Method, device, equipment and medium for detecting epidemic spread information

Abstract

The present invention discloses a method, apparatus, device, and medium for detecting epidemic spread information. The method includes obtaining user-provided online drug sales data for at least one drug corresponding to the same disease within a historical time period; extracting sales data and spatial data from the online drug sales data; generating a time vector based on the sales data; generating a space vector based on the spatial data; and determining predicted spatiotemporal information for the disease based on the time vector and the space vector. This embodiment of the present invention can accurately predict the spread of an epidemic based on drug sales data.

Description

Technical Field

[0001] The present invention relates to the field of epidemic control technology, and in particular to a method, device, equipment and medium for detecting epidemic spread information. Background Art

[0002] With the acceleration of globalization and the continuous development of human society, the speed and scope of epidemic spread are increasing, which brings huge challenges to public health and social economy. Therefore, it is necessary to accurately predict the spread of epidemics.

[0003] Currently, epidemic forecasting relies on traditional statistical models and manual analysis to predict the future spread of diseases.

[0004] However, the above prediction methods have the defects of low efficiency and low prediction accuracy. Summary of the Invention

[0005] The present invention provides a method, device, equipment and medium for detecting epidemic spread information. The embodiments of the present invention can accurately predict the spread of epidemics based on drug sales data.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting epidemic spread information, the method comprising:

[0007] Obtain online drug sales data provided by users for at least one drug corresponding to the same disease within a historical period;

[0008] Extract sales data and spatial data from online pharmaceutical sales data;

[0009] Generate a time vector based on sales data;

[0010] Generate spatial vectors based on spatial data;

[0011] According to the time vector and space vector, the predicted spatiotemporal information of the disease is determined.

[0012] In a second aspect, an embodiment of the present invention further provides a device for detecting epidemic spread information, the device comprising:

[0013] A data acquisition module is used to obtain online drug sales data provided by users in a historical period of time for at least one drug corresponding to the same disease;

[0014] Data extraction module, used to extract sales data and spatial data from online drug sales data;

[0015] A time vector generation module is used to generate a time vector based on sales data;

[0016] A space vector generation module is used to generate a space vector according to the space data;

[0017] The prediction module is used to determine the predicted spatiotemporal information of the disease based on the time vector and the space vector.

[0018] In a third aspect, an embodiment of the present invention further provides an epidemic spread information detection device, the epidemic spread information detection device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the epidemic spread information detection method of any embodiment of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the epidemic transmission information detection method of any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention, by acquiring online drug sales data within a historical time period, can accumulate drug sales data through an online platform, providing a data basis for epidemic spread prediction; by extracting sales data and spatial data, it can capture drug sales information from two dimensions of time and space respectively; by generating time vectors, it can model the temporal dynamics of disease spread, thereby revealing the cyclical changes and trends of epidemic spread, and providing time series data support for predicting future epidemic change trends; by generating space vectors, it can model the spatial distribution of epidemic spread, revealing the spread differences in different regions, and providing a basis for the analysis of the geographical characteristics of epidemic spread; by combining time vectors and space vectors, it can realize the spatiotemporal prediction of epidemic spread, and provide the epidemic spread situation at a certain time and place in the future.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flowchart of a method for detecting epidemic spread information provided by an embodiment of the present invention;

[0027] Figure 2 A flowchart of a method for detecting epidemic spread information provided by an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of a space matrix provided by an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of a time series downsampling module provided in an embodiment of the present invention;

[0030] Figure 5 A schematic diagram of a temporal image encoder provided by an embodiment of the present invention;

[0031] Figure 6 A schematic diagram of a sequential DiT module provided in an embodiment of the present invention;

[0032] Figure 7 A schematic structural diagram of an epidemic spread information detection device provided by an embodiment of the present invention;

[0033] Figure 8 A schematic structural diagram of an epidemic spread information detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of online drug sales data, user purchase records and user purchase behaviors provided by users are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] Figure 1 This is a flow chart of a method for detecting epidemic spread information provided by an embodiment of the present invention. This embodiment of the present invention is applicable to epidemic spread information detection. This method can be performed by an epidemic spread information detection device, which can be implemented in the form of hardware and / or software.

[0038] See also Figure 1 The epidemic spread information detection method shown includes:

[0039] S101. Obtain online drug sales data provided by users for at least one drug corresponding to the same disease within a historical period.

[0040] The same disease can be treated with multiple types of medications. For example, disease A can be treated with medication A, medication B, and / or medication C. A single medication cannot fully represent the spread of a disease. Therefore, obtaining user-provided online medication sales data for at least one medication corresponding to the same disease over a historical period can provide a comprehensive understanding of which medications were used to treat the disease over that period.

[0041] Online drug sales data refers to daily drug sales data collected through online platforms, for example, drug sales data collected on January 1, 2, and 3. This data can include the number of clicks on the drug detail page, the time the drug detail page was opened, the number of orders placed, the IP address that viewed the drug detail page, and the delivery address. Online drug sales data can be used to indirectly analyze user behavior and infer disease-related drug demand and potential distribution areas.

[0042] S102. Extract sales data and spatial data from online drug sales data.

[0043] Sales data may refer to data related to drug usage within online drug sales data. Sales data may include the number of clicks on a drug's details page, the time the drug's details page was opened, and the number of orders placed. Analysis of sales data can reflect user drug usage and purchasing intentions. For example, sales data may include: on January 1st, drug X's details page had XX clicks, the time the drug's details page was opened was YY, and the number of orders placed was ZZ; and on January 2nd, drug X's details page had XXX clicks, the time the drug's details page was opened was YYY, and the number of orders placed was ZZZ.

[0044] Spatial data can refer to location-related data within online drug sales data. Spatial data can include IP addresses and delivery addresses for browsing drug detail pages. Analyzing spatial data can reveal the geographic spread of diseases and hotspots. For example, spatial data might include the IP addresses and delivery addresses for browsing drug detail pages for drug X on January 1st, where IP addresses include X, Y, and Z, and delivery addresses include A, B, and C; and the IP addresses and delivery addresses for browsing drug detail pages for drug X on January 2nd, where IP addresses include XX, YY, and ZZ, and delivery addresses include AA, BB, and CC.

[0045] S103. Generate a time vector based on the sales data.

[0046] The time vector can refer to a feature vector generated by introducing timestamps into sales data. By applying formula calculations and normalization to sales data, sales data reflecting user behavior is quantified into feature values ​​along the time dimension. Since sales data itself does not exist in a time series, by arranging sales data in a specific chronological order, a time series can be constructed, thereby generating a time vector.

[0047] S104: Generate a spatial vector based on the spatial data.

[0048] A spatial vector can refer to a feature vector generated based on spatial data. This vector includes information about the spread of a disease associated with a geographic location. By mapping the spatial data of IP addresses and shipping addresses used to browse drug detail pages to a spatial matrix and then converting it into a feature vector, the spatial vector describes the distribution characteristics of the disease in geographic space. This spatial vector characterizes the probability of disease spread in different geographic locations and is used to predict the future spread of the disease.

[0049] S105. Determine predicted spatiotemporal information of the disease based on the time vector and the space vector.

[0050] Predicted spatiotemporal information can refer to information about the future time, geographic location, and probability of disease spread. Predicted spatiotemporal information about a disease can be generated by fusing time vectors and space vectors and combining them with a prediction model.

[0051] It can be seen that in the embodiment of the present application, by obtaining online drug sales data within a historical time period, the accumulation of drug sales data can be achieved through the online platform, providing a data basis for epidemic spread prediction; by extracting sales data and spatial data, the sales information of drugs can be captured from the two dimensions of time and space respectively; by generating time vectors, the temporal dynamics of disease spread can be modeled, thereby revealing the cyclical changes and trends of epidemic spread, and providing time series data support for predicting future epidemic change trends; by generating space vectors, the spatial distribution of epidemic spread can be modeled, revealing the spread differences in different regions, and providing a basis for the analysis of the geographical characteristics of epidemic spread; by combining time vectors and space vectors, the spatiotemporal prediction of epidemic spread can be achieved, and the epidemic spread situation at a certain time and place in the future can be provided.

[0052] The process of "generating a time vector based on sales data" has been refined to include "calculating the probability of disease concern based on multiple sales parameters and corresponding parameter values ​​included in the sales data; and generating a time vector based on the disease concern probability and the collection time of each parameter in the sales data," thereby improving the operation of epidemic transmission information detection. It should be noted that for portions not described in detail in this embodiment of the present invention, reference can be made to the descriptions of other embodiments. Figure 2 The present invention provides a flowchart of a method for detecting epidemic spread information.

[0053] See also Figure 2 The epidemic spread information detection method shown includes:

[0054] S201. Obtain online drug sales data provided by users for at least one drug corresponding to the same disease within a historical period.

[0055] S202. Extract sales data and spatial data from online drug sales data.

[0056] S203. Calculate the probability of disease attention based on multiple sales parameters and corresponding parameter values ​​included in the sales data.

[0057] The sales parameters may refer to the number of clicks on the drug details page, the time the drug details page was opened, and the number of orders placed in the sales data. The parameter values ​​may refer to the specific numerical values ​​of the sales parameters. For example, the sales parameters may refer to the number of clicks on the drug details page of drug X on January 1st as A; the time the drug details page of drug X was opened on January 1st as B; and the number of orders placed on January 1st as C. The number of clicks on the drug details page, the time the drug details page was opened, and the number of orders placed are sales parameters, and A, B, and C are parameter values.

[0058] The attention probability refers to the probability of interest in a particular drug. Calculating the attention probability can reveal the specific usage and purchasing intentions for the drug. A higher attention probability indicates a higher level of interest in the drug. The attention probability can be calculated using multiple sales parameters and their corresponding values.

[0059] S204: Generate a time vector based on the probability of disease attention and the collection time of each parameter in the sales data.

[0060] The collection time can refer to the timestamp information corresponding to each parameter in the sales data. The collection time is used to describe the temporal changes in each parameter value. Since sales data itself does not have a temporal feature, a time vector can be generated based on the disease probability of concern and the collection time of each parameter in the sales data.

[0061] S205: Generate a spatial vector based on the spatial data.

[0062] S206. Determine predicted spatiotemporal information of the disease based on the time vector and the space vector.

[0063] It can be seen that in this embodiment, by integrating multiple sales parameters and their corresponding parameter values, the user's attention and purchasing behavior towards drugs can be fully characterized, avoiding information bias caused by a single indicator; by calculating the attention probability of the disease, the key features of the user behavior can be extracted, and the complex original data can be converted into concise and meaningful numerical indicators; using the calculation method of attention probability, the correlation between different parameters can be captured, thereby improving the sensitivity to the disease transmission trend and the accuracy of the prediction; by combining the attention probability and the collection time, a time vector reflecting the dynamic changes in drug demand over time can be generated, supporting the time series analysis of epidemic spread.

[0064] In some embodiments, calculating the probability of disease concern based on multiple sales parameters and corresponding parameter values ​​included in the sales data includes:

[0065] The probability of attention for each disease is calculated based on the weight of each sales parameter on the drug and the parameter value corresponding to each sales parameter.

[0066] The weight can refer to the degree of influence of a sales parameter on drug awareness. A larger weight indicates a greater influence of the sales parameter on drug awareness; a smaller weight indicates a smaller influence. The weight can be set based on empirical values.

[0067] Sales parameters include the number of clicks on the drug details page, the time the drug details page is opened, and the number of orders. Among them, the number of clicks on the drug details page is positively correlated with the probability of attention, but when the drug details page is clicked too many times, there may be malicious clicks. Therefore, the relationship between the number of clicks on the drug details page and the probability of attention is a logarithmic positive correlation, which can reduce the problem of excessive amplification of the impact caused by too many clicks on the drug details page; the time the drug details page is opened and the probability of attention also show a positive correlation trend, but when the drug details page is opened for too long, it may be because the user forgets to close the details page after clicking on the drug details page. Therefore, the longer the drug details page is opened, the greater the impact on the probability of attention in the initial stage, but after exceeding a certain time threshold, the impact of the probability of attention decreases due to exponential decay; the number of orders and the probability of attention are linearly positively correlated. The greater the number of orders, the higher the probability of attention, and the fewer the number of orders, the lower the probability of attention.

[0068] In a specific example, the probability of interest for a disease is given by:

[0069]

[0070] In the formula, E(c, t, o) represents the probability of attention to a certain disease; c represents the parameter value of the number of clicks on the drug details page; t represents the parameter value of the time the drug details page is opened; o represents the parameter value of the number of orders; 0.3 represents the weight of the parameter value of the number of clicks on the drug details page; 0.2 represents the weight of the parameter value of the time the drug details page is opened; and 0.5 represents the weight of the number of orders.

[0071] It can be seen that in this embodiment, by assigning weights to sales parameters, it is possible to distinguish the importance of different sales parameters; by combining the parameter values ​​corresponding to the sales parameters, it is possible to quantify user behavior and make the numerical expression of the original data more accurate; by combining the weights and parameter values ​​of sales parameters, it is possible to accurately estimate the probability of disease attention.

[0072] In some embodiments, generating a space vector according to the spatial data includes:

[0073] Generate a spatial matrix based on the spatial data, where the position of each element in the matrix corresponds to the geographical location, and the element value of each element corresponds to the usage probability;

[0074] Generate a space vector based on a space matrix.

[0075] The spatial matrix may refer to a matrix used to describe the use of drugs in a geographical space, and the use probability may refer to the probability value of using each drug to treat a certain disease in a certain geographical location.

[0076] The spatial matrix may be input into a VAE (Variational Autoencoder) encoder to obtain a spatial vector, where the spatial vector is a two-dimensional vector.

[0077] In a specific example, Figure 3 A schematic diagram of a spatial matrix provided by an embodiment of the present invention can divide the predicted area into a 4*4 spatial matrix. Assuming that there is an IP address X for browsing the drug details page on January 1, the IP address X is converted to the geographic coordinates (2, 1); there is a delivery address Y on January 1, and the delivery address Y is converted to the geographic coordinates (3, 4). As long as there is an IP address and a delivery address for browsing the drug details page at a certain geographic location on a certain day, the initial usage probability corresponding to the geographic location is set to 1, and the assigned weights of the IP address and the delivery address for browsing the drug details page are 0.1 and 0.5 respectively, resulting in the following: Figure 3 For example, 0.1 in the second column of the third row indicates that the probability of using each drug to treat a disease in this region is 0.1. For example, 0.5 in the fourth column of the fifth row indicates that the probability of using each drug to treat a disease in this region is 0.5. Since the delivery address is more likely to be a disease transmission area than the IP address of the drug details page, the weight assigned to the delivery address can be set to five times the weight assigned to the IP address of the drug details page.

[0078] It can be seen that in this embodiment, by generating a spatial matrix from spatial data, a structured representation of spatial information can be achieved; by corresponding the position of each element in the matrix to the geographical location, accurate segmentation and positioning of the geographical space can be achieved; by corresponding the value of each element in the matrix to the usage probability, a quantitative description of the intensity of drug use or the probability of disease transmission in the geographical location can be achieved; by generating a spatial vector from the spatial matrix, compression and simplification of the representation of two-dimensional spatial data can be achieved, and by generating a spatial vector, a digital representation of spatial information can be achieved.

[0079] In some embodiments, generating a spatial matrix based on the spatial data includes:

[0080] extracting at least one spatial parameter from the spatial data;

[0081] According to the weight corresponding to each spatial parameter, the probability of using medicines for the same disease at the geographical location corresponding to each spatial parameter is calculated.

[0082] The spatial parameter may refer to a parameter set based on the IP address of the drug details page and the delivery address. For example, as long as the IP address of the drug details page and / or the delivery address exist at a certain geographic location, the spatial parameter of that geographic location is set to 1. The weights of the IP address of the drug details page and the delivery address are 0.1 and 0.5, respectively. If both the IP address of the drug details page and the delivery address exist at a certain geographic location, the weight corresponding to the spatial parameter of that geographic location is set to the weight of the delivery address.

[0083] It can be seen that in this embodiment, the extraction of spatial parameters can capture the characteristics of the geographical location and provide basic data for the generation of the spatial matrix in the subsequent steps; by assigning weights to each spatial parameter, the importance of different spatial characteristics can be quantified. The method of calculating the probability of use based on the spatial parameters and their weights can improve the accurate description of the distribution of drug use, thereby providing more accurate input for the prediction of disease spread.

[0084] In some embodiments, determining predicted spatiotemporal information of a disease based on a time vector and a space vector includes:

[0085] Determine the purchase probability of the disease medicine at each geographical location in the future time period based on the time vector and the space vector;

[0086] The predicted spatiotemporal information of the disease is determined based on the purchase probability of the disease's medicine at various geographical locations in the future time period; the predicted spatiotemporal information includes distribution time, distribution address and occurrence probability.

[0087] The purchase probability at each geographical location may refer to the probability of purchasing each drug for a particular disease at each geographical location. The purchase probability at each geographical location reflects the demand intensity of the drug in each geographical area and is used to predict the spread of the disease.

[0088] The distribution time refers to the predicted time period of disease spread in the future. The distribution time can refer to a specific day within the future time period.

[0089] The distribution address may refer to the geographical location range of the predicted disease spread, and may include specific cities and geographical coordinates.

[0090] Among them, the occurrence probability refers to the probability value of the disease spreading at each distribution time and each distribution address.

[0091] In a specific example, based on the time vector and the space vector, the purchase probability of a drug for a disease at each geographical location in a future time period can be determined by:

[0092] Since sales data is one-dimensional and spatial data is two-dimensional, it is necessary to convert the sales data into two-dimensional data. The sales data, the probability of attention, and the acquisition time of each parameter in the sales data are input into the time series downsampling module to obtain a multi-scale time series vector. This is then passed through the time series image encoder to obtain a time series two-dimensional vector. The time series two-dimensional vector can also be referred to as a time vector.

[0093] To accommodate the disease's transmission cycle, the time series downsampling module inputs sales data over a period of time and outputs multi-scale time series vectors for that period. The time series downsampling module can be composed of M layers of one-dimensional convolutional layers with a stride of 2, each layer outputting time series vectors of different scales, where each time series vector of different scales is a one-dimensional vector. Figure 4 A schematic diagram of a time series downsampling module provided in an embodiment of the present invention, wherein the first data may refer to sales data, and the right side of the figure represents time series vectors of different scales.

[0094] Time series vectors of different scales are input into the time series image encoder, which outputs a two-dimensional time series image vector. The time series vector is segmented according to a certain period and then concatenated to obtain a single-channel two-dimensional vector. This is then passed through a normalization layer to obtain a normalized single-channel two-dimensional vector. This two-dimensional vector is treated as a grayscale image and passed through a color filling network to generate a three-channel two-dimensional vector representing a color image. This three-channel two-dimensional vector is the two-dimensional time series image vector, which can also be referred to as a time vector. Figure 5 A schematic diagram of a time series image encoder provided in an embodiment of the present invention, wherein the top row of numbers in the figure represents the individual values ​​in the time series vector, indicating the value of the time series data at each time point, and the matrix in the middle of the figure may refer to the operation of segmenting and splicing time series vectors of different scales according to a period of 4 values ​​per row.

[0095] A spatial matrix generated according to spatial data is input into a VAE encoder to obtain a spatial two-dimensional vector, which may refer to a spatial vector.

[0096] By inputting the time vector, space vector, and random Gaussian noise into the time series DiT (Dynamic Information Transformer) module, the purchase probability of each drug for each disease at each geographical location in the future time period can be determined. By inputting random Gaussian noise into the embedding model, the noise embedding vector can be output, and each vector in the multi-scale time vector set is added together to obtain a new vector set. After passing through N layers of DiT layers, each DiT layer can include a temporal attention layer, a spatial attention layer, and a normalization layer. Figure 6A schematic diagram of a time-series DiT module provided by an embodiment of the present invention. Spatial vectors pass through a temporal attention layer, where spatial vector features are added to the DiT layer. Finally, the feature vector set output by the DiT layer passes through a scale fusion layer, which fuses feature vectors representing multiple scales to determine the purchase probability of a medication for a disease at various geographic locations in the future time period.

[0097] It can be seen that in this embodiment, by determining the purchase probability of medicines based on the time vector and the space vector, an accurate prediction of the demand for medicines can be achieved; by determining the predicted spatiotemporal information of the disease based on the purchase probability of medicines, a more accurate prediction of the disease transmission trend can be achieved, providing data support for public health decision-making; by providing the distribution time, distribution address and occurrence probability of the disease, a comprehensive assessment of the time, place and possibility of the future occurrence of the disease can be achieved.

[0098] Optionally, the predicted spatiotemporal information of the disease is determined based on the purchase probability of the disease drug at each geographical location in the future time period and the disease treatment relationship between the drug and the corresponding disease treatment. The disease treatment relationship between the drug and the corresponding disease treatment may refer to the relationship between which drugs can treat a certain disease.

[0099] In some embodiments, determining the purchase probability of a drug for a disease at each geographical location in a future time period based on the time vector and the space vector includes:

[0100] According to the time vector and the space vector, the purchase probability of the medicine for the disease at each geographical location in multiple future sub-time periods is determined; wherein the historical time period includes: multiple historical sub-time periods, and the historical sub-time periods correspond to the future sub-time periods one by one.

[0101] In a specific example, the historical time period may be January 1 to January 5, 2024, and the corresponding historical sub-time periods may be January 1, 2024, January 2, 2024, January 3, 2024, January 4, 2024, and January 5, 2024, that is, the historical sub-time period may be a specific day in the historical time period. When the historical time period is January 1 to January 5, 2024, the future time period may be January 1 to January 5, 2025, and the future sub-time periods may be January 1, 2025, January 2, 2025, January 3, 2025, January 4, 2025, and January 5, 2025, that is, the future sub-time period may be a specific day in the future time period. The one-to-one correspondence between the historical sub-time periods and the future sub-time periods may mean that the dates of the historical sub-time periods and the future sub-time periods also have a corresponding relationship. For example, when the historical sub-time period is January 1, 2024, the future sub-time period is January 1, 2025.

[0102] It can be seen that in this embodiment, by determining the purchase probability of drugs based on the time vector and the space vector, an accurate prediction of drug demand can be achieved; by subdividing the future time period into multiple sub-time periods and performing purchase probability prediction, a more detailed prediction of drug demand fluctuations can be achieved; by making a one-to-one correspondence between historical time periods and future sub-time periods, historical data can be effectively used to predict the purchase probability of future drugs, thereby improving the accuracy of the prediction.

[0103] Figure 7 A schematic diagram of the structure of an epidemic spread information detection device provided by an embodiment of the present invention. The embodiment of the present invention is applicable to the case of epidemic spread information detection. The device can execute the epidemic spread information detection method, and the device can be implemented in the form of hardware and / or software.

[0104] See also Figure 7 The epidemic spread information detection device shown includes: a data acquisition module 701, a data extraction module 702, a time vector generation module 703, a space vector generation module 704 and a prediction module 705, wherein:

[0105] The data acquisition module 701 is used to obtain online drug sales data provided by users within a historical period of at least one drug corresponding to the same disease;

[0106] Data extraction module 702, for extracting sales data and spatial data from online drug sales data;

[0107] A time vector generating module 703 is used to generate a time vector based on sales data;

[0108] A space vector generating module 704 is used to generate a space vector according to the space data;

[0109] The prediction module 705 is used to determine the predicted spatiotemporal information of the disease based on the time vector and the space vector.

[0110] The technical solution of the embodiment of the present invention, by acquiring online drug sales data within a historical time period, can accumulate drug sales data through an online platform, providing a data basis for epidemic spread prediction; by extracting sales data and spatial data, it can capture drug sales information from two dimensions of time and space respectively; by generating time vectors, it can model the temporal dynamics of disease spread, thereby revealing the cyclical changes and trends of epidemic spread, and providing time series data support for predicting future epidemic change trends; by generating space vectors, it can model the spatial distribution of epidemic spread, revealing the spread differences in different regions, and providing a basis for the analysis of the geographical characteristics of epidemic spread; by combining time vectors and space vectors, it can realize the spatiotemporal prediction of epidemic spread, and provide the epidemic spread situation at a certain time and place in the future.

[0111] In some embodiments, in terms of generating a time vector based on sales data, the time vector generating module 703 is specifically configured to:

[0112] Calculating the probability of disease attention based on multiple sales parameters and corresponding parameter values ​​included in the sales data;

[0113] A time vector is generated based on the probability of attention of the disease and the collection time of each parameter in the sales data.

[0114] In some embodiments, in calculating the probability of concern of a disease based on multiple sales parameters and corresponding parameter values ​​included in the sales data, the time vector generation module 703 is specifically configured to:

[0115] The probability of attention for each disease is calculated based on the weight of each sales parameter on the drug and the parameter value corresponding to each sales parameter.

[0116] In some embodiments, in terms of generating a space vector based on the spatial data, the space vector generating module 704 is specifically configured to:

[0117] Generate a spatial matrix based on the spatial data, where the position of each element in the matrix corresponds to the geographical location, and the element value of each element corresponds to the usage probability;

[0118] Generate a space vector based on a space matrix.

[0119] In some embodiments, in terms of generating a spatial matrix based on spatial data, the spatial vector generating module 704 is specifically configured to:

[0120] extracting at least one spatial parameter from the spatial data;

[0121] According to the weight corresponding to each spatial parameter, the probability of using medicines for the same disease at the geographical location corresponding to each spatial parameter is calculated.

[0122] In some embodiments, in determining predicted spatiotemporal information of a disease based on a time vector and a space vector, the prediction module 705 is specifically configured to:

[0123] Determine the purchase probability of the disease medicine at each geographical location in the future time period based on the time vector and the space vector;

[0124] The predicted spatiotemporal information of the disease is determined based on the purchase probability of the disease's medicine at various geographical locations in the future time period; the predicted spatiotemporal information includes distribution time, distribution address and occurrence probability.

[0125] In some embodiments, in determining the purchase probability of a drug for a disease at each geographical location in a future time period based on the time vector and the space vector, the prediction module 705 is specifically configured to:

[0126] According to the time vector and the space vector, the purchase probability of the medicine for the disease at each geographical location in multiple future sub-time periods is determined; wherein the historical time period includes: multiple historical sub-time periods, and the historical sub-time periods correspond to the future sub-time periods one by one.

[0127] The epidemic spread information detection device provided in the embodiment of the present invention can execute the epidemic spread information detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the epidemic spread information detection method.

[0128] Figure 8 A schematic structural diagram of an epidemic spread information detection device provided by an embodiment of the present invention.

[0129] like Figure 8 As shown, the epidemic spread information detection device 800 includes at least one processor 801 and a memory, such as a read-only memory (ROM) 802, a random access memory (RAM) 803, etc., which is communicatively connected to the at least one processor 801. The memory stores a computer program that can be executed by the at least one processor. The processor 801 can perform various appropriate actions and processes based on the computer program stored in the read-only memory (ROM) 802 or the computer program loaded from the storage unit 808 into the random access memory (RAM) 803. The RAM 803 can also store various programs and data required for the operation of the epidemic spread information detection device 800. The processor 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 808 is also connected to the bus 804.

[0130] Multiple components in the epidemic spread information detection device 800 are connected to an I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the epidemic spread information detection device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0131] Processor 801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processor, controller, microcontroller, etc. Processor 801 executes the various methods and processes described above, such as the epidemic spread information detection method.

[0132] In some embodiments, the epidemic spread information detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the epidemic spread information detection device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the processor 801, one or more steps of the epidemic spread information detection method described above can be performed. Alternatively, in other embodiments, the processor 801 can be configured to execute the epidemic spread information detection method by any other appropriate means (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide user interaction, the systems and techniques described herein can be implemented on an operational detection device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the epidemic spread information detection device. Other types of devices can also be used to provide user interaction; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by 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), a blockchain network, and the Internet.

[0138] A computing system may include clients and servers. The clients and servers are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within a cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS (Virtual Private Server) services.

[0139] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0140] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting epidemic spread information, characterized in that: The method comprises: Obtain online drug sales data provided by users for at least one drug corresponding to the same disease within a historical period; extracting sales data and spatial data from the online drug sales data; generating a time vector according to the sales data; Generating a spatial vector according to the spatial data includes: generating a spatial matrix according to the spatial data, wherein the position of each element in the matrix corresponds to a geographical location and the element value of each element corresponds to a usage probability; generating a spatial vector according to the spatial matrix; Determining predicted spatiotemporal information of the disease based on the time vector and the space vector, including: determining, based on the time vector and the space vector, a purchase probability of a drug for the disease at each geographical location in a future time period; determining predicted spatiotemporal information of the disease based on the purchase probability of the drug for the disease at each geographical location in the future time period; the predicted spatiotemporal information including distribution time, distribution address, and occurrence probability; The step of generating a spatial matrix according to the spatial data includes: extracting at least one spatial parameter from the spatial data; Calculating the use probability of a drug for the same disease at the geographical location corresponding to each of the spatial parameters according to the weight corresponding to each of the spatial parameters; The determining, based on the time vector and the space vector, the purchase probability of the drug for the disease at each geographical location in a future time period includes: Based on the time vector and the space vector, the purchase probability of the drug for the disease at each geographical location in multiple future sub-time periods is determined; wherein the historical time period includes: multiple historical sub-time periods, and the historical sub-time periods correspond to the future sub-time periods one by one.

2. The method according to claim 1, characterized in that Generating a time vector according to the sales data includes: Calculating the probability of concern of the disease based on a plurality of sales parameters and corresponding parameter values ​​included in the sales data; A time vector is generated according to the probability of attention of the disease and the collection time of each parameter in the sales data.

3. The method according to claim 2, characterized in that Calculating the probability of concern of the disease based on the multiple sales parameters and corresponding parameter values ​​included in the sales data, including: The probability of attention of each of the diseases is calculated based on the weight of each of the sales parameters to the drug and the parameter value corresponding to each of the sales parameters.

4. An epidemic spread information detection device, characterized in that: include: A data acquisition module is used to obtain online drug sales data provided by users in a historical period of time for at least one drug corresponding to the same disease; A data extraction module, configured to extract sales data and spatial data from the online drug sales data; A time vector generating module, configured to generate a time vector based on the sales data; A spatial vector generation module is configured to generate a spatial vector based on the spatial data, comprising: generating a spatial matrix based on the spatial data, wherein the position of each element in the matrix corresponds to a geographical location and the value of each element corresponds to a usage probability; and generating a spatial vector based on the spatial matrix; a prediction module, configured to determine predicted spatiotemporal information of the disease based on the time vector and the space vector, including: determining, based on the time vector and the space vector, a purchase probability of a drug for the disease at each geographical location in a future time period; and determining, based on the purchase probability of the drug for the disease at each geographical location in a future time period, the predicted spatiotemporal information of the disease; the predicted spatiotemporal information including distribution time, distribution address, and occurrence probability; Wherein, the space vector generation module includes: extracting at least one spatial parameter from the spatial data; Calculating the use probability of a drug for the same disease at the geographical location corresponding to each of the spatial parameters according to the weight corresponding to each of the spatial parameters; The prediction module includes: Based on the time vector and the space vector, the purchase probability of the drug for the disease at each geographical location in multiple future sub-time periods is determined; wherein the historical time period includes: multiple historical sub-time periods, and the historical sub-time periods correspond to the future sub-time periods one by one.

5. An epidemic spread information detection device, characterized in that: The epidemic spread information detection device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the epidemic spread information detection method described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the epidemic spread information detection method according to any one of claims 1 to 3 when executed.

Images