CN114332009A - Similar weather situation recognition method, device, equipment and storage medium - Google Patents

Abstract

The application provides a method, a device, equipment and a storage medium for identifying similar weather situations. The method comprises the following steps: receiving a similar weather situation identification request triggered by a user, wherein the similar weather situation identification request comprises a reference situation graph; determining a reference area and a reference index according to the reference situational map; acquiring relevant data of the candidate situation map matched with the reference area and the reference index; determining relevant data of a target situation map similar to the reference situation map from the relevant data according to the candidate situation maps; and acquiring the target situation map according to the related data of the target situation map. The method improves the efficiency and accuracy of identifying similar weather conditions.

Description

Similar weather situation recognition method, device, equipment and storage medium

Technical Field

The present application relates to the field of environmental protection and weather technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying similar weather situations.

Background

Knowing the weather situation and analyzing it to predict the weather in the future is one of the main tasks of the forecaster.

Because weather and weather conditions have strong correlation, a forecaster can predict future weather by referring to corresponding weather indexes when similar weather situations in history occur and the weather conditions after the similar weather situations occur. The weather situation refers to the distribution characteristics of the weather system on a weather chart and the atmospheric motion state represented by the distribution characteristics. The weather situation shows the distribution characteristics of the meteorological indexes on a certain area at a certain moment in a weather situation graph mode, such as an air pressure distribution situation graph, a temperature distribution situation graph, a humidity distribution situation graph, an atmospheric pollutant distribution situation graph, a wind speed distribution situation graph and the like.

At present, workers can not realize similar situation summarization by looking up thematic map data and combining with other monitoring data and predicting future weather evolution trend according to personal experience, and further can not summarize weather influence conditions of weather indexes. The staff look over the weather map of a period of time in the relevant online system of atmospheric environment, find historical similar weather situation picture, and then refer to weather indicator and actual weather when and after the similar weather situation of historical emergence, make a prediction to the weather in the future.

However, the weather indicators have a plurality of data types, the data size of the weather situation map is large, workers need to check a large amount of data to determine similar weather situations, and whether the weather situations are similar or not depends on subjective judgment of the workers, so that the efficiency of identifying the similar weather situations is low and the accuracy is low.

Disclosure of Invention

The application provides a method, a device, equipment and a storage medium for identifying similar weather situations, which are used for solving the problems of low efficiency and low accuracy in identifying similar weather situations in the prior art.

According to a first aspect of the present application, there is provided a similar weather situation recognition method, comprising:

receiving a similar weather situation identification request triggered by a user, wherein the similar weather situation identification request comprises a reference situation graph;

determining a reference area and a reference index according to the reference situational map;

acquiring relevant data of the candidate situation map matched with the reference area and the reference index; determining relevant data of a target situation map similar to the reference situation map according to the relevant data of the candidate situation map;

and acquiring the target situation map according to the related data of the target situation map.

According to a second aspect of the present application, there is provided a similar weather situation recognition apparatus comprising:

the system comprises a receiving module, a judging module and a judging module, wherein the receiving module is used for receiving a similar weather situation identification request triggered by a user, and the similar weather situation identification request comprises a reference situation graph;

the first determination module is used for determining a reference area and a reference index according to the reference situational map;

the first acquisition module is used for acquiring relevant data of the candidate situation map matched with the reference area and the reference index;

the second determination module is used for determining the related data of the target situation map similar to the reference situation according to the related data of the candidate situation map;

and the second acquisition module is used for acquiring the target situation map according to the relevant data of the target situation map.

According to a third aspect of the present application, there is provided an electronic device comprising: a memory, a processor, and a transceiver;

the memory, the processor and the transceiver circuitry are interconnected;

the memory stores computer-executable instructions;

the transceiver is used for transceiving data;

the processor executes computer-executable instructions stored by the memory to implement the method as in the first aspect.

According to the similar weather situation identification method, a similar weather situation identification request triggered by a user is received, wherein the similar weather situation identification request comprises a reference situation graph; determining a reference area and a reference index according to the reference situational map; acquiring relevant data of the candidate situation map matched with the reference area and the reference index; determining relevant data of a target situation map similar to the reference situation map according to the relevant data of the candidate situation map; acquiring a target situation map according to the relevant data of the target situation map; and limiting the recognition range of the similar weather situation in the related data of the candidate situation graph through the reference area and the reference index, and reducing the recognition data amount so as to improve the recognition efficiency. Meanwhile, the relevant data of the candidate situation diagrams matched with the reference area and the reference index are obtained, the relevant data of all the candidate situation diagrams can be identified by adopting a unified standard, the relevant data of the target situation diagram similar to the reference situation diagram is determined from the relevant data of the candidate situation diagrams, the similarity degree of all the candidate situation diagrams and the reference situation diagram can be identified simultaneously according to the relevant data of the candidate situation diagrams, the similarity degree of all the candidate situation diagrams and the reference situation diagram is measured by using the same standard, and the identification efficiency and accuracy are improved. And acquiring a target situation map according to the related data of the target situation map, wherein the weather situation in the target situation map is the similar weather situation. Therefore, an effect of improving the efficiency and accuracy of recognizing similar weather situations can be achieved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

FIG. 1 is a network architecture diagram of a similar weather situation recognition method provided in an embodiment of the present application;

FIG. 2 is a schematic flow chart of a similar weather situation recognition method according to a first embodiment of the present application;

FIG. 3 is a schematic flow chart of a similar weather situation recognition method according to a second embodiment of the present application;

FIG. 4A is a schematic flow chart of a similar weather situation recognition method according to a third embodiment of the present application;

FIG. 4B is a schematic diagram of grid data provided in accordance with a third embodiment of the present application;

FIG. 5 is a schematic flow chart of a similar weather situation recognition method according to a fourth embodiment of the present application;

FIG. 6A is a schematic flow chart of a similar weather situation recognition method according to a fifth embodiment of the present application;

FIG. 6B is a schematic diagram of a similar weather situation recognition method provided in accordance with a fifth embodiment of the present application;

FIG. 7 is a schematic structural diagram of a similar weather situation recognition apparatus according to a sixth embodiment of the present application;

fig. 8 is a block diagram of an electronic device provided in accordance with a seventh embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The terms referred to in this application are explained first:

weather system (Weather system): specific systems on flow fields, air pressure fields, temperature fields and humidity fields, or specific weather phenomena, which have a significant influence on the weather development.

Weather map (Weather map): the map is a special map filled with meteorological elements of all places at the same time.

Weather situation (synthetic location): the distribution characteristics of the weather system on the weather chart and the atmospheric motion state represented by the distribution characteristics are referred to.

Weather map, refers to a map that includes: distribution characteristic diagram of weather indexes (also called weather indexes) such as temperature, precipitation, cloud cover, wind speed, gust, air pressure, thunderstorm, humidity, snowdeposit, air pollutants, air quality index and the like on a weather diagram (also called weather diagram).

Wherein the air pollutants comprise PM_2.5(particulate matter having an equivalent diameter of 2.5 μm or less), PM₁₀(particulate matter having a particle size of 10 μm or less), nitrogen dioxide, sulfur dioxide, ground ozone, carbon monoxide, and the like.

The prior art to which this application relates is analyzed in detail below.

When the future weather needs to be predicted, similar weather situation graphs with the distribution situations of the weather indexes similar to the distribution situation of the weather indexes in the current weather situation graph can be found out in a large number of historical weather situation graphs, the weather evolution situation after the distribution situation of the weather indexes in the similar weather situation graphs occurs is referred to, the weather situations at different moments are subjected to relevant analysis, the weather evolution after the distribution situation of the weather indexes in the current weather situation graphs occurs is predicted, and then the future weather is predicted. Finding similar weather situation maps is a prerequisite for prediction using this method.

At present, workers can know past weather evolution conditions by checking visual thematic map data of one or more weather indexes in a certain area at a certain moment or checking a weather map on which different weather index data are superimposed within a period of time, and then predict future weather evolution trends according to personal experiences by combining the conditions with other monitoring data. When the method is used for predicting the weather change, the analysis can be carried out only according to the weather situation of a certain area at a certain time, similar weather situations cannot be identified, the correlation analysis of the weather situations at different moments cannot be realized, and the historical facies cannot be usedWeather-like situations predict the predicted weather. Workers can look at historical weather situation graphs in some online systems related to atmospheric environment to find similar weather situation graphs. However, the weather indexes have many kinds of data, and the weather situation map has a high time frequency and a wide space coverage. For example, for PM_2.5The weather situation map of (2) changes every moment, and workers need to check the historical weather situation map hour by hour or day by day to identify the similar weather situation map, so that the workload is large and the working efficiency is low. Meanwhile, the recognition of similar weather conditions completely depends on the experience of workers, similar weather conditions identified by different workers may be completely different, the recognition standards of the same worker for different weather conditions may also change, and the recognition efficiency of the similar weather conditions is low and inaccurate.

Therefore, in order to solve the technical problems in the prior art, the inventor proposes the technical solution of the present application through the discovery of creative research, aiming at solving the above problems in the prior art. In order to improve the efficiency and accuracy of identifying similar weather conditions, a current weather condition map is required to be used as a reference condition map, a region related to the current weather condition map is determined as a reference region, an index related to the current weather condition is determined as a reference index, relevant data of a candidate condition map is obtained according to the reference region and the reference index, a similar weather identification range is determined, the identification data volume is reduced, the similar weather conditions are prevented from being identified blindly in the historical weather conditions with huge data volume, and the identification efficiency is improved. Meanwhile, the related data of the target situation diagram similar to the reference situation diagram is determined from the related data of the candidate situation diagrams, the similarity between all the candidate situation diagrams and the reference situation diagram can be simultaneously identified according to the related data of the candidate situation diagrams, the similarity between all the candidate situation diagrams and the reference situation diagram is measured according to the same standard, and the identification efficiency and accuracy are improved. And acquiring a target situation map according to the related data of the target situation map, wherein the weather situation in the target situation map is the similar weather situation.

Next, a network architecture of a similar weather situation recognition method provided in the embodiment of the present application is introduced.

Fig. 1 is a network architecture corresponding to an application scenario provided in an embodiment of the present application, and as shown in fig. 1, the network architecture corresponding to an application scenario provided in the embodiment of the present application includes: an electronic device 11 and a data server 12. The electronic device 11 is communicatively connected to a data server 12. The data server 12 stores data related to historical weather situation maps.

In an application scenario, a client or an electronic device loaded with application software for identifying similar weather situations in the electronic device 11 accesses a website for identifying similar weather situations. And triggering a similar weather situation identification request by a user through an operation interface of the client or a webpage corresponding to the website, wherein the similar weather situation identification request comprises a reference situation map.

After receiving the similar weather situation recognition request, the electronic device 11 determines a reference area and a reference index according to the reference situation map, communicates with the data server 12, and sends a related data acquisition request of the candidate situation map to the data server 12. The relevant data acquisition request of the candidate situation map comprises a reference area and a reference index.

After receiving the request for obtaining the relevant data of the candidate situation map, the data server 12 sends the relevant data of the candidate situation map matched with the reference area and the reference index to the electronic device 11. After the electronic equipment receives the relevant data of the candidate situation diagrams matched with the reference area and the reference index, the relevant data of the target situation diagrams similar to the reference situation diagrams are determined from the relevant data of the candidate situation diagrams, and the target situation diagrams are obtained according to the relevant data of the target situation diagrams so as to identify the target situation diagrams similar to the reference situation diagrams.

The following describes the technical solution of the present application and how to solve the above technical problems with specific embodiments. The following specific embodiments may be combined with each other, and some embodiments may not be described in detail for the same or similar concepts or processes.

Embodiments of the present application will be described below in detail with reference to the accompanying drawings.

Example one

Fig. 2 is a schematic flow chart of a similar weather situation recognition method according to a first embodiment of the present application, and as shown in fig. 2, an implementation subject of the present application is a similar weather situation recognition apparatus. The similar weather situation recognition device is located in the electronic equipment. The method for identifying similar weather conditions provided by the embodiment comprises steps 201 to 205.

Step 201, receiving a similar weather situation recognition request triggered by a user, wherein the similar weather situation recognition request comprises a reference situation map.

In this embodiment, the electronic device is provided with a client of similar weather situation recognition application software, and the user triggers a similar weather situation recognition request in an operation interface of the client by opening the client of the similar weather situation recognition application software. Or the user inputs a website corresponding to the similar weather situation recognition in a search engine mounted on the electronic device to access the corresponding webpage, and triggers a similar weather situation recognition request on the webpage, wherein the similar weather situation recognition request comprises the reference situation map. After the user triggers the similar weather situation recognition request, the electronic equipment receives the similar weather situation recognition request. The reference situation graph is a weather situation graph with a preset format, is a distribution characteristic graph of the reference indexes in the reference area, and can intuitively reflect the distribution characteristics of the reference indexes in the reference area. The reference situation map may be a distribution feature map of the reference index on the reference area in real time or at a user-specified time. The user needs to find a target situation graph with the distribution characteristics of the historical benchmark indexes on the benchmark area similar to the distribution characteristics on the benchmark situation graph as a reference to predict future weather or analyze the relation between the weather and the weather situation graph. The reference index is any item in the weather indexes, and the weather indexes comprise: temperature, humidity, wind direction, wind speed, cloud cover, rain cover, precipitation, air pollutants, etc. Air pollutants including PM_2.5，PM₁₀Ground ozone, nitrogen dioxide, sulfur dioxide, carbon monoxide, and the like. The reference area is a certain range in a geographic space, for example, nationwide, a certain region, a certain province, or the like. For example, the reference situational map may be PM_2.5Concentration distribution diagram in Jingjin Ji area, numerical value distribution diagram in southwest area of temperature, and the like.

In this embodiment, the user may be an individual or an enterprise that needs to predict weather, or a worker that needs to obtain a similar weather situation map for data analysis.

And step 202, determining a reference area and a reference index according to the reference situational graph.

And analyzing the reference situation map, and determining a reference area and a reference index. Specifically, the reference situational map is a picture in a predetermined format, a file header mark of the picture in the predetermined format stores a reference region and a reference index, and the reference region and the reference index are determined by reading corresponding fields of the reference region and the reference index in the predetermined format in the file header mark.

Step 203, acquiring relevant data of the candidate situation map matched with the reference area and the reference index.

In this embodiment, the region in the relevant data of the candidate situation map matched with the reference region and the reference index is the reference region, and the finger mark is the reference index. Meanwhile, the electronic equipment can be pre-stored with the relevant data of the situation map of each index in each area within a period of time.

The relevant data of the situation map is a weather situation map of a certain index in a certain area, an index type and an area range, or a file formed by encoding indexes, areas and distribution characteristics of the indexes in the area reflected in the weather situation map through a preset algorithm. Such as may include: data in a picture format, such as data in a jpeg (joint Photographic Experts group) format, a type of an index in the picture, and an area range to which the picture refers; and the data in the JPEG format is coded by a preset algorithm to form a file.

Meanwhile, the related data of the pre-stored situation maps may be classified by area, index or time, and the electronic device may use an index of the related data of the pre-stored situation maps as a reference index according to the reference area and the reference index, and use the related data of the situation maps with the area as the reference area as the related data of the candidate situation maps matched with the reference area and the reference index.

And step 204, determining relevant data of the target situation map similar to the reference situation map according to the relevant data of the candidate situation map.

In this embodiment, the relevant data of the candidate situation map is a picture with the same format as the reference situation map, so that picture comparison or identification algorithms such as a mean hash algorithm, a perceptual hash algorithm, a difference hash algorithm and the like can be used to compare the reference situation map with the pictures in the relevant data of the candidate situation map one by one, determine whether the pictures are similar to the reference situation map, and determine that the pictures similar to the reference situation map are the relevant data of the target situation map similar to the reference situation map.

And step 205, acquiring the target situation map according to the relevant data of the target situation map.

In this embodiment, the relevant data of the target situation map may be a picture similar to the reference situation picture determined in step 204, and all or any part of the picture may be used as the target situation map. The target situation map is a distribution characteristic map in which the distribution situation of the reference index on the reference area is similar to the distribution situation in the reference situation map historically. The user can predict the future weather after the distribution situation in the reference situation chart occurs by referring to the weather situation after the distribution situation in the target situation chart occurs.

As an optional implementation manner, in step 201, the format of the reference situational graph may not be limited, the similar weather situational identification request further includes a reference area and a reference index, and the user needs to input the reference situational graph, the reference area and the reference index when triggering the similar weather situational identification request. In step 202, the reference area and the reference index may be determined directly from the similar weather situation recognition request.

In the similar weather situation recognition method provided by the embodiment, a similar weather situation recognition request triggered by a user is received, the similar weather situation recognition request includes a reference situation map, a reference area and a reference index are determined according to the reference situation map, relevant data of a candidate situation map matched with the reference area and the reference index are acquired, relevant data of a target situation map similar to the reference situation map are determined according to the relevant data of the candidate situation map, the target situation map is acquired according to the relevant data of the target situation map, and as the similar weather situation recognition range is limited in the relevant data of the candidate situation map through the reference area and the reference index, the recognized data size is reduced, and the recognition efficiency is improved. Because the related data of the target situation diagram similar to the reference situation diagram is determined from the related data of the candidate situation diagrams, the related data of all the candidate situation diagrams are identified by adopting a uniform standard, the related data of the target situation diagram similar to the reference situation diagram is determined from the related data of the candidate situation diagrams, the similarity between all the candidate situation diagrams and the reference situation diagram can be simultaneously identified according to the related data of the candidate situation diagrams, the similarity between all the candidate situation diagrams and the reference situation diagram is measured by using the same standard, and the identification efficiency and accuracy are improved. And acquiring a target situation map according to the related data of the target situation map, wherein the weather situation in the target situation map is the similar weather situation. Therefore, the similar weather identification method provided by the embodiment improves the efficiency and accuracy of identifying similar weather situations.

Example two

Fig. 3 is a schematic flow chart of a similar weather situation recognition method according to a second embodiment of the present application, and as shown in fig. 3, the similar weather situation recognition method provided in this embodiment refines step 203 on the basis of the first embodiment. In this embodiment, step 203 acquires the relevant data of the candidate situation map matched with the reference area and the reference index, and the refinement includes steps 301 to 302.

Step 301, sending a request for obtaining relevant data of the candidate situation map to a data server, where the request for obtaining relevant data of the candidate situation map includes a reference area and a reference index.

In this embodiment, the data related to the situation map is data in which the type of the index, the range of the area, and the value of the index in the area are stored. The data related to the candidate situation map may be a weather map of the indicator in the area, a file obtained by encoding weather data of the indicator in the area according to a preset algorithm, or a file including information of the indicator, the area, the time and the like in a file header and presenting the value of the indicator in the area by using grid data. The data related to the candidate situation map is data in which the index is the same as the reference index and the area is the same as the reference area in the data related to the situation map. The mesh data refers to data stored in a grid structure in a computer, and includes meshes of uniform size in which attributes, values, and the like of the data can be stored. The grids in the grid data are arranged according to a certain rule, and therefore, the geospatial coordinate information can be hidden in the storage addresses of the grids. For example, for a value of a certain index in a certain area, a grid with a uniform size may be divided in a map of the certain area, and the value of the area in which each grid is located is stored in the grid.

In this embodiment, the data server may store data related to a situation map at all times or in a period of time. Meanwhile, the server can also update the relevant data of the situation map periodically, and can divide the relevant data of the situation map into directory structures according to the attributes such as data type, occurrence time, index type, area range and the like for storage, so that the data server can retrieve and search the data conveniently.

The electronic equipment sends a request for acquiring relevant data of the candidate situation map to the data server, the request for acquiring relevant data of the candidate situation map comprises a reference area and a reference index, and after receiving the request for acquiring relevant data of the candidate situation map, the data server can inquire in stored data according to the reference area and the reference index, find out relevant data of the candidate situation map matched with the reference area and the reference index and send the relevant data to the electronic equipment.

Step 302, receiving the relevant data of the candidate situation graph sent by the data server.

In this embodiment, the electronic device receives the data related to the candidate situation map sent by the data server.

In the method for identifying similar weather situations provided by this embodiment, the request for acquiring the relevant data of the candidate situation map is sent to the data server, the request for acquiring the relevant data of the candidate situation map includes the reference area and the reference index, and the relevant data of the candidate situation map sent by the data server is received.

EXAMPLE III

Fig. 4A is a schematic flowchart of a similar weather situation recognition method according to a third embodiment of the present application, and fig. 4B is a schematic diagram of grid data according to the third embodiment of the present application. As shown in fig. 4A, in the method for identifying similar weather situations provided in this embodiment, based on any one of the above embodiments, the relevant data of the candidate situation graph is a file whose header includes information such as an index, a region, and time, and the value of the index in the region is presented by using the grid structure data, and step 204 is refined. In this embodiment, step 204 determines the relevant data of the target situation map similar to the reference situation map according to the relevant data of the candidate situation map, and the refinement includes steps 401 to 402.

Step 401, converting the reference situational graph into a reference file by using a preset algorithm, wherein the reference file comprises a reference index, a reference area and a value of the reference index in the reference area.

In this embodiment, the reference file may be a file that includes information such as an index, a region, and time in a file header and presents a value of the index in the region in the mesh structure data.

In this embodiment, the preset algorithm recodes the reference situation map, and converts the reference situation map into a reference file. The index type, the area information, the value of the index in the area and the like in the situation map can be stored in a file header, the longitude and latitude coordinates of the upper left corner and the lower right corner of the area displayed in the picture can be stored as the area information, the value of the index in the area can be converted into a data form with a regular grid structure, and then the number of horizontal grids, the number of vertical grids, the grid interval and the data in the grids are stored in the corresponding fields of the file according to the arrangement mode specified in the preset algorithm. The grid spacing may be varied according to the geographic region range of the time store to reduce the information lost to converting the picture into a file. The grid data is in a situational mapAnd drawing grids with uniform sizes, and storing the value of the area where each grid is positioned into the grids. For example, the values of the indices in the region in the situation map are converted into grid data, resulting in 3 × 3 grid data as shown in fig. 4B. For example, when storing a situation map of a certain index in a certain province, the grid spacing may be 0.1 longitude and 0.1 latitude, and when storing situation maps of adjacent provinces, the grid spacing may be 0.5 longitude and 0.5 latitude. The distribution situation of the reference indexes displayed in the reference picture in the reference area is also shown after numerical value coding, so that the reference picture with a predetermined format can be directly converted into a corresponding file. When the server searches for the relevant data of the candidate situation map matched with the reference area and the reference index, the server can directly inquire the corresponding field to find or form the relevant data of the candidate situation map. Illustratively, the reference index is PM_2.5The reference area is Kyoto Ji, and the server inquires that the index is PM_2.5The regional situation map is national and PM can be passed_2.5Extracting the corresponding field in the Jingjin Ji area, and forming the relevant data of the candidate situation map according to the same coding rule with the preset algorithm.

And step 402, determining relevant data of the target situation map according to the value of the reference index in the reference area and the value of the candidate index in the candidate area.

In this embodiment, the candidate index in the relevant data of the candidate situation map is the reference index, and the candidate region is the reference region. The values of the candidate indicators in the same candidate area in the correlation data of the candidate situational graphs may be compared with the values of the reference indicators in the reference area one by one, to determine whether the two values are the same or within a first predetermined percentage, e.g., 5%, to compare the number of values determined to be the same or within the first predetermined percentage with the total number of values, and to determine the correlation data of the candidate situational graphs having the number of values within the first predetermined percentage exceeding a second predetermined percentage, e.g., 80%, as the correlation data of the target situational graph.

According to the similar weather situation recognition method provided by the embodiment, the reference situation graph is converted into the reference file by using the preset algorithm, the reference file comprises the reference index, the reference area and the value of the reference index in the reference area, the relevant data of the target situation graph is determined according to the value of the reference index in the reference area and the value of the candidate index in the candidate area, and the picture with larger occupied storage space is coded into the file with smaller occupied storage space by using the preset algorithm.

Example four

Fig. 5 is a schematic flowchart of a similar weather situation recognition method according to a fourth embodiment of the present application, and as shown in fig. 5, the similar weather situation recognition method according to the present embodiment refines step 402 based on the third embodiment. In the embodiment, step 402 determines the relevant data of the target situation map according to the value of the reference index in the reference area and the value of the candidate index in the candidate area, and the refinement includes step 501 and step 505.

Step 501, the value of the reference index in the reference area and the value of the candidate index in the candidate area are processed into reference mesh data and candidate mesh data, respectively.

In this embodiment, the reference file may be analyzed according to an arrangement manner specified in a preset algorithm, and the value of the reference index in the reference area and the value of the candidate index in the candidate area are restored to the grid data corresponding to the situation map and processed into the reference grid data and the candidate grid data having the same grid pitch and grid number. The number of meshes and the mesh pitch of the reference mesh data and the candidate mesh data may be set in advance, or may be adjusted according to the range size of the reference region. Meanwhile, for some data related to the candidate situation map, when the value of the candidate index in the candidate area is processed as the candidate grid data, the stored larger grid data may be diluted into the smaller grid data, for example, when the candidate situation map is converted into a file, the candidate index is converted into 500 × 500 grid data and then stored in the field corresponding to the file according to the specified arrangement mode, and when the field corresponding to the file is reprocessed as the candidate grid data, one grid may be selected in every first predetermined number of grids in the horizontal grid, and one grid may be selected in every second predetermined number of grids in the vertical grid, so as to form 64 × 64 grid data.

Step 502, respectively converting the reference grid data and the candidate grid data into matrixes, and performing discrete cosine transformation to obtain a reference coefficient matrix and a candidate coefficient matrix.

In this embodiment, the data values in the grids of the reference grid data and the candidate grid data may be respectively converted into the reference matrix and the candidate matrix according to the original arrangement manner, and the reference matrix and the candidate matrix may be respectively subjected to discrete transformation to respectively obtain the reference coefficient matrix and the candidate coefficient matrix. When the grid data is 64 × 64, the converted matrix is 64 rows and 64 columns, and the size of the coefficient matrix obtained after discrete cosine transform is 64 × 64.

Step 503, calculating the reference hash value and the candidate hash value of the reference coefficient matrix and the candidate coefficient matrix respectively.

In this embodiment, only the matrix with the predetermined row and column numbers at the upper left corner of the reference coefficient matrix and the candidate coefficient matrix may be retained, and in the coefficient matrix obtained by discrete cosine transform, the matrix at the upper left corner is a low-frequency component in the data, that is, information that can most represent the meaning of the data. For a picture, the low-frequency component is a region with slow brightness or gray scale change and describes main information carried by the picture, and the high-frequency classification is a part with severe change in the picture, namely the edge, the contour and the local detail of the picture, and has little influence on the main information expressed by the picture. The similar identification is carried out on the main information carried by the picture, so that the matrix at the upper left corner is reserved, and the calculation amount can be reduced while most information is not lost.

In this embodiment, an average value of all numbers in the reference coefficient matrix may be calculated, all numbers in the reference coefficient matrix may be sequentially compared with the average value, a number greater than or equal to the average value is denoted as 1, a number less than or equal to the average value is denoted as 0, and a result of comparing all numbers in the matrix with the average value is sequentially combined into a character string, where the character string is a hash value of the reference coefficient matrix. The candidate hash values of the candidate coefficient matrix may be calculated by the same method, which is not described herein.

And step 504, determining the similarity between the candidate situation graph and the reference situation graph according to the reference hash value and the candidate hash value.

In this embodiment, since the grid numbers of the reference grid data and the candidate grid data are the same in step 501, the string lengths of the finally obtained reference hash value and the candidate hash value are the same, the number of the reference hash value and the number of the candidate hash value on the bit corresponding to the character string can be determined by comparing the two character strings, and the number of the corresponding bit with the same value is used as the similarity between the candidate situation map and the reference situation map.

And 505, determining relevant data of the target situation graph according to the similarity.

In this embodiment, the similarity may be ranked, and the relevant data of the candidate situation map with the similarity ranked first 10% may be determined as the relevant data of the target situation map. When the relevant data of the target situation map is not the situation map, the picture corresponding to the relevant data of the target situation map can be determined as the target situation map.

The method for identifying similar weather situations provided by this embodiment processes the values of the reference index in the reference area and the candidate index in the candidate area into reference grid data and candidate grid data, respectively converts the reference grid data and the candidate grid data into matrices, performs discrete cosine transform to obtain a reference coefficient matrix and a candidate coefficient matrix, respectively calculates the reference hash value and the candidate hash value of the reference coefficient matrix and the candidate coefficient matrix, determines the similarity between the candidate situation map and the reference situation map according to the reference hash value and the candidate hash value, determines the relevant data of the target situation map according to the similarity, reduces the data size due to the fact that the distribution of the values of the index in the area is converted into grid data, and meanwhile, determines the similarity between the candidate situation map and the reference situation map by using methods such as discrete cosine transform, and unifies the judgment standards of the similarity, therefore, the recognition efficiency and accuracy can be further improved.

As an alternative implementation manner, on the basis of any one of the above embodiments, before step 502, step 5011 to step 5012 may be further included.

In step 5011, a non-emphasized region is determined from the reference grid data.

In this embodiment, there may be non-emphasized areas that do not need to be concerned with when identifying similar weather conditions. Illustratively, the reference situational map is PM_2.5When the concentration distribution situation of a certain area exists, the user performs similar weather situation recognition, focuses on similar high concentration distribution situations of the area history, and does not focus on the difference of low concentration areas. That is, only PM is needed in the target situation map_2.5The high concentration distribution pattern of (2) may be the same, for the case of low concentration distribution, for example, PM_2.5The two local concentrations of 0 and 149 are not much affected by the high concentration region of interest even if they are greatly different from each other, and it can be considered that the map is the target map.

Thus, non-emphasized regions may be determined from the reference grid data, which may be preset according to the type of target index, illustratively PM_2.5、PM₁₀When the air pollutants are waited, the area with the value less than 150 in the grid data is preset as a non-key area. Meanwhile, when the user triggers the similar weather situation identification request, the user can designate a non-key area in the similar weather situation identification request.

In step 5012, the values corresponding to the non-emphasized regions in the reference grid data and the candidate grid data are adjusted to be consistent.

In this embodiment, in order to avoid that the different distribution conditions of the non-key areas affect the accuracy of the similar weather situation recognition, the values corresponding to the non-key areas in the reference grid data and the candidate grid data are adjusted to be consistent, so that the distribution conditions of the non-key areas are completely consistent in the subsequent recognition process, and the target situation map with inconsistent distribution conditions of the non-key areas is prevented from being missed to be recognized.

In the method for identifying similar weather situations provided by this embodiment, the non-emphasized region is determined according to the reference grid data, and the corresponding values of the non-emphasized region in the reference grid data and the candidate grid data are adjusted to be consistent, so that the influence of the non-emphasized region on identifying similar situation maps is reduced, and the situation maps with different non-emphasized regions but the same emphasized region can be identified, thereby further improving the accuracy of identification.

As an alternative implementation, on the basis of any of the above embodiments, step 504 may be refined to include steps 5041 to 5042.

At step 5041, a hamming distance between the base hash value and the candidate hash value is calculated.

In this embodiment, the hamming distance indicates that two character strings with the same length correspond to different numbers, and may be obtained by performing xor operation on the reference hash value and the candidate hash value.

Step 5042, determining similarity between the candidate situation map and the reference situation map according to the hamming distance.

In this embodiment, a first preset value, a second preset value and a third preset value may be preset, which are ordered from small to large, the candidate situation graph with the hamming distance smaller than the first preset value is determined to have high similarity, the candidate situation graph with the hamming distance between the second preset value and the third preset value is determined to have medium similarity, and the candidate situation graph with the hamming distance larger than the third preset value is determined to have low similarity. And determining the relevant data of the candidate situation graph with high similarity as the relevant data of the target situation graph.

According to the similar weather situation recognition method provided by the embodiment, the hamming distance between the reference hash value and the candidate hash value is calculated, the similarity between the candidate situation graph and the reference situation graph is determined according to the hamming distance, and the similarity between the candidate situation graph and the reference situation graph is quantized according to the hamming distance, so that the accuracy of similar weather situation recognition can be further improved.

As an alternative implementation, step 505 may be refined to include steps 5051 to 5052 based on any of the above embodiments.

In step 5051, the similarity is compared with a preset similarity.

In step 5052, the relevant data of the candidate situation map with similarity greater than or equal to the preset similarity is determined as the relevant data of the target situation map.

In this embodiment, the preset similarity may be a preset value, or the preset similarity value may be specified by the user in the similar weather situation recognition request when the user triggers the similar weather situation recognition request. And comparing the similarity between the candidate situation diagram and the reference situation diagram with a preset similarity, and determining the relevant data of the candidate situation diagram of which the similarity between the candidate situation diagram and the reference situation diagram is greater than or equal to the preset similarity as the relevant data of the target situation diagram.

In this embodiment, the similarity is compared with the preset similarity, and the related data of the candidate situation map with the similarity greater than or equal to the preset similarity is determined as the related data of the target situation map.

EXAMPLE five

Fig. 6A is a schematic flowchart of a similar weather situation recognition method according to a fifth embodiment of the present application, and fig. 6B is a schematic diagram of the similar weather situation recognition method according to the fifth embodiment of the present application. As shown in fig. 6A, in the similar weather situation identification method provided in this embodiment, on the basis of any one of the above embodiments, the similar weather situation identification request further includes a reference index, the reference index includes any one or more of the weather indexes except for a reference index, and the weather index includes: in this embodiment, the method for identifying similar weather conditions further includes steps 601 to 609 if the file header of the picture in the predetermined format includes a field corresponding to time and the related data of the candidate situational graph includes time corresponding to the candidate situational graph.

Step 601, determining the time corresponding to the reference situation diagram according to the reference situation diagram.

The field which comprises the corresponding time in the file header mark of the picture with the preset format is used for storing the time when the weather situation occurs.

In this embodiment, the time corresponding to the reference situational map may be obtained by reading a field corresponding to the time in the header flag of the reference situational map.

Step 602, obtaining first reference data of the reference index in the reference area and at the time corresponding to the reference situational map.

In this embodiment, the first reference data reflects a time when the reference indicator is in the current similar weather situation, that is, a time corresponding to the reference situation map, and a distribution condition of the reference indicator in the reference area. The first reference data may be a file including information of an index, a region, time, etc. in a picture or file header and presenting values of the index in the region in the mesh structure data.

The electronic device may send a first reference data obtaining request to the data server, where the first reference data obtaining request includes time corresponding to the target situation map, a reference index, and a reference area. The server searches the first reference data in the stored data after receiving the first reference data acquisition request and sends the first reference data to the electronic equipment.

Step 603, obtaining second reference data of the reference index in the reference area and at the time corresponding to the target situation map.

In this embodiment, the second reference data reflects the time when the reference indicator has a similar weather situation in history, that is, the time corresponding to the target situation map, and the distribution of the reference indicator in the reference area. The second reference data may be a file including information of an index, a region, time, etc. in a picture or file header and presenting values of the index in the region in the mesh structure data. The method for obtaining the second reference data may be the same as the method for obtaining the first reference data, and is not described herein again.

Step 604, calculating a first difference value of the reference index according to the first reference data and the second reference data, wherein the first difference value is a difference value between the time corresponding to the reference index in the reference area and the reference situational map and the time corresponding to the target situational map.

In this embodiment, the method in the fourth embodiment may be used to obtain the mesh data corresponding to the first reference data and the mesh data corresponding to the second reference data. And obtaining a first difference value by using the grid data corresponding to the first reference data and the grid data corresponding to the second reference data to make a difference, wherein the first difference value can still be the grid data, and the value in the grid can be formed by sequentially calculating the difference value between the numerical value in the grid data corresponding to the first reference data and the data in the grid data corresponding to the second reference data.

And step 605, acquiring third reference data of the reference index in the reference area after a predetermined time period corresponding to the target situation map.

In this embodiment, the predetermined time period may be several hours or several days, and the time corresponding to the third reference data that needs to be acquired may be obtained by adding the predetermined time period to the time corresponding to the target situation map. The third reference data may be a file including information of an index, a region, time, etc. in a picture or file header and presenting a value of the index in the region in the mesh structure data. The third reference data may be obtained by the method of obtaining the first reference data, which is not described herein again.

Step 606, calculating a second difference value of the reference index according to the second reference data and the third reference data, wherein the second difference value is a difference value of the reference index in the reference area after a predetermined time period of the target situation diagram corresponding time and the target situation diagram corresponding time.

In this embodiment, the second difference of the reference index may reflect a weather condition after a predetermined time after a similar weather situation occurs in history, and has a reference meaning for predicting future weather. The second difference may be obtained by obtaining the first difference, which is not described herein.

Step 607, calculating the change rate of the reference index in the predetermined time period according to the second difference and the predetermined time period.

In the embodiment, the change rate of the reference index in the preset time period reflects the change condition of the weather in the preset time period after similar weather conditions happen historically, and the reference significance is provided for predicting the future weather. The second difference may be divided by the predetermined time period to obtain a rate of change of the reference indicator over the predetermined time period.

Step 608, a third difference of the reference index is obtained, where the third difference is a difference between the time corresponding to the reference situational map and the time corresponding to the target situational map when the reference index is in the reference area.

In this embodiment, after step 502 is finished, the reference grid data and the candidate grid data are obtained, and the method in step 604 may be used to perform a difference between the reference grid data and the candidate grid data to obtain a third difference value, where the third difference value can reflect a degree of similarity between the target situation diagram and the reference situation diagram, and the higher the degree of similarity is, the higher the reference value of the first difference value and the second difference value for predicting future weather is.

And step 609, outputting any one or more of a target situation map, first reference data, second reference data, a first difference value, a third reference value, a second difference value, a change rate of the reference index in a preset time period and a third difference value, so that the user can predict weather according to any one or more of the target situation map, the first reference data, the second reference data, the first difference value, the third reference value, the second difference value, the change rate of the reference index in the preset time period and the third difference value.

In this embodiment, when the user triggers a similar weather situation recognition request, the user determines which items of the target situation map, the first reference data, the second reference data, the first difference value, the third reference value, the second difference value, the change rate of the reference index in a predetermined time period, and the third difference value need to be output, so as to be referred by the user, and further predict the future weather.

The electronic device issues any one or more of the target situation graph, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index within the predetermined time period and the third difference in real time, for example, the target situation graph, the first reference data, the second reference data, the first difference, the third difference, the change rate of the reference index within the predetermined time period and the third difference are displayed in a client operation interface or a webpage of the similar weather situation recognition application software in real time, or the target situation graph, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index within the predetermined time period and the third difference are visualized on the map, so that a user can view any one or more of the target situation graph, the first reference data, the second reference data, the first difference, the third difference, the second difference and the third difference in real time to predict future weather.

In this embodiment, it is understood that step 601 precedes step 602. Step 602 and step 603 both precede step 604, and there is no necessary order of execution between step 602 and step 603. Steps 603 and 605 precede step 606, and there is no necessary order of execution between step 603 and step 605. Step 606 precedes step 607. Step 601 precedes step 608. Step 609 is executed at the end, and the steps preceding it, there is no other necessary execution order than the above order. Fig. 6B is a schematic diagram of a similar weather situation recognition method provided in this embodiment, and data required to acquire any one of the target situation map, the first reference data, the second reference data, the first difference value, the third reference value, the second difference value, the change rate of the reference index in the predetermined time period, and the third difference value is shown in fig. 6B.

The method for identifying similar weather situations provided in this embodiment includes determining a time corresponding to a reference situational map according to the reference situational map, obtaining first reference data of a reference index in a reference region and at the time corresponding to the reference situational map, obtaining second reference data of the reference index in the reference region and at the time corresponding to a target situational map, calculating a first difference of the reference index according to the first reference data and the second reference data, where the first difference is a difference of the reference index in the reference region and at the time corresponding to the reference situational map and at the time corresponding to the target situational map, obtaining third reference data of the reference index in the reference region and after a predetermined time period of the time corresponding to the target situational map, calculating a second difference of the reference index according to the second reference data and the third reference data, where the second difference is a difference of the reference index in the reference region and at the time corresponding to the target situational map and at the predetermined time corresponding to the target situational map, and calculating the change rate of the reference index in the preset time period according to the second difference and the preset time period, acquiring a third difference of the reference index, wherein the third difference is the difference between the time corresponding to the reference situation diagram and the time corresponding to the target situation diagram in the reference area, and outputting any one or more of the target situation diagram, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index in the preset time period and the third difference, so that the user can perform weather prediction according to any one or more of the target situation diagram, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index in the preset time period and the third difference. Because the difference between the reference situation diagram and the target situation diagram is quantitatively output as the third difference value, the distribution conditions and the weather change conditions of the reference index and the reference index during and after the occurrence of the historical similar weather situation are equivalently output, the condition that the identification accuracy of the similar weather situation is insufficient and the reference historical weather situation completely depends on experience caused by subjective factors during manual data analysis is avoided, and better reference can be provided for predicting the future weather.

EXAMPLE six

Fig. 7 is a schematic structural diagram of a similar weather situation recognition apparatus according to a sixth embodiment of the present application, and as shown in fig. 7, the similar weather situation recognition apparatus 70 provided in this embodiment is located in an electronic device. The similar weather situation recognition apparatus 70 includes: the device comprises a receiving module 71, a first determining module 72, a first obtaining module 73, a second determining module 74, a second obtaining module 75 and a second obtaining module 76.

The receiving module 71 is configured to receive a similar weather situation identification request triggered by a user, where the similar weather situation identification request includes a reference situation map.

A first determining module 72 for determining a reference region and a reference index according to the reference situational map.

A first obtaining module 73, configured to obtain relevant data of the candidate situation map matching the reference area and the reference index.

A second determining module 74, configured to determine relevant data of the target situation map similar to the reference situation according to the relevant data of the candidate situation map.

And a second obtaining module 75, configured to obtain the target situation map according to the relevant data of the target situation map.

The similar weather situation recognition apparatus provided in this embodiment may execute the similar weather situation recognition method provided in the first embodiment, and the specific implementation manner is similar to the principle, which is not described herein again.

Optionally, in the similar weather situation recognition apparatus provided in this embodiment, the first obtaining module 73 is specifically configured to send a request for obtaining relevant data of the candidate situation map to the data server, where the request for obtaining relevant data of the candidate situation map includes a reference area and a reference index; and receiving the relevant data of the candidate situation graph sent by the data server.

Optionally, in the similar weather situation recognition apparatus provided in this embodiment, the second determining module 74 is specifically configured to convert the reference situation map into a reference file by using a preset algorithm, where the reference file includes a reference index, a reference area, and a value of the reference index in the reference area; and determining the relevant data of the target situation map according to the value of the reference index in the reference area and the value of the candidate index in the candidate area.

Optionally, in the apparatus for identifying similar weather conditions provided in this embodiment, the second determining module 74 is specifically configured to process the value of the reference indicator in the reference area and the value of the candidate indicator in the candidate area into reference grid data and candidate grid data, respectively; respectively converting the reference grid data and the candidate grid data into matrixes, and performing discrete cosine transformation to obtain a reference coefficient matrix and a candidate coefficient matrix; respectively calculating a reference hash value and a candidate hash value of the reference coefficient matrix and the candidate coefficient matrix; determining the similarity between the candidate situation graph and the reference situation graph according to the reference hash value and the candidate hash value; and determining related data of the target situation graph according to the similarity.

Optionally, in the apparatus for identifying similar weather conditions provided in this embodiment, the second determining module 74 is specifically configured to determine the non-emphasized region according to the reference grid data; the values corresponding to the non-emphasized regions in the reference grid data and the candidate grid data are adjusted to be consistent.

Optionally, in the apparatus for identifying similar weather conditions provided in this embodiment, the second determining module 74 is specifically configured to calculate hamming distances between the reference hash value and the candidate hash values; and determining the similarity between the candidate situation graph and the reference situation graph according to the Hamming distance.

Optionally, in the device for identifying similar weather situations provided in this embodiment, the second determining module 74 is specifically configured to compare the similarity with a preset similarity; and determining the relevant data of the candidate situation graph with the similarity greater than or equal to the preset similarity as the relevant data of the target situation graph.

Optionally, the similar weather situation recognition apparatus provided in this embodiment further includes a calculation module and an output module.

The first determining module 73 is further specifically configured to determine a time corresponding to the reference situational map according to the reference situational map.

The second obtaining module 75 is further configured to obtain first reference data of the reference indicator in the reference region and at a time corresponding to the reference situational map; acquiring second reference data of the reference index in the reference area and at the time corresponding to the target situation map; acquiring third reference data of the reference index in the reference area and after a preset time period corresponding to the target situation map; and acquiring a third difference value of the reference index, wherein the third difference value is the difference value of the reference index in the reference area, in the time corresponding to the reference situation diagram and in the time corresponding to the target situation diagram.

The calculation module is specifically configured to calculate a first difference of the reference index according to the first reference data and the second reference data, where the first difference is a difference between a time corresponding to the reference index in the reference region and the reference situational map and a time corresponding to the target situational map; calculating a second difference value of the reference index according to the second reference data and the third reference data, wherein the second difference value is a difference value of the reference index in the reference area after a preset time period of the target situation diagram corresponding time and the target situation diagram corresponding time; and calculating the change rate of the reference index in the preset time period according to the second difference and the preset time period.

The output module is specifically configured to output any one or more of a target situation map, first reference data, second reference data, a first difference value, a third reference value, a second difference value, a change rate of the reference indicator in a predetermined time period, and a third difference value, so that a user performs weather prediction according to any one or more of the target situation map, the first reference data, the second reference data, the first difference value, the third reference value, the second difference value, the change rate of the reference indicator in the predetermined time period, and the third difference value.

The similar weather situation recognition apparatus provided in this embodiment may execute the similar weather situation recognition method provided in any one of the second to fifth embodiments, and the specific implementation manner is similar to the principle, which is not described herein again.

EXAMPLE seven

Fig. 8 is a block diagram of an electronic device according to a seventh embodiment of the present application, and as shown in fig. 8, the electronic device provided in this embodiment includes a memory 81, at least one processor 82, and a transceiver 83.

The memory 81, processor 82 and transceiver 83 are electrically interconnected.

The memory 81 stores computer-executable instructions.

The transceiver 83 is used for transmitting and receiving data.

The processor 82 executes computer-executable instructions stored by the memory 81 to implement a similar weather situation recognition method provided by any one of the first to fifth embodiments.

The processor 82 generally controls overall operation of the device 80, such as operations associated with display, data communication, and recording operations.

The memory 81 is configured to store various types of data to support operations at the apparatus 80. Examples of such data include instructions for any application or method operating on the apparatus 80. The memory 81 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The apparatus 80 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

The relevant description may be understood by referring to relevant descriptions and effects corresponding to the steps of the similar weather situation identification method provided in any one of the embodiments, and details are not described herein.

The electronic device 80 may further include other components, which is not limited in this embodiment.

In this embodiment, a non-transitory computer-readable storage medium including instructions stored therein is provided, where the instructions are executed by a processor to implement the method for identifying similar weather situations as provided in any one of the embodiments. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc., and the instructions in the storage medium, when executed by a processor of the terminal device, enable the terminal device to perform similar weather situation recognition methods as described above.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that the acts and modules referred to are not necessarily required in this application.

It should be further noted that, although the steps in the flowchart are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

It will be appreciated that the above described apparatus embodiments are merely illustrative and that the apparatus of the present application may be implemented in other ways. For example, the division of the units/modules in the above embodiments is only one logical function division, and there may be another division manner in actual implementation. For example, multiple units, modules, or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented.

In addition, unless otherwise specified, each functional unit/module in the embodiments of the present application may be integrated into one unit/module, or each unit/module may exist alone physically, or two or more units/modules may be integrated together. The integrated units/modules may be implemented in the form of hardware or software program modules.

If the integrated unit/module is implemented in hardware, the hardware may be digital circuitry, analog circuitry, etc. Physical implementations of hardware structures include, but are not limited to, transistors, memristors, and the like. The artificial intelligence processor may be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, ASIC, etc., unless otherwise specified. Unless otherwise specified, the Memory unit may be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive Random Access Memory rram (resistive Random Access Memory), Dynamic Random Access Memory dram (Dynamic Random Access Memory), Static Random Access Memory SRAM (Static Random-Access Memory), enhanced Dynamic Random Access Memory edram (enhanced Dynamic Random Access Memory), High-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid Memory cubic hmc (hybrid Memory cube), and the like.

The integrated units/modules, if implemented in the form of software program modules and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. The technical features of the embodiments may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (11)

1. A method for identifying similar weather situations is characterized by comprising the following steps:

receiving a similar weather situation identification request triggered by a user, wherein the similar weather situation identification request comprises a reference situation graph;

determining a reference area and a reference index according to the reference situational map;

acquiring relevant data of the candidate situation map matched with the reference area and the reference index;

determining relevant data of a target situation map similar to the reference situation map according to the relevant data of the candidate situation map;

and acquiring the target situation map according to the related data of the target situation map.

2. The method of claim 1, wherein obtaining data related to candidate situation maps matching the reference region and the reference index comprises:

sending a related data acquisition request of the candidate situation map to a data server, wherein the related data acquisition request of the candidate situation map comprises the reference area and the reference index;

and receiving the relevant data of the candidate situation graph sent by the data server.

3. The method according to claim 1, wherein the data related to the candidate situation map is a candidate file corresponding to the candidate situation map and encoded by using a preset encoding algorithm, the candidate file comprises candidate indexes, candidate areas and values of the candidate indexes in the candidate areas, and the determining the data related to the target situation map similar to the reference situation map from the data related to the candidate situation map comprises:

converting the reference situational graph into a reference file by using a preset algorithm, wherein the reference file comprises a reference index, a reference area and a value of the reference index in the reference area;

and determining the relevant data of the target situation map according to the value of the reference index in the reference area and the value of the candidate index in the candidate area.

4. The method of claim 3, wherein determining the relevant data of the target situation map according to the value of the reference indicator in the reference region and the value of the candidate indicator in the candidate region comprises:

processing the value of the reference index in the reference area and the value of the candidate index in the candidate area into reference grid data and candidate grid data respectively;

respectively converting the reference grid data and the candidate grid data into matrixes, and performing discrete cosine transformation to obtain a reference coefficient matrix and a candidate coefficient matrix;

respectively calculating a reference hash value and a candidate hash value of the reference coefficient matrix and the candidate coefficient matrix;

determining the similarity between the candidate situation graph and the reference situation graph according to the reference hash value and the candidate hash value;

and determining related data of the target situation graph according to the similarity.

5. The method according to claim 4, before converting the reference grid data and the candidate grid data into matrices and performing discrete cosine transform to obtain a reference coefficient matrix and a candidate coefficient matrix, respectively, further comprising:

determining a non-key area according to the reference grid data;

adjusting the corresponding values of the non-emphasized regions in the reference grid data and the candidate grid data to be consistent.

6. The method of claim 4, wherein determining the similarity of the candidate situational map and the reference situational map based on the reference hash value and the candidate hash value comprises:

calculating Hamming distances of the reference hash value and the candidate hash values;

and determining the similarity between the candidate situation map and the reference situation map according to the Hamming distance.

7. The method of claim 4, wherein said determining data related to said target situation map based on said similarity comprises:

comparing the similarity with a preset similarity;

and determining the relevant data of the candidate situation graph with the similarity greater than or equal to the preset similarity as the relevant data of the target situation graph.

8. The method according to claim 4, wherein the similar weather situation recognition request further comprises reference indicators, the reference indicators comprise any one or more of the weather indicators except for the benchmark indicators, and the weather indicators comprise: any one or more of temperature, humidity, wind direction, wind speed, cloud cover, rainfall, precipitation and air pollutants; the candidate file further comprises candidate situation graph corresponding time, and the method further comprises the following steps:

determining the time corresponding to the reference situation map according to the reference situation map;

acquiring first reference data of a reference index in the reference region and at the time corresponding to the reference situation map;

acquiring second reference data of the reference index in the reference area and at the time corresponding to the target situation map;

calculating a first difference value of the reference index according to the first reference data and the second reference data, wherein the first difference value is a difference value of the reference index in the reference area, at the time corresponding to the reference situation diagram and at the time corresponding to the target situation diagram;

acquiring third reference data of a reference index in the reference area after a preset time period corresponding to the target situation map;

calculating a second difference value of the reference index according to second reference data and third reference data, wherein the second difference value is a difference value of the reference index in the reference area after a preset time period of the target situation diagram corresponding time and the target situation diagram corresponding time;

calculating the change rate of the reference index in a preset time period according to the second difference and the preset time period;

acquiring a third difference value of the reference index, wherein the third difference value is the difference value of the reference index in the reference area, at the time corresponding to the reference situation map and at the time corresponding to the target situation map;

and outputting any one or more of the target situation map, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index in a preset time period and the third difference so that the user can predict weather according to any one or more of the target situation map, the first reference data, the second reference data, the first difference, the third reference value, the second difference, the change rate of the reference index in the preset time period and the third difference.

9. A similar weather situation recognition apparatus, comprising:

the system comprises a receiving module, a judging module and a judging module, wherein the receiving module is used for receiving a similar weather situation identification request triggered by a user, and the similar weather situation identification request comprises a reference situation graph;

the first determination module is used for determining a reference area and a reference index according to the reference situational map;

the first acquisition module is used for acquiring relevant data of the candidate situation map matched with the reference area and the reference index;

the second determination module is used for determining the related data of the target situation map similar to the reference situation according to the related data of the candidate situation map;

and the second acquisition module is used for acquiring the target situation map according to the relevant data of the target situation map.

10. An electronic device, comprising: a memory, a processor, and a transceiver;

the memory, the processor and the transceiver circuitry are interconnected;

the memory stores computer-executable instructions;

the transceiver is used for transceiving data;

the processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1 to 8.

11. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of any one of claims 1 to 8.

Images