Visited crowd data processing method and device, equipment and storage medium

Abstract

The invention provides a visiting crowd data processing method and device, equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: determining search input information according to a data depression part in visited population data of a target area; calling a real-time search engine result capture service API according to the search input information to obtain first depression filling content; according to a non-data depression part in the visited population data, utilizing a preset data trend prediction model to obtain a second depression filling content; and based on the first depression filling content and the second depression filling content, performing filling processing on the data depression part in the visited crowd data to obtain the processed visited crowd data, thereby preventing the accuracy of various data analysis results based on the visited crowd data from being influenced by the data depression in the visited crowd data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for processing visitor data. Background Art

[0002] Data depressions refer to data that is large in volume but low in quality, disorganized, and difficult to use effectively. For visitor data in a certain area, the data depressions it contains will affect the accuracy of the results of various data analyses such as "traffic trend analysis", "crowd portrait analysis", "demand analysis", "safety hazard assessment", and "time series analysis", and cannot provide strong data support for relevant decisions in the corresponding area. Summary of the invention

[0003] The present invention provides a method, device, electronic device and computer-readable storage medium for processing visitor data, which can fill data depressions in visitor data and ensure the accuracy of various data analysis results based on the visitor data.

[0004] The embodiments of the present invention can be implemented as follows:

[0005] In a first aspect, the present invention provides a method for processing visitor data, which is applied to an electronic device, wherein a real-time search engine result crawling service API is deployed on the electronic device, and the method comprises:

[0006] Determine the search input information based on the data depression in the visitor data of the target area;

[0007] Calling the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content;

[0008] According to the non-data depression part in the visitor population data, using a preset data trend prediction model, obtaining the second depression filling content;

[0009] Based on the first depression filling content and the second depression filling content, a filling process is performed on the data depression part in the visitor population data to obtain processed visitor population data.

[0010] Optionally, the data depression portion includes a plurality of data points, and the step of determining the search input information according to the data depression portion in the visitor population data of the target area includes:

[0011] A search input statement corresponding to each of the data points is generated according to the area information of the target area and the visit time corresponding to each of the data points, and the search input information includes the search input statement corresponding to each of the data points.

[0012] Optionally, the data depression portion includes a plurality of data points, the search input information includes a search input statement corresponding to each of the data points, and the step of calling the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content includes:

[0013] For each of the data points, calling the real-time search engine result crawling service API according to the search input statement corresponding to the data point to obtain the online search results corresponding to the data point;

[0014] Extracting first filling information corresponding to the data point from the online search results corresponding to the data point using a preset information extraction model;

[0015] The first depression filling content includes first filling information corresponding to each of the data points.

[0016] Optionally, the data depression portion includes a plurality of data points, and the step of obtaining the second depression filling content according to the non-data depression portion in the visitor population data by using a preset data trend prediction model includes:

[0017] Inputting the non-data depression part into the preset data trend prediction model for data prediction;

[0018] Based on the visit time corresponding to each of the data points in the data depression part, the second filling information corresponding to each of the data points is extracted from the output result of the preset data trend prediction model, and the second depression filling content includes the second filling information corresponding to each of the data points.

[0019] Optionally, the data depression portion includes a plurality of data points, the first depression filling content includes first filling information corresponding to each of the data points, the second depression filling content includes second filling information corresponding to each of the data points, and the step of performing filling processing on the data depression portion in the visitor population data based on the first depression filling content and the second depression filling content to obtain the processed visitor population data includes:

[0020] For each of the data points, determining valid filling information corresponding to the data point according to the first filling information and the second filling information corresponding to the data point;

[0021] The data depression of the visitor population data is filled using the valid filling information corresponding to each data point to obtain the processed visitor population data.

[0022] Optionally, the first filling information includes a first filling value, the second filling information includes a second filling value, the valid filling information includes a valid filling value, and the step of determining the valid filling information corresponding to the data point according to the first filling information and the second filling information corresponding to the data point includes:

[0023] When the first filling value is not a preset value, taking an average of the first filling value and the second filling value as the effective filling value;

[0024] In the case where the first filling value is a preset value, the first filling value is used as the effective filling value.

[0025] In a second aspect, the present invention provides a visitor data processing device, which is applied to an electronic device, on which a real-time search engine result crawling service API is deployed, and the device comprises:

[0026] A determination module, used to determine search input information according to a data depression portion in the visitor population data of a target area;

[0027] An acquisition module is used to call the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content; and obtain the second depression filling content according to the non-data depression part in the visitor population data using a preset data trend prediction model;

[0028] A processing module is used to perform filling processing on the data depression part in the visitor population data based on the first depression filling content and the second depression filling content to obtain processed visitor population data.

[0029] Optionally, the data depression portion includes a plurality of data points, the first depression filling content includes first filling information corresponding to each of the data points, and the second depression filling content includes second filling information corresponding to each of the data points;

[0030] The processing module is specifically used to determine, for each of the data points, the valid filling information corresponding to the data point based on the first filling information and the second filling information corresponding to the data point; and use the valid filling information corresponding to each data point to fill the data depression part of the visitor data to obtain the processed visitor data.

[0031] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for processing visitor data as described in the first aspect above is implemented.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for processing visitor data as described in the first aspect.

[0033] Compared with the prior art, the present invention provides a method for processing visitor data: determining search input information according to the data depression part in the visitor data of the target area; calling the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content; obtaining the second depression filling content according to the non-data depression part in the visitor data using the preset data trend prediction model; filling the data depression part in the visitor data based on the first depression filling content and the second depression filling content to obtain the processed visitor data. Since the present invention uses the search input information determined based on the data depression part to call the real-time search engine result crawling service API to obtain the first depression filling content, uses the non-data depression part and the preset data trend prediction model to obtain the second depression filling content, and then uses the first depression filling content and the second depression filling content to fill the data depression part, the accuracy of various data analysis results based on the visitor data is avoided from being affected by the data depression in the visitor data.

[0034] Other features and advantages disclosed in the present invention will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present invention.

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A schematic diagram of a flow chart of a method for processing visitor data provided by an embodiment of the present invention;

[0038] Figure 2 An example diagram of visitor data provided by an embodiment of the present invention;

[0039] Figure 3 An example diagram of forecast data generated using ARIMA provided by an embodiment of the present invention;

[0040] Figure 4 An example diagram of prediction data generated using LightBGM provided in an embodiment of the present invention;

[0041] Figure 5 An example diagram of second depression filling content provided by an embodiment of the present invention;

[0042] Figure 6 An example diagram of visitor data before and after processing provided by an embodiment of the present invention;

[0043] Figure 7 A functional unit block diagram of a visitor data processing device provided by an embodiment of the present invention;

[0044] Figure 8 A schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0045] Icons: 100 - visitor data processing device; 101 - determination module; 102 - acquisition module; 103 - processing module; 200 - electronic device; 210 - memory; 220 - processor. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, 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 described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0049] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.

[0050] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0051] In order to ensure the accuracy of various data analysis results based on visitor data, an embodiment of the present invention provides a visitor data processing method, which will be described in detail below.

[0052] Please refer to Figure 1 The method for processing visitor data includes steps S101 to S104.

[0053] S101, determining search input information according to a data depression portion in visitor data of a target area.

[0054] The visitor data may be a time series, recording the number of visitors to the target area within each unit time.

[0055] For example, the visitor data of Shopping Mall A contains 887 data points, as shown in the following table. The data point numbered 0 means that 2,657 people visited Shopping Mall A on February 1, 2022, and the data point numbered 884 means that 13,759 people visited Shopping Mall A on July 4, 2024.

[0056]

[0057]

[0058] The trend of the above visitor data is judged, such as Figure 2 As shown, in the red box area, the data trend is obviously concave downward, and this data is the data depression part. Correspondingly, the other areas are non-data depression parts.

[0059] The search input information includes a search input statement corresponding to each data point in the data depression part. In an embodiment of the present invention, a search input statement corresponding to each data point can be generated according to the area information of the target area and the visit time corresponding to each data point.

[0060] The area information of the target area may be the target area name, and the target area name and the visit time corresponding to each data point may be used to fill in a preset statement template to generate a search input statement corresponding to each data point.

[0061] For example, it is assumed that the data depression part in the crowd visit data of shopping mall A includes data points numbered 721 to 754. For the data point numbered 721, its corresponding visit time is 2024-02-17.

[0062] Assuming that the preset statement template is "How many visits were there at {time} {target area name}", fill the visit time "2024-02-17" and the target area name "A Shopping Mall" into the corresponding positions in the preset statement template, and obtain the search input statement "How many visits were there at A Shopping Mall on February 17, 2024" corresponding to the data point numbered 721.

[0063] S102, calling a real-time search engine result crawling service API according to the search input information to obtain the first depression filling content.

[0064] The first depression filling content includes first filling information corresponding to each data point in the data depression part.

[0065] In a possible implementation, for each data point, a real-time search engine result crawling service API is called according to the search input statement corresponding to the data point to obtain the online search results corresponding to the data point; and a preset information extraction model is used to extract the first filling information corresponding to the data point from the online search results corresponding to the data point.

[0066] Among them, the real-time search engine result crawling service API is a program interface that allows users to automatically obtain real-time search results from search engines. By calling the real-time search engine result crawling service API, it simulates the search behavior of real users on the search engine, crawls and parses the search result page, and obtains networked search results.

[0067] In a possible implementation, the real-time search engine result crawling service API may be SerpApi, and search results of various search engines including Google, Bing, Yahoo, Yandex, etc. are obtained through SerpApi.

[0068] The preset information extraction model may be a large language model, and a prompt may be written to guide the large language model to identify and extract the required first filler information from the online search results.

[0069] For example, assuming that the search input statement corresponding to a data point is "How many visitors did Mall A have on February 17, 2024", SerpApi is called according to the search input statement to search in various search engines.

[0070] For the online search results returned by SerpApi, write Prompt to input the big language model, so that the big language model can extract the first fill information including location, time and number of people from the online search results through the instructions of Prompt.

[0071] The prompt you write can be:

[0072] From this text {online search results}, extract key information and return it in JSON format:

[0073] The returned format is {

[0074] location: location, such as: City X, Shopping Mall A, Hospital B, Station C, etc.

[0075] date: time, such as: 2023-07-10;

[0076] person-cnt: number of people, default value: 0, such as how many people visited, traveled, or visited the place. If the specific value cannot be found, the default value is used.

[0077] The information in the returned format is extracted from the specified text, do not convert to other languages, do not add any information to the JSON, and do not provide any explanatory notes.

[0078] S103, obtaining second depression filling content according to the non-data depression part in the visitor population data by using a preset data trend prediction model.

[0079] Among them, the preset data trend prediction model refers to a model for predicting the data trend of visiting population data.

[0080] The second depression filling content includes the second filling information corresponding to each data point. In a possible implementation, the non-data depression part can be input into a preset data trend prediction model for data prediction; based on the arrival time corresponding to each data point in the data depression part, the second filling information corresponding to each data point is extracted from the output result of the preset data trend prediction model.

[0081] In the embodiment of the present invention, the preset data trend prediction model is obtained by comparing and testing the ARIMA and LightBGM models.

[0082] Use ARIMA to predict the test data, such as Figure 3 As shown, the green line is the test part of the experimental data, and the red line is the ARIMA forecast data corresponding to the test part. It can be seen that the trend difference between the ARIMA forecast data and the test part.

[0083] The average absolute error between the two is 2465.75, and the average absolute percentage error is 0.163.

[0084] Use LightGBM to predict the test data, such as Figure 4As shown, the green line is the test part of the experimental data, and the red line is the LightGBM predicted data corresponding to the test part. It can be observed that the trend of the LightGBM predicted data is obviously similar to that of the test part. The average absolute error between the two is 1959.49, and the average absolute percentage error is 0.136.

[0085] Since LightGBM has lower mean absolute error and mean absolute percentage error, LightBGM is determined as the preset data trend prediction model.

[0086] In the embodiment of the present invention, the non-data depression part before the data depression part in the visitor population data is input into LightBGM to perform data trend prediction, such as Figure 5 As shown, the green line is the data depression part in the visiting population data, and the red line is the LightBGM prediction result within the time range corresponding to the data depression part.

[0087] The data depression part includes multiple data points, and the LightBGM prediction result also includes multiple data points. For any target data point in the data depression part, the content of the data point in the LightBGM prediction result that has the same arrival time as the target data point is used as the second filling information of the target data point.

[0088] S104, based on the first depression filling content and the second depression filling content, fill the data depression part in the visitor population data to obtain processed visitor population data.

[0089] In a possible implementation, the implementation process of step S104 can be to determine, for each data point, the valid filling information corresponding to the data point based on the first filling information and the second filling information corresponding to the data point; use the valid filling information corresponding to each data point to fill the data depression part of the visitor data to obtain the processed visitor data.

[0090] Among them, the first depression filling content includes the first filling information corresponding to each data point in the data depression part, and the first filling information corresponding to each data point includes the visit time and the first filling value. The first filling value refers to the number of visitors extracted from the networked search results obtained based on the search input statement corresponding to the data point.

[0091] The second depression filling content includes the second filling information corresponding to each data point in the data depression part. The second filling information corresponding to each data point includes the visit time and the second filling value. The second filling value refers to the number of visitors extracted from the prediction results output by LightBGM.

[0092] It can be understood that the effective fill information includes the visit time and the effective fill value. The effective fill value refers to the final number of visitors at the corresponding visit time determined based on the number of visitors extracted from the online search results obtained based on the search input statement corresponding to the data point and the number of visitors extracted from the predicted results output by LightBGM.

[0093] For any data point, the corresponding first filling information, second filling information and the access time in the effective filling information are the same, and the effective filling value is determined by the first filling value and the second filling value. There are two situations in the determination process:

[0094] In case one, when the first filling value is not a preset value, the average of the first filling value and the second filling value is taken as the effective filling value.

[0095] In scenario two, when the first filling value is a preset value, the first filling value is used as a valid filling value.

[0096] The preset value can be set according to actual needs. For example, assuming that the preset value is 0, the visit time is recorded as date, the first fill value is recorded as llm_cnt, the second fill value is recorded as forecast_cnt, and the effective fill value is recorded as visit_cnt.

[0097] Assume that the date corresponding to a data point is 2024-02-17, llm_cnt=21500, forecast_cnt=12965. Since llm_cnt is not equal to 0, visit_cnt=(llm_cnt+forecast_cnt) / 2=(21500+12965) / 2=17232.5, that is, the number of visitors to the target area on February 17, 2024 is 17232.5.

[0098] For each data point in the data depression part, the above method is used to calculate the effective filling value corresponding to the data point, and the current value of each data point is replaced with the calculated effective filling value, thereby completing the filling process of the data depression in the visitor population data.

[0099] For example, Figure 6 As shown, after the data depression part of the visitor data of Shopping Mall A from February 1, 2022 to July 7, 2024 was filled and processed in the above way, the number of visitors on each date corresponding to the data depression part was increased to a certain extent and was in line with the historical data trend.

[0100] In order to execute the corresponding steps in the above method embodiment and various possible implementations, an implementation of the visitor data processing device 100 is provided below.

[0101] Please refer to Figure 7 The visitor data processing device 100 includes a determination module 101 , an acquisition module 102 and a processing module 103 .

[0102] The determination module 101 is used to determine the search input information according to the data depression part in the visitor population data of the target area.

[0103] The acquisition module 102 is used to call the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content; according to the non-data depression part in the visiting population data, using the preset data trend prediction model, obtain the second depression filling content.

[0104] The processing module 103 is used to fill the data depression part in the visitor population data based on the first depression filling content and the second depression filling content to obtain the processed visitor population data.

[0105] Optionally, the data depression portion includes multiple data points, and the determination module 101 is specifically used to generate a search input statement corresponding to each data point based on the area information of the target area and the visit time corresponding to each data point, and the search input information includes the search input statement corresponding to each data point.

[0106] Optionally, the data depression portion includes multiple data points, and the search input information includes a search input statement corresponding to each data point. The acquisition module 102 is specifically used to call the real-time search engine result crawling service API for each data point according to the search input statement corresponding to the data point, to obtain the networked search results corresponding to the data point; use a preset information extraction model to extract the first filling information corresponding to the data point from the networked search results corresponding to the data point; wherein the first depression filling content includes the first filling information corresponding to each data point.

[0107] Optionally, the data depression part includes multiple data points, and the acquisition module 102 is also specifically used to input the non-data depression part into a preset data trend prediction model for data prediction; based on the arrival time corresponding to each data point in the data depression part, the second filling information corresponding to each data point is extracted from the output result of the preset data trend prediction model, and the second depression filling content includes the second filling information corresponding to each data point.

[0108] Optionally, the data depression portion includes multiple data points, the first depression filling content includes first filling information corresponding to each data point, and the second depression filling content includes second filling information corresponding to each data point. The processing module 103 is specifically used to determine, for each data point, the valid filling information corresponding to the data point according to the first filling information and the second filling information corresponding to the data point; and use the valid filling information corresponding to each data point to fill the data depression portion of the visitor data to obtain the processed visitor data.

[0109] Optionally, the first filling information includes a first filling value, the second filling information includes a second filling value, and the valid filling information includes a valid filling value. When the processing module 103 is used to determine the valid filling information corresponding to a data point based on the first filling information and the second filling information corresponding to the data point, it is specifically used to, when the first filling value is not a preset value, use the average of the first filling value and the second filling value as the valid filling value; when the first filling value is a preset value, use the first filling value as the valid filling value.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the visitor data processing device 100 described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0111] Furthermore, the embodiment of the present invention also provides an electronic device 200, please refer to Figure 8 , the electronic device 200 may include a memory 210 and a processor 220 .

[0112] The processor 220 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of a program of a visitor data processing method provided in the above method embodiment.

[0113] The memory 210 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 210 may exist independently and be connected to the processor 220 via a communication bus. The memory 210 may also be integrated with the processor 220. Among them, the memory 210 is used to store machine executable instructions for executing the scheme of the present application. The processor 220 is used to execute the machine executable instructions stored in the memory 210 to implement the above-mentioned method embodiment.

[0114] An embodiment of the present invention further provides a computer-readable storage medium containing a computer program. When the computer program is executed, it can be used to perform relevant operations in a method for processing visitor data provided in the above method embodiment.

[0115] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for processing visitor data, characterized in that: Applied to an electronic device, on which a real-time search engine result crawling service API is deployed, the method comprises: Determine the search input information based on the data depression in the visitor data of the target area; Calling the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content; According to the non-data depression part in the visitor population data, using a preset data trend prediction model, obtaining the second depression filling content; Based on the first depression filling content and the second depression filling content, a filling process is performed on the data depression part in the visitor population data to obtain processed visitor population data.

2. The method according to claim 1, characterized in that The data depression portion includes a plurality of data points, and the step of determining the search input information according to the data depression portion in the visitor population data of the target area includes: A search input statement corresponding to each of the data points is generated according to the area information of the target area and the visit time corresponding to each of the data points, and the search input information includes the search input statement corresponding to each of the data points.

3. The method according to claim 1, characterized in that The data depression portion includes a plurality of data points, the search input information includes a search input statement corresponding to each of the data points, and the step of calling the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content includes: For each of the data points, calling the real-time search engine result crawling service API according to the search input statement corresponding to the data point to obtain the online search results corresponding to the data point; Extracting first filling information corresponding to the data point from the online search results corresponding to the data point using a preset information extraction model; The first depression filling content includes first filling information corresponding to each of the data points.

4. The method according to claim 1, characterized in that The data depression portion includes a plurality of data points, and the step of obtaining the second depression filling content according to the non-data depression portion in the visitor population data by using a preset data trend prediction model includes: Inputting the non-data depression part into the preset data trend prediction model for data prediction; Based on the visit time corresponding to each of the data points in the data depression part, the second filling information corresponding to each of the data points is extracted from the output result of the preset data trend prediction model, and the second depression filling content includes the second filling information corresponding to each of the data points.

5. The method according to claim 1, characterized in that The data depression portion includes a plurality of data points, the first depression filling content includes first filling information corresponding to each of the data points, the second depression filling content includes second filling information corresponding to each of the data points, and the step of performing filling processing on the data depression portion in the visitor population data based on the first depression filling content and the second depression filling content to obtain the processed visitor population data includes: For each of the data points, determining valid filling information corresponding to the data point according to the first filling information and the second filling information corresponding to the data point; The data depression of the visitor population data is filled using the valid filling information corresponding to each data point to obtain the processed visitor population data.

6. The method according to claim 5, characterized in that The first filling information includes a first filling value, the second filling information includes a second filling value, the valid filling information includes a valid filling value, and the step of determining the valid filling information corresponding to the data point according to the first filling information and the second filling information corresponding to the data point includes: When the first filling value is not a preset value, taking an average of the first filling value and the second filling value as the effective filling value; In the case where the first filling value is a preset value, the first filling value is used as the effective filling value.

7. A visitor data processing device, characterized in that: Applied to an electronic device, on which a real-time search engine result crawling service API is deployed, the device comprises: A determination module, used to determine search input information according to a data depression portion in the visitor population data of a target area; An acquisition module is used to call the real-time search engine result crawling service API according to the search input information to obtain the first depression filling content; and obtain the second depression filling content according to the non-data depression part in the visitor population data using a preset data trend prediction model; A processing module is used to perform filling processing on the data depression part in the visitor population data based on the first depression filling content and the second depression filling content to obtain processed visitor population data.

8. The device according to claim 7, characterized in that The data depression portion includes a plurality of data points, the first depression filling content includes first filling information corresponding to each of the data points, and the second depression filling content includes second filling information corresponding to each of the data points; The processing module is specifically used to determine, for each of the data points, the valid filling information corresponding to the data point based on the first filling information and the second filling information corresponding to the data point; and use the valid filling information corresponding to each data point to fill the data depression part of the visitor data to obtain the processed visitor data.

9. An electronic device, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for processing visitor data as claimed in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the visitor data processing method as described in any one of claims 1 to 6.

Images