Public health information authenticity evaluation system based on artificial intelligence

Abstract

The invention belongs to the technical field of artificial intelligence service, and discloses a public health information authenticity evaluation system based on artificial intelligence. A data set needing to be checked and a public health data set are collected and preprocessed, the information set needing to be checked comprises first medicine data, first health care data and first rehabilitation data, and the public health data comprises second medicine data, second health care data and second rehabilitation data; comparing and analyzing the data set to be checked and the public health data set to obtain a content reference value, and classifying to obtain a classification result; analyzing the classification result to obtain information evaluation reference values, and classifying the information evaluation reference values to obtain a decision information set; and displaying the decision information set, and analyzing the decision information set to obtain the periodic information reference table, and generally, the method has the remarkable advantages of good auxiliary working effect, high auxiliary decision degree and strong information processing capability.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence service technology, and more specifically, to an artificial intelligence-based public health information authenticity assessment system. Background Art

[0002] Public health and general Medical Services There is a certain difference. In order to allocate public health resources fairly, efficiently and reasonably, we must clarify what public health is. The American Committee of Rural and Urban Health Administrators defines public health as: Public health is the science and art of preventing disease, prolonging life and promoting physical and mental health through evaluation, policy development and safeguards. With the rapid development of my country's economy, people are paying more and more attention to public health. Due to the diversity, complexity and professionalism of public health itself, it is difficult for most non-professionals to have scientific and professional public health knowledge. At present, people need to obtain public health knowledge mostly from self-media platforms or online search engines, but with the diversified development of media platforms, a lot of false public health information knowledge has been released. Therefore, how to identify and solve the release of false public health information knowledge has become a major problem in today's society.

[0003] The patent application with the publication number CN116266301A discloses a method and system for verifying the authenticity of basic public health services. It uses information technology to automatically verify the authenticity of patients and services through data. It can replace most of the manual authenticity verification work of telephone calls with automatic data analysis of the information system, reducing labor costs and time costs. Compared with the current manual authenticity verification of basic public health service calls, it can significantly improve quality control efficiency and accuracy, thereby promoting the improvement and improvement of the quality of basic public health services.

[0004] However, although the above-mentioned method and system for verifying the authenticity of basic public health services has achieved the purpose of verifying the authenticity of public health services to a certain extent by screening manual calls through information technology, in today's situation, how to reduce the spread of false public health information is an urgent issue that needs to be addressed. The spread of false public health information can easily cause uninformed people to suffer physical damage due to the use of incorrect medical methods, and false public health information often contains illegal sales of medical supplies. If it is not resolved in time, it will cause serious physical and property losses to ordinary people.

[0005] In view of this, the present invention proposes an artificial intelligence-based public health information authenticity assessment system to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising: A data collection module is used to collect and pre-process a data set to be checked and a public health data set, wherein the information set to be checked includes first medical data, first health care data and first rehabilitation data, and the public health data includes second medical data, second health care data and second rehabilitation data; Furthermore, the methods for collecting the datasets to be verified and the public health datasets include: By connecting to news platforms, social platforms and forum platforms, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the first medical data, the first health care data and the first rehabilitation data; By connecting to CNKI, official media platforms of governments at all levels, and official websites of governments at all levels, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the second medicine data, the second health care data and the second rehabilitation data; Preprocessing methods include data cleaning and data denoising; A feature processing module is used to compare and analyze the data set to be checked and the public health data set to obtain content reference values, classify the content reference values, and obtain classification results; Furthermore, the steps of performing comparative analysis include: Q1: Based on the NLP natural speech processing library, the texts of the dataset to be verified and the public health dataset are split into phrases, and meaningless words in the phrases are removed; Q2: Preset the vocabulary threshold, count the frequency of each word in the text, and obtain the vocabulary vector. When the vocabulary vector is greater than the vocabulary threshold, mark the vocabulary vector as the key vocabulary vector. Q3: By substituting into the calculation formula: Get the content reference value, where and are the key vocabulary vectors of the dataset to be verified and the public health dataset, respectively. The key word vector and The dot product of and They are respectively the key word vectors and The module length; By substituting into the calculation formula: Get the key word vector and The dot product of is calculated by substituting: and Get the key word vectors respectively and The module length; Furthermore, the methods for classifying content reference values ​​include: A classification threshold interval (A1, A2) is preset. When the content reference value is less than A1, data invalid information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A1 and less than A2, data related information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A2, data strong related information is sent to the data evaluation module through the communication unit. The invalid data information includes the invalid data number, the data related information includes the request response and the data number that needs to be processed by the data evaluation module, and the data strong related information includes the request response and the data number that needs to be processed by the data evaluation module first; Pack invalid data information, data related information and data strongly related information to obtain classification results; A data evaluation module is used to analyze the classification results, obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; Further, the steps of performing the analysis include: W1: When the received information is invalid data, it will not be processed; W2: When the received information is data-related information and data-strongly related information, data-strongly related information is processed first; W3: Based on the logistic regression model, the data sets to be checked and the public health data sets corresponding to the data-related information or data-strongly-related information are input into the logistic regression model, and the information evaluation reference value is output; Furthermore, the information evaluation reference values ​​are classified as follows: Preset the authenticity threshold interval (B1, B2), when the information evaluation reference value is less than B1, send a data false SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B1 and less than B2, send a data doubt SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B2, send a data true SMS to the feedback processing module through the communication unit; The SMS message about false data includes the following: the content of the dataset to be verified is false public health information, and the staff is required to contact the publisher as soon as possible to delete and modify it, and to release rumor-refuting information through official media. The SMS message about questionable data includes the following: the content of the dataset to be verified is questionable, and the staff is required to conduct manual verification. The SMS message about authentic data includes the following: the content of the dataset to be verified is true public health information. Packing false data SMS, questionable data SMS and real data SMS to obtain a decision information set; A feedback processing module is used to display the decision information set and analyze the decision information set to obtain a period information reference table; Furthermore, the methods for analyzing the decision information set include: Obtain a decision information set within a preset time unit, and count the number of false SMS messages, SMS messages with questionable data, and SMS messages with authentic data respectively; By substituting into the calculation formula: Get the false SMS reference value, where The number of false SMS messages. is the total number of SMS messages; Based on the Excel spreadsheet tool, the total number of SMS messages and the reference value of false SMS messages are used to generate a periodic information reference table based on the preset time unit; Further, S1: collecting and preprocessing a data set to be checked and a public health data set, wherein the information set to be checked includes first medical data, first health care data and first rehabilitation data, and the public health data includes second medical data, second health care data and second rehabilitation data; S2: Compare and analyze the dataset to be checked and the public health dataset to obtain content reference values, classify them, and obtain classification results; S3: Analyze the classification results to obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; S4: Display the decision information set, and analyze the decision information set to obtain a period information reference table.

[0007] The technical effects and advantages of the public health information authenticity assessment system based on artificial intelligence of the present invention are as follows: Through the data acquisition module, the present invention can collect a large amount of public health information-related content in a short period of time. Compared with previous manual collection, it not only greatly reduces time and labor costs, but also greatly improves the comprehensiveness, convenience and accuracy of information collection. Through the feature processing module, it is very convenient to conduct preliminary verification of the public health information-related content circulated in the media. The obtained classification results can be used as an important basis for subsequent processing, reducing the difficulty of analysis. By analyzing the classification results, false public health information can be identified in a targeted manner, reducing the operating time of the system. The obtained decision information set can assist staff in making quick decisions based on the content of public health information, greatly improving work efficiency. The periodic information reference table can intuitively display the number of public health information-related information releases and the number of false information within the period, which is convenient for staff to intuitively understand the status of public health information in society. Generally speaking, the present invention has the significant advantages of good auxiliary work effect, high degree of auxiliary decision-making and strong information processing capability. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of an artificial intelligence-based public health information authenticity assessment system of the present invention; Figure 2 This is a schematic diagram of an artificial intelligence-based public health information authenticity assessment method of the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] Example 1 See also Figure 1 As shown, the public health information authenticity assessment system based on artificial intelligence described in this embodiment includes: A data collection module is used to collect and pre-process a data set to be checked and a public health data set, wherein the information set to be checked includes first medical data, first health care data and first rehabilitation data, and the public health data includes second medical data, second health care data and second rehabilitation data; Furthermore, the methods for collecting the datasets to be verified and the public health datasets include: By connecting to news platforms, social platforms and forum platforms, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the first medical data, the first health care data and the first rehabilitation data; By connecting to CNKI, official media platforms of governments at all levels, and official websites of governments at all levels, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the second medicine data, the second health care data and the second rehabilitation data; It should be explained that based on the Speechnotes speech recognition software, audio and video content can be converted into text format; Preprocessing methods include data cleaning and data denoising; A feature processing module is used to compare and analyze the data set to be checked and the public health data set to obtain content reference values, classify the content reference values, and obtain classification results; Further, the steps of performing comparative analysis include: Q1: Based on the NLP natural speech processing library, the texts of the dataset to be verified and the public health dataset are split into phrases, and meaningless words in the phrases are removed; It needs to be explained that meaningless words include words that have no expressive meaning; Q2: Preset the vocabulary threshold, count the frequency of each word in the text, and obtain the vocabulary vector. When the vocabulary vector is greater than the vocabulary threshold, mark the vocabulary vector as the key vocabulary vector. Q3: By substituting into the calculation formula: Get the content reference value, where and are the key vocabulary vectors of the dataset to be verified and the public health dataset, respectively. The key word vector and The dot product of and They are respectively the key word vectors and The module length; By substituting into the calculation formula: Get the key word vector and The dot product of is calculated by substituting: and Get the key word vectors respectively and The module length; Further, the methods for classifying content reference values ​​include: A classification threshold interval (A1, A2) is preset. When the content reference value is less than A1, data invalid information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A1 and less than A2, data related information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A2, data strong related information is sent to the data evaluation module through the communication unit. The invalid data information includes the invalid data number, the data related information includes the request response and the data number that needs to be processed by the data evaluation module, and the data strong related information includes the request response and the data number that needs to be processed by the data evaluation module first; Pack invalid data information, data related information and data strongly related information to obtain classification results; A data evaluation module is used to analyze the classification results, obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; Further, the steps of performing the analysis include: W1: When the received information is invalid data, it will not be processed; W2: When the received information is data-related information and data-strongly related information, data-strongly related information is processed first; W3: Based on the logistic regression model, the data sets to be checked and the public health data sets corresponding to the data-related information or data-strongly-related information are input into the logistic regression model, and the information evaluation reference value is output; Further, the methods for classifying the information evaluation reference values ​​include: Preset the authenticity threshold interval (B1, B2), when the information evaluation reference value is less than B1, send a data false SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B1 and less than B2, send a data doubt SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B2, send a data true SMS to the feedback processing module through the communication unit; The SMS message about false data includes the following: the content of the dataset to be verified is false public health information, and the staff is required to contact the publisher as soon as possible to delete and modify it, and to release rumor-refuting information through official media. The SMS message about questionable data includes the following: the content of the dataset to be verified is questionable, and the staff is required to conduct manual verification. The SMS message about authentic data includes the following: the content of the dataset to be verified is true public health information. Packing false data SMS, questionable data SMS and real data SMS to obtain a decision information set; A feedback processing module is used to display the decision information set and analyze the decision information set to obtain a period information reference table; Further, the methods for analyzing the decision information set include: Obtain a decision information set within a preset time unit, and count the number of false SMS messages, SMS messages with questionable data, and SMS messages with authentic data respectively; It needs to be explained that the preset time unit is based on months, quarters or years; By substituting into the calculation formula: Get the false SMS reference value, where The number of false SMS messages. is the total number of SMS messages; Based on the Excel spreadsheet tool, the total number of SMS messages and the reference value of false SMS messages are used to generate a periodic information reference table based on the preset time unit; The present embodiment has the beneficial effect that, through the data acquisition module, a large amount of content related to public health information can be collected in a targeted manner in a short period of time. Compared with the previous manual collection, it not only greatly reduces the time and labor costs, but also greatly improves the comprehensiveness, convenience and accuracy of information collection. Through the feature processing module, it is very convenient to conduct a preliminary check on the content related to public health information circulated in the media. The obtained classification results can be used as an important basis for subsequent processing, reducing the difficulty of analysis. By analyzing the classification results, false public health information can be identified in a targeted manner, reducing the operating time of the system. The obtained decision information set can assist the staff to make quick decisions based on the content of public health information, greatly improving work efficiency. The periodic information reference table can intuitively display the number of public health information-related information releases and the number of false ones within the period, so that the staff can intuitively understand the status of public health information in society. In general, the present invention has the significant advantages of good auxiliary work effect, high degree of auxiliary decision-making and strong information processing capability.

[0011] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a method for evaluating the authenticity of public health information based on artificial intelligence is provided, including: S1: collecting a data set to be verified and a public health data set, and preprocessing them, the information set to be verified includes first medical data, first health care data and first rehabilitation data, and the public health data includes second medical data, second health care data and second rehabilitation data; S2: Compare and analyze the dataset to be checked and the public health dataset to obtain content reference values, classify them, and obtain classification results; S3: Analyze the classification results to obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; S4: Display the decision information set, and analyze the decision information set to obtain a period information reference table.

[0012] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the above-mentioned artificial intelligence-based public health information authenticity assessment method is implemented.

[0013] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for evaluating the authenticity of public health information based on artificial intelligence in the embodiment of this application, based on the method for evaluating the authenticity of public health information based on artificial intelligence introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the method for evaluating the authenticity of public health information based on artificial intelligence in the embodiment of this application, it belongs to the scope of protection of this application.

[0014] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0015] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An artificial intelligence-based public health information authenticity assessment system, characterized in that: include: A data collection module is used to collect and pre-process a data set to be checked and a public health data set, wherein the information set to be checked includes first medical data, first health care data and first rehabilitation data, and the public health data includes second medical data, second health care data and second rehabilitation data; The feature processing module is used to compare and analyze the data set to be checked and the public health data set to obtain content reference values, classify them, and obtain classification results; A data evaluation module is used to analyze the classification results, obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; The feedback processing module is used to display the decision information set and analyze the decision information set to obtain a period information reference table.

2. According to claim 1, a public health information authenticity assessment system based on artificial intelligence is characterized in that: Methods for collecting datasets that need to be checked and public health datasets include: By connecting to news platforms, social platforms and forum platforms, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the first medical data, the first health care data and the first rehabilitation data; By connecting to CNKI, official media platforms of governments at all levels, and official websites of governments at all levels, we collect articles, audio and video content related to medicine, health care and rehabilitation, and obtain the second medicine data, the second health care data and the second rehabilitation data; Preprocessing methods include data cleaning and data denoising.

3. The public health information authenticity assessment system based on artificial intelligence according to claim 2 is characterized in that: The steps for comparative analysis include: Q1: Based on the NLP natural speech processing library, the texts of the dataset to be verified and the public health dataset are split into phrases, and meaningless words in the phrases are removed; Q2: Preset the vocabulary threshold, count the frequency of each word in the text, and obtain the vocabulary vector. When the vocabulary vector is greater than the vocabulary threshold, mark the vocabulary vector as the key vocabulary vector. Q3: By substituting into the calculation formula: Get the content reference value, where and are the key vocabulary vectors of the dataset to be verified and the public health dataset, respectively. The key word vector and The dot product of and They are respectively the key word vectors and The module length; By substituting into the calculation formula: Get the key word vector and The dot product of is calculated by substituting: and Get the key word vectors respectively and The mold length.

4. The public health information authenticity assessment system based on artificial intelligence according to claim 3 is characterized in that: Ways to categorize content references include: A classification threshold interval (A1, A2) is preset. When the content reference value is less than A1, data invalid information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A1 and less than A2, data related information is sent to the data evaluation module through the communication unit. When the content reference value is greater than A2, data strong related information is sent to the data evaluation module through the communication unit. The invalid data information includes the invalid data number, the data related information includes the request response and the data number that needs to be processed by the data evaluation module, and the data strong related information includes the request response and the data number that needs to be processed by the data evaluation module first; Pack invalid data information, data-related information, and data-strongly related information to obtain classification results.

5. The artificial intelligence-based public health information authenticity assessment system according to claim 4, characterized in that: The steps to perform the analysis include: W1: When the received information is invalid data, it will not be processed; W2: When the received information is data-related information and data-strongly related information, data-strongly related information is processed first; W3: Based on the logistic regression model, the data sets to be verified and the public health data sets corresponding to the data-related information or data-strongly related information are input into the logistic regression model, and the information evaluation reference value is output.

6. The artificial intelligence-based public health information authenticity assessment system according to claim 5, characterized in that: Ways to categorize information evaluation reference values ​​include: Preset the authenticity threshold interval (B1, B2), when the information evaluation reference value is less than B1, send a data false SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B1 and less than B2, send a data doubt SMS to the feedback processing module through the communication unit, when the information evaluation reference value is greater than B2, send a data true SMS to the feedback processing module through the communication unit; The SMS message about false data includes the following: the content of the dataset to be verified is false public health information, and the staff is required to contact the publisher as soon as possible to delete and modify it, and to release rumor-refuting information through official media. The SMS message about questionable data includes the following: the content of the dataset to be verified is questionable, and the staff is required to conduct manual verification. The SMS message about authentic data includes the following: the content of the dataset to be verified is true public health information. Pack the SMS messages with false data, SMS messages with questionable data and SMS messages with real data to get a decision information set.

7. The artificial intelligence-based public health information authenticity assessment system according to claim 6, characterized in that: Ways to analyze the decision information set include: Obtain a decision information set within a preset time unit, and count the number of false SMS messages, SMS messages with questionable data, and SMS messages with authentic data respectively; By substituting into the calculation formula: Get the false SMS reference value, where The number of false SMS messages. is the total number of SMS messages; Based on the Excel spreadsheet tool, the total number of SMS messages and the reference value of false SMS messages are used to generate a periodic information reference table based on the preset time unit.

8. A method for evaluating the authenticity of public health information based on artificial intelligence, implemented according to the system for evaluating the authenticity of public health information based on artificial intelligence according to claims 1-7, characterized in that: S1: Collect the data set to be checked and the public health data set, and perform preprocessing. The information set to be checked includes the first medical data, the first health care data and the first rehabilitation data. The public health data includes the second medical data, the second health care data and the second rehabilitation data. S2: Compare and analyze the dataset to be checked and the public health dataset to obtain content reference values, classify them, and obtain classification results; S3: Analyze the classification results to obtain information evaluation reference values, classify the information evaluation reference values, and obtain a decision information set; S4: Display the decision information set, and analyze the decision information set to obtain a period information reference table.

Images