine-tuning the COVID-Net network using the labeled infectious disease image data set and the cross entropy loss function.

[0037] Step 8: Generate infectious disease image structured data based on the infectious disease image data set and the image recognition result data set. The infectious disease image structured data may be structured data corresponding to the infectious disease image data set and the image recognition result data set. The infectious disease image structured data may include structured row data of each infectious disease image. Each infectious disease image structured row data in the infectious disease image structured row data may be row data in the infectious disease image structured data. Each infectious disease image structured row data in the infectious disease image structured row data corresponds to a "personnel identity information" field and a "symptom" field. In practice, for each infectious disease image data in the infectious disease image data set, first, the image recognition result data corresponding to the infectious disease image data in the image recognition result data set may be determined as the target image recognition result data. Secondly, the personnel identity information corresponding to the infectious disease image data may be determined as the field value corresponding to the "personnel identity information" field. Then, the update time corresponding to the target image recognition result data and the infectious disease image data may be combined into the image recognition result data to be determined, and the image recognition result data to be determined may be determined as the field value corresponding to the "symptom" field. Thus, the image recognition result data to be determined and the personal identity information corresponding to the infectious disease image data can be combined into infectious disease image structured sub-data. Finally, the combined infectious disease image structured sub-data can be combined into infectious disease image structured data.

[0038] The ninth step is to integrate and process the infectious disease text structured data, the infectious disease image structured data and the infectious disease image structured data to obtain infectious disease label structured data. Among them, the infectious disease label structured data can be structured data obtained by combining the infectious disease text structured data, the infectious disease image structured data and the infectious disease image structured data. The infectious disease label structured data corresponds to the above-mentioned fields. The infectious disease label structured data can include each infectious disease label structured row data. Each infectious disease label structured row data in the above-mentioned infectious disease label structured row data can be row data in the above-mentioned infectious disease label structured data. Each infectious disease label structured row data in the above-mentioned infectious disease label structured row data corresponds to a data source and an update time.

[0039] In practice, for each infectious disease text structured row data included in the above infectious disease text structured data, each infectious disease image structured row data included in the above infectious disease image structured data, and each infectious disease image structured row data included in the above infectious disease image structured data, the above execution entity may combine the infectious disease text structured row data, infectious disease image structured row data, and infectious disease image structured row data with the same field value of the corresponding "personnel identity information" field into infectious disease label structured row data. Finally, the obtained infectious disease label structured row data may be combined into infectious disease label structured data.

[0040] In practice, for each infectious disease label structured row data in the above-mentioned infectious disease label structured row data, the above-mentioned execution subject can determine the generation time corresponding to the above-mentioned infectious disease label structured row data as the update time corresponding to the above-mentioned infectious disease label structured row data. Among them, the above-mentioned generation time can be the time when the above-mentioned infectious disease label structured row data is obtained by combination. The above-mentioned infectious disease monitoring unstructured database can be determined as the data source corresponding to the above-mentioned infectious disease label structured row data.

[0041] As an example, when the above fields are "personnel identity information, whether to wear a mask, age, symptoms", and the infectious disease text structured row data is "personnel identity information: 12345, whether to wear a mask: wearing a mask at 12:34 on January 17, 2025, age: 25, symptoms: pancreatitis at 17:46 on December 1, 2024", the infectious disease image structured row data is "personnel identity information: 12345, whether to wear a mask: not wearing a mask at 17:25 on January 10, 2025", When the structured row data of the infected image is "personnel identity information: 12345, symptoms: pneumonia at 18:35 on March 2, 2025", the combined structured row data of the infectious disease label is "personnel identity information: 12345, whether to wear a mask: wearing a mask at 12:34 on January 17, 2025, not wearing a mask at 17:25 on January 10, 2025, age: 25, symptoms: pancreatitis at 17:46 on December 1, 2024, pneumonia at 18:35 on March 2, 2025".

[0042] Step 104, generating infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data.

[0043] In some embodiments, the execution entity may generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data.

[0044] In some optional implementations of some embodiments, the execution entity may generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data through the following steps: The first step is to integrate the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data to obtain infectious disease integrated structured data. The infectious disease integrated structured data may be structured data obtained by combining the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data.

[0045] The above-mentioned infectious disease integrated structured data corresponds to the above-mentioned various fields. The above-mentioned infectious disease integrated structured data includes various infectious disease integrated structured row data. Each infectious disease integrated structured row data in the above-mentioned various infectious disease integrated structured row data can be row data in the above-mentioned infectious disease integrated structured data. Each infectious disease integrated structured row data in the above-mentioned various infectious disease integrated structured row data may include various field values ​​corresponding to the above-mentioned various fields. Each infectious disease integrated structured row data in the above-mentioned various infectious disease integrated structured row data corresponds to update time and data source.

[0046] In practice, for each infectious disease structured row data included in the above infectious disease structured data, each infectious disease label structured row data included in the above infectious disease label structured data, and each infectious disease monitoring structured row data included in the above infectious disease monitoring structured data, the above execution entity may combine the infectious disease structured row data, infectious disease label structured row data, and infectious disease monitoring structured row data with the same field value of the corresponding "personnel identity information" field into infectious disease integrated structured row data. Then, the combined infectious disease integrated structured row data may be combined into infectious disease integrated structured data.

[0047] In practice, for each of the above-mentioned infectious disease integrated structured row data, first, the time of generating the above-mentioned infectious disease integrated structured row data can be determined as the update time corresponding to the above-mentioned infectious disease integrated structured row data. Then, for each field value included in the above-mentioned infectious disease integrated structured row data, based on each data source corresponding to each of the above-mentioned field values, the data source that appears the most times among the above-mentioned data sources can be determined as the data source corresponding to the above-mentioned infectious disease integrated structured row data.

[0048] As an example, when the integrated structured row data of an infectious disease is "Name: Li Si, Age: 45, Activity Path: 12 Community, 12th Floor, 1234, Symptoms: Pneumonia", and the data of "Name: Li Si" comes from the above-mentioned infectious disease monitoring structured database, the data of "Age: 45" also comes from the above-mentioned infectious disease monitoring structured database, "Activity Path: 12 Community, 12th Floor, 1234" comes from the above-mentioned infectious disease monitoring semi-structured database, and "Symptoms: Pneumonia" comes from the above-mentioned infectious disease monitoring unstructured database, since "Name: Li Si" and "Age: 45" both come from the infectious disease monitoring structured database, the infectious disease monitoring structured database appears twice, while the above-mentioned infectious disease monitoring semi-structured database and the above-mentioned infectious disease monitoring unstructured database only appear once. Therefore, the data source corresponding to the above-mentioned infectious disease integrated structured row data is the infectious disease monitoring structured database.

[0049] The second step is to perform data conversion processing on the above-mentioned infectious disease integrated structured data to obtain infectious disease converted structured data. Among them, the above-mentioned infectious disease converted structured data can be the converted infectious disease integrated structured data. The above-mentioned infectious disease converted structured data can correspond to the above-mentioned various fields. The above-mentioned infectious disease converted structured data can include various infectious disease converted structured row data. Each infectious disease converted structured row data in the above-mentioned various infectious disease converted structured row data can be row data in the above-mentioned infectious disease converted structured data. Each infectious disease converted structured row data in the above-mentioned various infectious disease converted structured row data can include various field values ​​corresponding to the above-mentioned various fields. Each infectious disease converted structured row data in the above-mentioned various infectious disease converted structured row data corresponds to an update time and a data source.

[0050] In practice, the execution entity may input the infectious disease integrated structured data into a time format conversion function to obtain infectious disease conversion structured data. The time format conversion function may be a function that can convert time into UTC time format. For example, the time format conversion function may be a utc function.

[0051] In practice, for each infectious disease conversion structured row data in the above-mentioned infectious disease conversion structured row data, first, the above-mentioned execution subject can determine the time of generating the above-mentioned infectious disease conversion structured row data as the update time. Then, the infectious disease integrated structured row data corresponding to the above-mentioned infectious disease conversion structured row data in the above-mentioned each infectious disease integrated structured row data can be determined as the target infectious disease integrated structured row data. Then, the data source corresponding to the above-mentioned target infectious disease integrated structured row data can be determined as the data source corresponding to the above-mentioned infectious disease conversion structured row data.

[0052] The third step is to generate infectious disease encrypted structured data based on the infectious disease conversion structured data. The infectious disease encrypted structured data may be infectious disease conversion structured data that has been encrypted. The infectious disease encrypted structured data corresponds to the above-mentioned fields. The infectious disease encrypted structured data may include each infectious disease encrypted structured row data. Each infectious disease encrypted structured row data in the above-mentioned infectious disease encrypted structured row data may be row data corresponding to the infectious disease encrypted structured data. Each infectious disease encrypted structured row data in the above-mentioned infectious disease encrypted structured row data may include each field value corresponding to each of the above-mentioned fields.

[0053] In practice, the execution subject may encrypt the values ​​of each field corresponding to the "personnel identity information" field in the infectious disease conversion structured data through an encryption algorithm to obtain infectious disease encrypted structured data. The encryption algorithm may be an algorithm capable of encrypting data. For example, the encryption algorithm may be a SHA256 algorithm.

[0054] In practice, for each infectious disease encrypted structured row data in the above-mentioned infectious disease encrypted structured row data, first, the above-mentioned execution subject can determine the time of encrypting the above-mentioned infectious disease encrypted structured row data as the update time. Secondly, the infectious disease conversion structured row data corresponding to the above-mentioned infectious disease encrypted structured row data in the above-mentioned each infectious disease conversion structured row data can be determined as the target infectious disease conversion structured row data. Then, the data source corresponding to the above-mentioned target infectious disease conversion structured row data can be determined as the data source corresponding to the above-mentioned infectious disease encrypted structured row data.

[0055] The fourth step is to perform data standardization processing on the above-mentioned infectious disease encrypted structured data to obtain infectious disease monitoring standardized data. Among them, the above-mentioned infectious disease monitoring standardized data can be processed infectious disease encrypted structured data. The above-mentioned infectious disease monitoring standardized data can correspond to the above-mentioned various fields. The above-mentioned infectious disease monitoring standardized data can include various infectious disease monitoring standardized row data. Each infectious disease monitoring standardized row data in the above-mentioned various infectious disease monitoring standardized row data can be the row data corresponding to the above-mentioned infectious disease monitoring standardized data. Each infectious disease monitoring standardized row data in the above-mentioned various infectious disease monitoring standardized row data can include various field values ​​corresponding to the above-mentioned various fields. Each infectious disease monitoring standardized row data in the above-mentioned various infectious disease monitoring standardized row data corresponds to an update time and a data source. In practice, the above-mentioned execution subject can convert the various field values ​​corresponding to the "activity path" field in the above-mentioned infectious disease encrypted structured data into longitude and latitude coordinates by calling a map interface to obtain infectious disease monitoring standardized data. Among them, the above-mentioned map interface can be an API interface that can convert an address into longitude and latitude coordinates. For example, the above-mentioned map interface can be a Tiandi Map API. In practice, for each of the above-mentioned standardized row data for infectious disease monitoring, first, the above-mentioned execution entity may determine the time of generating the above-mentioned standardized row data for infectious disease monitoring as the update time corresponding to the above-mentioned standardized row data for infectious disease monitoring. Secondly, the infectious disease encrypted structured row data corresponding to the above-mentioned standardized row data for infectious disease monitoring in the above-mentioned encrypted structured row data for infectious diseases may be determined as the target infectious disease encrypted structured row data. Then, the data source corresponding to the above-mentioned encrypted structured row data for infectious diseases may be determined as the data source corresponding to the above-mentioned standardized row data for infectious disease monitoring.

[0056] Step 105, performing data cleaning processing on the infectious disease monitoring standardized data to obtain infectious disease monitoring cleaned data.

[0057] In some embodiments, the execution subject may perform data cleaning on the infectious disease monitoring standardized data to obtain infectious disease monitoring cleaned data, wherein the infectious disease monitoring cleaned data may be infectious disease monitoring standardized data that has undergone data cleaning.

[0058] The infectious disease monitoring cleansing data includes various infectious disease cleansing data. The various infectious disease cleansing data may be row data corresponding to the infectious disease monitoring cleansing data. Each infectious disease cleansing data in the various infectious disease cleansing data corresponds to a data source and an update time.

[0059] In the process of adopting technical solutions to solve the above technical problems, the following problems are often accompanied: When data is fused through rule matching, erroneous data often exists in the fused data, which makes it easy to be affected by erroneous data when identifying duplicate data on the fused data, resulting in a low recognition rate of duplicate data, which in turn leads to more duplicate data contained in the generated data. As a result, when prompt information is sent according to the generated data, there is a high probability of repeated sending to the same terminal, which causes a waste of computing resources when sending prompt information.

[0060] Faced with the above technical problems, we decided to adopt the following solutions: In some optional implementations of some embodiments, the execution subject may perform data cleaning on the infectious disease monitoring standardized data through the following steps to obtain infectious disease monitoring cleaned data: The first step is to determine the number of each field corresponding to the above-mentioned infectious disease monitoring standardized data as the standard field quantity data.

[0061] In the second step, for each of the infectious disease monitoring standardized row data included in the infectious disease monitoring standardized data, the following steps are performed: The first sub-step is to perform missing field detection processing on the above-mentioned standardized row data for infectious disease monitoring to obtain a missing field data set. Among them, each missing field data in the above-mentioned missing field data set can be a field value that meets the preset missing condition among the various field values ​​included in the above-mentioned standardized row data for infectious disease monitoring. Among them, the above-mentioned preset missing condition can be that the field value is empty. In practice, the above-mentioned execution entity can determine the various field values ​​that meet the above-mentioned preset missing condition among the various field values ​​included in the above-mentioned standardized row data for infectious disease monitoring as the missing field data set.

[0062] In the second sub-step, the quantity corresponding to each missing field data in the missing field data set is determined as the missing field quantity data.

[0063] The third sub-step is to determine the ratio of the missing field quantity data to the standard field quantity data as the field missing probability data corresponding to the standardized row data for infectious disease monitoring.

[0064] The fourth sub-step is to perform data supplementation processing on the above-mentioned infectious disease monitoring standardized row data in response to determining that the above-mentioned field missing probability data meets the preset field missing condition, and obtain infectious disease supplementary structure data. Among them, the above-mentioned field missing condition can be that the above-mentioned field missing probability data is less than the preset field missing threshold. The above-mentioned field missing threshold can be a preset value. Here, the specific setting of the above-mentioned field missing threshold is not limited. The above-mentioned infectious disease supplementary structure data can be data obtained by supplementing each field value that is a null value in the above-mentioned infectious disease monitoring standardized row data. In practice, first, the above-mentioned execution subject can determine each field value that is a null value in each field value included in the above-mentioned infectious disease monitoring standardized row data as each field value to be supplemented. Then, for each field value to be supplemented in each of the above-mentioned field values ​​to be supplemented, first, the field corresponding to the above-mentioned field value to be supplemented can be determined as the target field to be supplemented. Then, the field that is the same as the above-mentioned target field to be supplemented in each field included in the preset field correspondence table can be determined as the target field data. Then, the default field value corresponding to the above-mentioned target field data can be determined as the target field value to be supplemented. Then, the above-mentioned field values ​​to be supplemented in the above-mentioned infectious disease monitoring standardized row data can be replaced with the above-mentioned target field values ​​to be supplemented to update the above-mentioned infectious disease monitoring standardized row data. Then, when all the above-mentioned field values ​​to be supplemented are replaced, the last updated infectious disease monitoring standardized row data can be determined as infectious disease supplementary structure data. Among them, the above-mentioned field correspondence table can be a pre-set relationship table for characterizing the correspondence between the above-mentioned fields and the various default field values. Each of the above-mentioned default field values ​​can be an initial field value corresponding to the field pre-set by a technician.

[0065] The third step is to perform data detection processing on each obtained infectious disease supplementary structure data to obtain each data detection result corresponding to the above-mentioned infectious disease supplementary structure data. Among them, each data detection result in the above-mentioned data detection results can be a label used to characterize whether the corresponding infectious disease supplementary structure data is abnormal. For example, the above-mentioned data detection result can be "normal" or "abnormal". In practice, for each infectious disease supplementary structure data in the above-mentioned infectious disease supplementary structure data, the above-mentioned execution subject can determine the field value of the corresponding field "age" in each field value included in the above-mentioned infectious disease supplementary structure data as the target age field value. In response to determining that the above-mentioned target age field value is greater than or equal to the preset age threshold, "abnormal" can be determined as the data detection result corresponding to the above-mentioned infectious disease supplementary structure data. In response to determining that the above-mentioned target age field value is less than the above-mentioned age threshold, "normal" can be determined as the data detection result corresponding to the above-mentioned infectious disease supplementary structure data. Among them, the above-mentioned age threshold can be a preset value. Here, the specific setting of the above-mentioned age threshold is not limited.

[0066] In the fourth step, for each of the above data detection results, in response to determining that the above data detection result meets a preset data detection result condition, the following steps are performed: In the first sub-step, the infectious disease supplementary structure data corresponding to the data detection result in the above-mentioned infectious disease supplementary structure data is determined as the infectious disease supplementary structure data to be corrected. The above-mentioned data detection result condition may be that the data detection result is "abnormal".

[0067] The second sub-step is to perform data correction processing on the above-mentioned infectious disease supplementary structure data to be corrected to obtain the infectious disease corrected structure data. Among them, the above-mentioned infectious disease corrected structure data can be the corrected infectious disease supplementary structure data. In practice, first, the above-mentioned execution subject can determine the field value of "age" corresponding to each field value corresponding to the above-mentioned infectious disease supplementary structure data to be corrected as the field value to be corrected. Then, the difference between the above-mentioned field value to be corrected and the preset corrected age threshold can be determined as the target corrected field value. Finally, the field value to be corrected in the above-mentioned infectious disease supplementary structure data to be corrected can be replaced with the above-mentioned target corrected field value through a data replacement function. Among them, the above-mentioned data replacement function can be a replace function. The above-mentioned corrected age threshold can be a pre-set value that is less than the above-mentioned age threshold.

[0068] The fifth step is to determine the above-mentioned infectious disease supplementary structure data as the infectious disease supplementary structure data set.

[0069] The sixth step is to update the infectious disease supplementary structure data corresponding to the infectious disease correction structure data in the infectious disease supplementary structure data set based on the obtained infectious disease correction structure data to obtain an updated infectious disease supplementary structure data set. In practice, first, the execution subject can determine the infectious disease supplementary structure data corresponding to the infectious disease correction structure data in the infectious disease supplementary structure data set as the infectious disease supplementary structure data to be replaced. Then, the infectious disease supplementary structure data to be replaced in the infectious disease supplementary structure data set can be replaced with the infectious disease correction structure data through the data replacement function to update the infectious disease supplementary structure data set to obtain an updated infectious disease supplementary structure data set.

[0070] In the seventh step, each infectious disease supplementary structure data in the updated infectious disease supplementary structure data set is determined as each infectious disease cleaned data.

[0071] Step 8: Integrate and process the above infectious disease cleaning data to obtain infectious disease monitoring cleaning data. In practice, the above execution entity can combine the above infectious disease cleaning data into infectious disease monitoring cleaning data.

[0072] The above technical solution and its related contents are combined with steps 101 to 109 as an inventive point of an embodiment of the present disclosure, which solves the problem of "waste of computing resources". The factors that lead to waste of storage resources are often as follows: when data is fused by rule matching, there are often erroneous data in the fused data, which makes it easy to be affected by erroneous data when identifying duplicate data for the fused data, resulting in a low recognition rate of duplicate data, which in turn leads to more duplicate data contained in the generated data, resulting in a high probability of repeated sending to the same terminal when sending prompt information according to the generated data, thereby causing waste of computing resources when sending prompt information. If the above factors are solved, the waste of computing resources can be reduced. In order to achieve this effect, the present disclosure first determines the number of each field corresponding to the above-mentioned infectious disease monitoring standardized data as the standard field number data. Thus, the number of each field can be obtained. Secondly, for each infectious disease monitoring standardized row data in each infectious disease monitoring standardized row data included in the above-mentioned infectious disease monitoring standardized data, the following steps are performed: First, the above-mentioned infectious disease monitoring standardized row data is subjected to missing field detection processing to obtain a missing field data set. Thus, each field without field value in the above-mentioned infectious disease monitoring standardized row data can be obtained. Secondly, the number corresponding to each missing field data in the missing field data set is determined as the missing field number data. Thus, the number of each missing field data in the missing field data set can be obtained. Then, the ratio of the missing field number data to the standard field number data is determined as the field missing probability data corresponding to the above-mentioned infectious disease monitoring standardized row data. Thus, the missing rate of the field value corresponding to the above-mentioned infectious disease monitoring standardized row data can be obtained. Then, in response to determining that the above-mentioned field missing probability data meets the preset field missing condition, the above-mentioned infectious disease monitoring standardized row data is subjected to data supplementation processing to obtain infectious disease supplementary structure data. Thus, each field value of each field value included in the above-mentioned infectious disease monitoring standardized row data as a null value can be supplemented. Then, the obtained each infectious disease supplementary structure data is subjected to data detection processing to obtain each data detection result corresponding to the above-mentioned each infectious disease supplementary structure data. Thus, abnormal data in the above-mentioned each infectious disease supplementary structure data can be detected. Then, for each data detection result in the above-mentioned each data detection result, in response to determining that the above-mentioned data detection result meets the preset data detection result condition, the following steps are performed: Then, the infectious disease supplementary structure data corresponding to the above-mentioned data detection result in the above-mentioned each infectious disease supplementary structure data is determined as the infectious disease supplementary structure data to be corrected. Thus, the infectious disease supplementary structure data that need to be corrected in the infectious disease supplementary structure data can be obtained. Then, the infectious disease supplementary structure data to be corrected is processed to obtain the infectious disease corrected structure data.Thus, the supplementary structural data of each infectious disease that needs to be corrected can be corrected. Then, the supplementary structural data of each infectious disease is determined as an infectious disease supplementary structural data set. Then, based on the obtained corrected structural data of each infectious disease, the supplementary structural data of each infectious disease corresponding to the corrected structural data of each infectious disease in the supplementary structural data set of the infectious disease is updated to obtain an updated supplementary structural data set of infectious diseases. Thus, a corrected supplementary structural data set of infectious diseases can be obtained. Then, the supplementary structural data of each infectious disease in the updated supplementary structural data set of infectious diseases is determined as each infectious disease cleaning data. Finally, the above-mentioned cleaning data of each infectious disease is integrated to obtain infectious disease monitoring cleaning data. Also, because the missing values ​​of the fused data can be supplemented and the erroneous values ​​can be corrected, and then the prompt information is sent according to the corrected data, the influence of the erroneous data on the identification of duplicate data can be reduced, and then the number of duplicate data in the finally generated data can be reduced, and then the probability of repeated sending to the same terminal when sending the prompt information according to the finally generated data can be reduced, and then the waste of computing resources during sending can be reduced.

[0073] Step 106 , based on each infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on every two infectious disease cleaning data that meet a preset matching condition in each infectious disease cleaning data to obtain each similarity matching result.

[0074] In some embodiments, the execution subject may perform similarity matching on each two infectious disease cleaning data that meet the preset matching conditions in each infectious disease cleaning data based on each infectious disease cleaning data included in the infectious disease monitoring cleaning data, and obtain each similarity matching result. Among them, the preset matching condition may be that the infectious disease cleaning data is the infectious disease cleaning data to be matched. The infectious disease cleaning data to be matched may be infectious disease cleaning data that has not been similarly matched. Each similarity matching result in the above similarity matching results may be a numerical value for characterizing the degree of similarity between the two infectious disease cleaning data. In practice, for each two infectious disease cleaning data that meet the above matching conditions in each infectious disease cleaning data, first, the two infectious disease cleaning data may be vectorized by a word vector embedding model to obtain two infectious disease vector data. Then, the cosine similarity between the two infectious disease vector data may be determined as the similarity matching result. Among them, each infectious disease vector data in the two infectious disease vector data may be a word vector corresponding to the infectious disease cleaning data. The word vector embedding model may be a model that takes text data as input and outputs a word vector corresponding to the text data. Among them, the word vector embedding model may be a Word2Vec model.

[0075] Step 107: Generate target infectious disease structured data based on each similarity matching result and each infectious disease cleansing data.

[0076] In some embodiments, the execution entity may generate target infectious disease structured data based on the similarity matching results and the infectious disease cleansing data.

[0077] In some optional implementations of some embodiments, the execution subject may generate target infectious disease structured data based on the above-mentioned similarity matching results and the above-mentioned infectious disease cleansing data through the following steps: In the first step, for each of the above similarity matching results, in response to determining that the above similarity matching result meets a preset similarity condition, the following steps are performed: In the first sub-step, two infectious disease cleaning data corresponding to the above similarity matching results in the above infectious disease cleaning data are determined as two infectious disease cleaning data to be compared. Among them, the above similarity condition can be that the similarity matching result is greater than a preset similarity threshold. The above similarity threshold can be a pre-set value. Here, there is no limitation on the specific setting of the above similarity threshold. Each of the above two infectious disease cleaning data to be compared corresponds to each field. Each of the above two infectious disease cleaning data to be compared includes each field value corresponding to each of the above fields.

[0078] In the second sub-step, for each of the above fields, perform the following steps: Sub-step one: determine the above fields as target fields.

[0079] Sub-step 2: Determine two field values ​​corresponding to the target field in each field value included in the two infectious disease cleansing data to be compared as two field values ​​to be compared.

[0080] Sub-step three, performing data comparison processing on the above two field values ​​to be compared to obtain a data comparison result. Among them, the above data comparison result can be a numerical value used to characterize the similarity between the above two field values ​​to be compared. In practice, the above execution entity can vectorize the above two field values ​​to be compared through the above word vector embedding model to obtain two vector data to be compared. Among them, each of the above two vector data to be compared can be the word vector corresponding to the field value to be compared. Then, the cosine similarity between the above two vector data to be compared can be determined as the data comparison result.

[0081] Sub-step 4: in response to determining that the data comparison result satisfies a preset comparison result condition, executing the following steps: First, based on the two to-be-compared field values ​​corresponding to the above data comparison result, two weight data corresponding to the above two to-be-compared field values ​​are determined. Among them, the above comparison result condition can be that the above data comparison result is equal to a preset data comparison threshold. The above data comparison threshold can be a pre-set value. Here, there is no limitation on the specific setting of the above data comparison threshold. Each of the above two weight data can be the weight corresponding to the to-be-compared field value.

[0082] Then, based on the above two weight data, target weight data is generated. The above target weight data may be the larger weight data of the above two weight data. In practice, the above execution subject may determine the larger weight data of the above two weight data as the target weight data.

[0083] Then, the to-be-compared field value corresponding to the above-mentioned target weight data among the above-mentioned two to-be-compared field values ​​is determined as the target field value.

[0084] The third sub-step is to generate target structured data based on the determined target field values. The target structured data may be structured data obtained by combining the target field values. In practice, the target field values ​​may be combined into target structured data.

[0085] The second step is to combine the generated target structured data into target infectious disease structured data.

[0086] In the process of adopting technical solutions to solve the above technical problems, the following problems are often accompanied: The data fusion method through rule matching has low flexibility in processing duplicate data or similar data in the data, which can easily lead to a large amount of duplicate data in the fused data, which in turn leads to a high degree of duplication of each personnel information determined based on the fused data. As a result, when sending prompt information based on each personnel information, there is a high probability of repeated sending to the same terminal, which in turn causes a waste of computing resources when sending prompt information.

[0087] Faced with the above technical problems, we decided to adopt the following solutions: In some optional implementations of some embodiments, the execution subject may determine two weight data corresponding to the two to-be-compared field values ​​based on the two to-be-compared field values ​​corresponding to the data comparison result through the following steps: In the first step, the field value to be compared that satisfies the preset first field value condition among the two field values ​​to be compared is determined as the first field value to be compared, wherein the first field value condition may be that the field value to be compared is any one of the two field values ​​to be compared.

[0088] In the second step, the field value to be compared that satisfies the preset second field value condition among the two field values ​​to be compared is determined as the second field value to be compared. The preset second field value condition may be that the field value to be compared is not the first field value to be compared.

[0089] In the third step, the data source and update time corresponding to the first field value to be compared are determined as the first data source and the first update time respectively.

[0090] Step 4: determine the difference between the first update time and the preset time as first time difference data. The preset time may be the current time. The unit corresponding to the first time difference data may be hours.

[0091] In the fifth step, the product of the first time difference data and the preset attenuation coefficient is determined as the attenuation difference data. The preset attenuation coefficient may be a pre-set value. The preset attenuation coefficient may be a value used to characterize the degree to which the credibility of the data gradually decreases over time.

[0092] Step 6: Determine the difference between the preset time coefficient and the attenuation difference data as the first time data corresponding to the first field value to be compared. The preset time coefficient may be a natural constant e.

[0093] The seventh step is to determine the first field missing data corresponding to the first field value to be compared based on the first field value to be compared. The first field missing data may be the field missing rate corresponding to the infectious disease cleaning data to be compared where the first field value to be compared is located. The field missing rate may characterize the proportion of each field value that is a null value in the infectious disease cleaning data to be compared in the field values ​​included in the infectious disease cleaning data to be compared. In practice, first, the execution entity may determine the infectious disease cleaning data to be compared corresponding to the first field value to be compared as the infectious disease cleaning data to be detected. Then, each field value that is a null value in each field value included in the infectious disease cleaning data to be detected may be determined as a missing field cleaning data set. Then, the number of each missing field cleaning data in the missing field cleaning data set may be determined as the missing number. Then, the ratio of the missing number to the standard field number data may be determined as the first field missing data.

[0094] In the eighth step, the data source corresponding to the first field value to be compared is determined as the first data source, wherein the first data source corresponds to initial weight data, wherein the initial weight data may be a value used to characterize the credibility of the first data source.

[0095] In the ninth step, each preset data source is determined as each target data source. Among them, each of the above target data sources corresponds to target initial weight data. The above target initial weight data can be a numerical value used to characterize the credibility of the target data source. The above data sources can be the above infectious disease monitoring structured database, the above infectious disease monitoring semi-structured database and the above infectious disease monitoring unstructured database.

[0096] The tenth step is to determine each target initial weight data corresponding to each of the above target data sources as each weight data to be processed.

[0097] In the eleventh step, various exponential weight data are generated based on the preset exponential coefficient and the above-mentioned various weight data to be processed. Among them, the above-mentioned preset exponential coefficient can be a natural constant e. In practice, for each of the above-mentioned weight data to be processed, the above-mentioned execution subject can determine the exponential weight data to the power of the above-mentioned weight data to be processed of the above-mentioned exponential coefficient. For example, when the above-mentioned weight data to be processed is "5", the corresponding exponential weight data is e to the power of 5.

[0098] In the twelfth step, the sum of the above-mentioned index weight data is determined as the index total weight data.

[0099] Optionally, after determining the sum of the above-mentioned individual index weight data as the index sum weight data, the above-mentioned execution subject may also, for each of the above-mentioned individual index weight data, first, determine the target data source corresponding to the above-mentioned index weight data as the data source to be processed. Then, the ratio of the above-mentioned index weight data to the above-mentioned index sum weight data may be determined as weight ratio data. Then, the above-mentioned weight ratio data may be determined as the target initial weight data corresponding to the above-mentioned data source to be processed, so as to update the target initial weight data corresponding to the above-mentioned data source to be processed.

[0100] In the thirteenth step, the ratio of the initial weight data to the sum of the exponential weight data is determined as the first exponential weight data.

[0101] In the fourteenth step, the sum of the first time data, the first field missing data and the first exponential weight data is determined as the first weight data.

[0102] Step 15: Determine the second weight data based on the second field value to be compared. The second weight data may be a numerical value used to characterize the credibility of the second field value to be compared. In practice, the method for determining the second weight data may refer to the specific implementation method for determining the first weight data in step 107, which will not be described in detail here.

[0103] In the sixteenth step, the first weight data and the second weight data are determined as two weight data corresponding to the two field values ​​to be compared.

[0104] The above technical solution and its related contents are combined with steps 101 to 109 as an inventive point of an embodiment of the present disclosure, which solves the problem of "waste of computing resources". The factors that lead to waste of storage resources are often as follows: the flexibility of processing duplicate data or similar data in the data by data fusion through rule matching is low, which easily leads to a large amount of duplicate data in the fused data, and then leads to a high degree of repetition of each personnel information determined according to the fused data, resulting in a high probability of repeated sending to the same terminal when sending prompt information according to each personnel information, thereby causing waste of computing resources when sending prompt information. If the above factors are solved, the waste of computing resources can be reduced. In order to achieve this effect, the present disclosure first determines the field value to be compared that meets the preset first field value condition in the above two field values ​​to be compared as the first field value to be compared. Thus, the first field value to be compared can be determined. Secondly, the field value to be compared that meets the preset second field value condition in the above two field values ​​to be compared is determined as the second field value to be compared. Thus, the second field value to be compared can be determined. Then, the data source and update time corresponding to the first field value to be compared are determined as the first data source and the first update time, respectively. Then, the difference between the first update time and the preset time is determined as the first time difference data. Thus, the difference between the data update time and the current time of the first field value to be compared can be obtained. Then, the product of the first time difference data and the preset attenuation coefficient is determined as the attenuation difference data. Thus, the attenuation difference data can be obtained. Then, the difference between the preset time coefficient and the attenuation difference data is determined as the first time data corresponding to the first field value to be compared. Thus, the credibility of the first field value to be compared can be preliminarily obtained. Then, based on the first field value to be compared, the first field missing data corresponding to the first field value to be compared is determined. Thus, the field missing rate corresponding to the first field value to be compared can be obtained. Then, the data source corresponding to the first field value to be compared is determined as the first data source, wherein the first data source corresponds to the initial weight data. Thus, the credibility of the data source corresponding to the first field value to be compared can be obtained. Then, each preset data source is determined as each target data source, wherein each of the above target data sources corresponds to target initial weight data. Then, each target initial weight data corresponding to each target data source is determined as each weight data to be processed. Thus, each target initial weight data corresponding to each preset data source can be obtained. Then, based on the preset exponential coefficient and each weight data to be processed, each exponential weight data is generated. Then, the sum of each exponential weight data is determined as exponential sum weight data. Then, the ratio of the above initial weight data to the above exponential sum weight data is determined as the first exponential weight data.Then, the sum of the first time data, the first field missing data and the first index weight data is determined as the first weight data. Thus, the weight data corresponding to the first field value to be compared can be obtained. Then, based on the second field value to be compared, the second weight data is determined. Thus, the weight data corresponding to the second field value to be compared can be obtained. Finally, the first weight data and the second weight data are determined as two weight data corresponding to the two field values ​​to be compared. Also, because two data with high similarity can be fused or replaced during data processing, because the number of duplicate data in the fused data can be reduced, and thus the repetition of each personnel information determined according to the fused data can be reduced, and the probability of repeated sending to the same terminal when sending prompt information according to each personnel information can be reduced, and thus the waste of computing resources can be reduced.

[0105] Step 108, based on the target infectious disease structured data, determine the information of each person to be notified.

[0106] In some embodiments, the execution subject may determine the information of each person to be prompted based on the target infectious disease structured data. The information of each person to be prompted may be the identity information of the person to whom the prompt information needs to be sent. In practice, for each target structured data in each target structured data included in the target infectious disease structured data, first, the execution subject may determine the field value of the corresponding "symptom" field in each target field value included in the target structured data as the target symptom field value. In response to determining that the target symptom field value satisfies the preset symptom field value condition, the execution subject may determine the field value of the corresponding "personnel identity information" field in each target field value included in the target structured data as the information of the person to be prompted. The symptom field value condition may be that there are symptom keywords in the target symptom field value. The symptom keywords may be keywords related to the symptoms of infectious disease infection. The symptom keywords may include, but are not limited to, fever and cough. The prompt information may be information for prompting people to seek medical treatment in time. For example, the prompt information may be "Please seek medical treatment in time".

[0107] Step 109: Send the preset prompt information to each terminal corresponding to the information of each person to be prompted.

[0108] In some embodiments, the execution subject may send preset prompt information to each terminal corresponding to each of the above-mentioned information of the person to be prompted. Each of the above-mentioned terminals may be a mobile phone. In practice, the execution subject may send preset prompt information to each of the above-mentioned terminals. The prompt information may be information for prompting the person to seek medical treatment in time. For example, the prompt information may be "Please seek medical treatment in time".

[0109] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the multi-source heterogeneous data fusion method of some embodiments of the present disclosure, the consumption of computing resources during data processing can be reduced and the data processing efficiency can be improved. Specifically, the reason for the large computing resources consumed during data processing and the low data processing efficiency is that when the data is fused by rule matching, computing resources need to be consumed to process the data one by one, which easily leads to a large computational complexity during data processing, and then leads to a large computing resource consumed during data processing, resulting in a low processing efficiency during data processing. Based on this, the multi-source heterogeneous data fusion method of some embodiments of the present disclosure, first, obtains infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data and infectious disease monitoring unstructured data. Thus, data from different data sources and different data structures that need to be processed can be obtained. Secondly, based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data, infectious disease structured data is generated. Thus, semi-structured data can be converted into structured data. Then, based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data, infectious disease label structured data is generated. Thus, unstructured data can be converted into structured data. Then, based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data, infectious disease monitoring standardized data is generated. Thus, all the generated structured data can be fused, and all the structured data can be standardized. Then, the infectious disease monitoring standardized data is cleaned to obtain infectious disease monitoring cleaned data, wherein the infectious disease monitoring cleaned data includes each infectious disease cleaning data, and each infectious disease cleaning data in the above infectious disease cleaning data corresponds to a data source and an update time. Thus, infectious disease monitoring cleaned data can be obtained. Then, based on each infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on each two infectious disease cleaning data that meet the preset matching conditions in the above infectious disease cleaning data to obtain each similarity matching result. Thus, the two infectious disease cleaning data with higher similarity in the above infectious disease cleaning data can be fused into one data. Then, based on the above similarity matching results and the above infectious disease cleaning data, target infectious disease structured data is generated. Thus, target infectious disease structured data can be obtained. Then, based on the above target infectious disease structured data, the information of each person to be prompted is determined. Thus, the personnel to whom the prompt information needs to be sent can be determined according to the obtained target infectious disease structured data. Finally, the preset prompt information is sent to each terminal corresponding to each of the above-mentioned personnel information to be prompted.Also, because data from different data sources and different data structures can be converted into structured data before being fused, the computing resources consumed when fusing the data can be reduced, and the data processing efficiency during data fusion can be improved.

[0110] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a multi-source heterogeneous data fusion device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0111] like Figure 2 As shown, the multi-source heterogeneous data fusion device 200 of some embodiments includes: an acquisition unit 201, a first generation unit 202, a second generation unit 203, a third generation unit 204, a data cleaning unit 205, a matching unit 206, a fourth generation unit 207, a determination unit 208, and a sending unit 209. The acquisition unit 201 is configured to acquire infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data, and infectious disease monitoring unstructured data; the first generation unit 202 is configured to generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data; the second generation unit 203 is configured to generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data; the third generation unit 204 is configured to generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data; the data cleaning unit 205 is configured to perform data cleaning processing on the infectious disease monitoring standardized data to obtain Infectious disease monitoring cleaning data, wherein the above-mentioned infectious disease monitoring cleaning data includes various infectious disease cleaning data, and each infectious disease cleaning data in the above-mentioned various infectious disease cleaning data corresponds to a data source and an update time; a matching unit 206 is configured to perform similarity matching on each two infectious disease cleaning data in the above-mentioned various infectious disease cleaning data that meet preset matching conditions based on the various infectious disease cleaning data included in the above-mentioned infectious disease monitoring cleaning data, to obtain various similarity matching results; a fourth generating unit 207 is configured to generate target infectious disease structured data based on the above-mentioned various similarity matching results and the above-mentioned various infectious disease cleaning data; a determining unit 208 is configured to determine each person information to be prompted based on the above-mentioned target infectious disease structured data; a sending unit 209 is configured to send the preset prompt information to each terminal corresponding to the above-mentioned each person information to be prompted.

[0112] It can be understood that the units described in the multi-source heterogeneous data fusion device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the multi-source heterogeneous data fusion device 200 and the units included therein, and will not be described in detail here.

[0113] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0114] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0115] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0116] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0117] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0118] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0119] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains infectious disease monitoring data, wherein the above-mentioned infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data and infectious disease monitoring unstructured data; generates infectious disease structured data based on the infectious disease monitoring semi-structured data included in the above-mentioned infectious disease monitoring data; generates infectious disease label structured data based on the infectious disease monitoring unstructured data included in the above-mentioned infectious disease monitoring data; generates infectious disease monitoring standardized data based on the above-mentioned infectious disease structured data, the above-mentioned infectious disease label structured data and the infectious disease monitoring structured data included in the above-mentioned infectious disease monitoring data; and generates infectious disease monitoring standardization data based on the above-mentioned infectious disease monitoring standardization data. The infectious disease monitoring cleaning data is cleaned and processed to obtain infectious disease monitoring cleaning data, wherein the infectious disease monitoring cleaning data includes various infectious disease cleaning data, and each infectious disease cleaning data in the various infectious disease cleaning data corresponds to a data source and an update time; based on the various infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on every two infectious disease cleaning data in the various infectious disease cleaning data that meet preset matching conditions to obtain various similarity matching results; based on the various similarity matching results and the various infectious disease cleaning data, target infectious disease structured data is generated; based on the target infectious disease structured data, information on various persons to be prompted is determined; and the preset prompt information is sent to various terminals corresponding to the various information on various persons to be prompted.

[0120] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a first generation unit, a second generation unit, a third generation unit, a data cleaning unit, a matching unit, a fourth generation unit, a determination unit, and a sending unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases, for example, the acquisition unit may also be described as a "unit for acquiring infectious disease monitoring data".

[0123] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0124] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A multi-source heterogeneous data fusion method, comprising: Acquiring infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data, and infectious disease monitoring unstructured data; Generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data; Generate infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data; Generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data; Performing data cleaning processing on the infectious disease monitoring standardized data to obtain infectious disease monitoring cleaned data, wherein the infectious disease monitoring cleaned data includes individual infectious disease cleaned data, and each infectious disease cleaned data in the individual infectious disease cleaned data corresponds to a data source and an update time; Based on each infectious disease cleaning data included in the infectious disease monitoring cleaning data, similarity matching is performed on every two infectious disease cleaning data that meet a preset matching condition in the each infectious disease cleaning data to obtain each similarity matching result; Generate target infectious disease structured data based on the respective similarity matching results and the respective infectious disease cleansing data; Based on the target infectious disease structured data, determine the information of each person to be notified; The preset prompt information is sent to each terminal corresponding to each person information to be prompted.

2. The method according to claim 1, wherein: The generating infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data includes: Performing data parsing on the infectious disease monitoring semi-structured data to obtain data sets of various infectious disease fields; For each infectious disease field data set in the various infectious disease field data sets, performing data conversion processing on the infectious disease field data set to obtain infectious disease field structured data; The obtained structured data of each infectious disease field are integrated to obtain infectious disease structured data.

3. The method according to claim 1, wherein: The generating of infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data and the infectious disease monitoring structured data included in the infectious disease monitoring data includes: Integrating the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data to obtain infectious disease integrated structured data; Performing data conversion processing on the infectious disease integrated structured data to obtain infectious disease converted structured data; Generate infectious disease encrypted structured data based on the infectious disease conversion structured data; The infectious disease encrypted structured data is subjected to data standardization processing to obtain infectious disease monitoring standardized data.

4. The method according to claim 1, wherein: The infectious disease monitoring unstructured data includes an infectious disease text dataset, an infectious disease image dataset, an infectious disease audio dataset, and an infectious disease imaging dataset; And the generating of infectious disease label structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data includes: Based on the infectious disease audio data set included in the infectious disease monitoring unstructured data, data conversion processing is performed on each infectious disease audio data included in the infectious disease audio data set to obtain an audio text data set, wherein each audio text data in the audio text data set corresponds to personnel identity information; Integrate the audio text dataset and the infectious disease text dataset included in the infectious disease monitoring unstructured data to obtain an infectious disease text integrated dataset; For each infectious disease text integration data in the infectious disease text integration data set, performing keyword extraction processing on the infectious disease text integration data set to obtain a keyword data set; Generate infectious disease text structured data based on the obtained keyword data sets; Performing image recognition processing on the infectious disease image dataset included in the infectious disease monitoring unstructured data to obtain an image recognition result dataset; Generate infectious disease image structured data based on the infectious disease image dataset and the image recognition result dataset; Performing recognition processing on the infectious disease image data set included in the infectious disease monitoring unstructured data to obtain an image recognition result data set; Generate infectious disease image structured data based on the infectious disease image dataset and the image recognition result dataset; The infectious disease text structured data, the infectious disease image structured data and the infectious disease video structured data are integrated and processed to obtain infectious disease label structured data.

5. The method according to claim 1, wherein: Each infectious disease cleaning data in the infectious disease cleaning data corresponds to each field, data source and update time, and each field in the infectious disease cleaning data corresponds to a field value; And generating target infectious disease structured data based on the similarity matching results and the infectious disease cleansing data includes: For each of the similarity matching results, in response to determining that the similarity matching result satisfies a preset similarity condition, performing the following steps: Determine two infectious disease cleaned data corresponding to the similarity matching results in the respective infectious disease cleaned data as two infectious disease cleaned data to be compared, wherein each of the two infectious disease cleaned data to be compared corresponds to each field, and each of the two infectious disease cleaned data to be compared includes each field value corresponding to each field; For each of the various fields described, perform the following steps: determining the field as a target field; Determine two field values ​​corresponding to the target field in each field value included in the two infectious disease cleaning data to be compared as two field values ​​to be compared; Performing data comparison processing on the two to-be-compared field values ​​to obtain a data comparison result; In response to determining that the data comparison result meets a preset comparison result condition, the following steps are performed: Based on the two to-be-compared field values ​​corresponding to the data comparison result, two weight data corresponding to the two to-be-compared field values ​​are determined; Based on the two weight data, generating target weight data; Determine the to-be-compared field value corresponding to the target weight data among the two to-be-compared field values ​​as the target field value; Generate target structured data based on the determined target field values; The generated target structured data are combined into target infectious disease structured data.

6. A multi-source heterogeneous data fusion device, comprising: An acquisition unit is configured to acquire infectious disease monitoring data, wherein the infectious disease monitoring data includes infectious disease monitoring structured data, infectious disease monitoring semi-structured data, and infectious disease monitoring unstructured data; A first generating unit is configured to generate infectious disease structured data based on the infectious disease monitoring semi-structured data included in the infectious disease monitoring data; A second generating unit is configured to generate infectious disease tag structured data based on the infectious disease monitoring unstructured data included in the infectious disease monitoring data; a third generating unit configured to generate infectious disease monitoring standardized data based on the infectious disease structured data, the infectious disease label structured data, and the infectious disease monitoring structured data included in the infectious disease monitoring data; A data cleaning unit is configured to perform data cleaning processing on the infectious disease monitoring standardized data to obtain infectious disease monitoring cleaned data, wherein the infectious disease monitoring cleaned data includes individual infectious disease cleaned data, and each infectious disease cleaned data in the individual infectious disease cleaned data corresponds to a data source and an update time; a matching unit configured to perform similarity matching on each two infectious disease cleaning data that meet a preset matching condition in each infectious disease cleaning data included in the infectious disease monitoring cleaning data, and obtain each similarity matching result; a fourth generating unit, configured to generate target infectious disease structured data based on the respective similarity matching results and the respective infectious disease cleansing data; A determination unit, configured to determine information of each person to be notified based on the target infectious disease structured data; The sending unit is configured to send the preset prompt information to each terminal corresponding to the information of each person to be prompted.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images