A business object sorting method and device

Abstract

The present application relates to the technical field of big data processing, and specifically discloses a business object ranking method and device, the method comprising: obtaining a target public opinion data set, determining the absolute volume of each business object in a target sub-region and a target region, and the absolute volume of multiple business objects in a target sub-region and a target region using the target public opinion data set, and selecting a target business object based on the absolute volume of each business object in the target sub-region; determining the relative volume of each target business object in the target sub-region according to the absolute volume of each business object in the target sub-region and the target region, and the absolute volume of multiple business objects in the target sub-region and the target region; and ranking multiple target business objects based on the absolute volume and the relative volume to obtain a business object sequence in the target sub-region. The embodiments of the present application can accurately determine the ranking of business objects in each sub-region that are popular in the entire mainstream market.

Description

Technical Field

[0001] The present application relates to the field of big data processing technology, and in particular to a business object sorting method and device. Background Art

[0002] With the development of the Internet industry, especially mobile Internet, information promotion through the Internet has become a new form of information dissemination and has been widely used.

[0003] At present, when promoting information about some business objects, the promotion platform often combines the historical search and historical visit information of each city to count the business objects that are most popular with users in the city, and then recommends them in the user page of the city after ranking them according to the degree of user attention. However, in the above-mentioned prior art, the ranking of business objects in subsequent recommendations is only planned based on the interests of historical users in each city, which cannot form a good representativeness of users in the entire mainstream market, resulting in the inability to accurately determine the ranking of business objects that are popular in the entire mainstream market in each city, resulting in a continuous increase in the deviation between the actual users of the business objects and the users in the mainstream market. Therefore, a more effective solution needs to be provided. Summary of the invention

[0004] The present application provides a business object ranking method and device, which can accurately determine the ranking of business objects popular in each sub-region in the entire mainstream market, reduce the deviation between actual users of business objects and mainstream market users, and greatly improve the business object recommendation effect.

[0005] In one aspect, the present application provides a method for sorting business objects, the method comprising:

[0006] Acquire a target public opinion data set of multiple business objects in a target area, wherein each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area;

[0007] Determine the absolute volume of each business object in a target sub-area, the absolute volume of the multiple business objects in the target sub-area, the absolute volume of each business object in the target area, and the absolute volume of the multiple business objects in the target area by using the target public opinion dataset, wherein the target sub-area is any sub-area in the target area;

[0008] Based on the absolute sound volume of each business object in the target sub-area, selecting a plurality of target business objects corresponding to the target sub-area;

[0009] Determine the relative sound volume of each target business object in the target sub-area according to the absolute sound volume of each target business object in the target sub-area, the absolute sound volume of each target business object in the target area, the absolute sound volumes of the multiple business objects in the target sub-area, and the absolute sound volumes of the multiple business objects in the target area;

[0010] The multiple target business objects are sorted based on the absolute sound volume and the relative sound volume of each target business object in the target sub-area to obtain a business object sequence of the target sub-area.

[0011] Another aspect provides a business object sorting device, the device comprising:

[0012] A target public opinion data set acquisition module, used to acquire a target public opinion data set of multiple business objects in a target area, wherein each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area;

[0013] An absolute volume determination module, used to determine the absolute volume of each business object in a target sub-area, the absolute volumes of the multiple business objects in the target sub-area, the absolute volume of each business object in the target area, and the absolute volume of the multiple business objects in the target area using the target public opinion data set, wherein the target sub-area is any sub-area in the target area;

[0014] A target business object selection module, configured to select a plurality of target business objects corresponding to the target sub-area based on the absolute sound volume of each business object in the target sub-area;

[0015] a relative sound volume determination module, configured to determine the relative sound volume of each target business object in the target sub-area according to the absolute sound volume of each target business object in the target sub-area, the absolute sound volume of each target business object in the target area, the absolute sound volumes of the multiple business objects in the target sub-area, and the absolute sound volumes of the multiple business objects in the target area;

[0016] The sorting module is used to sort the multiple target business objects based on the absolute sound volume and relative sound volume of each target business object in the target sub-area to obtain a business object sequence in the target sub-area.

[0017] On the other hand, a business object sorting device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the business object sorting method as described above.

[0018] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the business object sorting method as described above.

[0019] The business object sorting method and device provided by this application have the following technical effects:

[0020] This application calculates the absolute voice and relative voice indicators of business objects in different sub-regions through public opinion data. By combining the absolute voice and relative voice indicators, it can form a good representativeness of users in the entire mainstream market, and rank multiple target business objects with higher absolute voice in each sub-region by combining the absolute voice and relative voice indicators. It can accurately determine the ranking of business objects in each sub-region that are popular in the entire mainstream market, narrow the deviation between actual users of business objects and users in the mainstream market, and greatly improve the business object recommendation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

[0023] Figure 2 It is a flowchart of a method for sorting business objects provided in an embodiment of the present application;

[0024] Figure 3 It is a flowchart of obtaining a target public opinion data set of multiple business objects in a target area provided by an embodiment of the present application;

[0025] Figure 4 This is a schematic diagram of a process for preprocessing an original public opinion content set provided by an embodiment of the present application;

[0026] Figure 5 is a schematic diagram of a process for determining absolute sound volume provided by an embodiment of the present application;

[0027] Figure 6 This is a schematic diagram of a process for determining a relative sound volume of a target service object in a target sub-area provided by an embodiment of the present application;

[0028] Figure 7It is a flow chart of obtaining a sequence of business objects in the target sub-area by sorting the multiple target business objects based on the absolute sound volume and relative sound volume of each target business object in the target sub-area provided by an embodiment of the present application;

[0029] Figure 8 It is a structural schematic diagram of a business object sorting device provided in an embodiment of the present application;

[0030] Fig. 9 This is a hardware structure block diagram of a server for implementing a business object sorting method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar business objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0033] See also Figure 1 , Figure 1 is a schematic diagram of an application environment provided by an embodiment of the present application, such as Figure 1 As shown, the application environment may include a terminal 01 , a server 02 and a terminal 03 .

[0034] In the embodiments of this specification, terminal 01 may include at least one terminal of a business promotion platform. Specifically, terminal 01 may be used to promote and display business objects in a target area. Specifically, the target area may be all promotion areas where the business promotion platform promotes business objects, such as a country, an Asian region, etc. Specifically, the business object may be the information itself promoted on the business promotion platform, or the brand, enterprise, institution, etc. corresponding to the information. Specifically, terminal 01 may include but is not limited to physical devices of the type of smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices, etc. It may also be software running on a physical device, such as an application, a web page, etc. The operating system running on the physical device in the embodiments of this application may include but is not limited to Android systems, IOS systems, linux, windows, etc.

[0035] In the embodiment of the present specification, the server 02 can be used to calculate the absolute volume and relative volume of each business object in the target sub-area based on the target public opinion data of multiple business objects in the target area of ​​at least one business promotion platform, and to sort the business objects in the target sub-area based on the absolute volume and relative volume. Specifically, the target sub-area can be any sub-area in the target area. Specifically, for example, the target area is a country, and correspondingly, the target sub-area can be a city in the country, etc. In the embodiment of the present specification, the absolute volume can represent the degree of attention paid to the business object in the target sub-area; the relative volume can represent the relative degree of attention paid to the business object in the target sub-area relative to other sub-areas in the target area. Specifically, the server 02 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. In actual applications, the server 02 may also send the result of sorting the business objects in the target sub-area to the backend server of the business promotion platform. Accordingly, the backend server may promote the business objects in different target sub-areas based on the result of sorting the business objects. In some embodiments, the server 02 may also be the backend server of the business promotion platform. Accordingly, the server 02 may directly promote the business objects in different target sub-areas based on the result of sorting the business objects.

[0036] In the embodiment of this specification, in order to facilitate the business party (the enterprise, organization, etc. corresponding to the business object) to understand the situation of its own business object in different target sub-areas, the server 02 can send data such as the absolute volume and relative volume of each business object in the target sub-area to the terminal 03. Specifically, the terminal 03 can be a terminal for the business party. Specifically, the terminal 03 can include but is not limited to physical devices such as smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices, etc. It can also be software running on a physical device, such as an application, a web page, etc. The operating system running on the physical device in the embodiment of this application can include but is not limited to Android system, IOS system, Linux, Windows, etc.

[0037] In the embodiments of this specification, the above-mentioned terminal and the server may be directly or indirectly connected via wired or wireless communication, and this application does not impose any limitation thereto.

[0038] The embodiments of this specification mainly relate to big data processing and artificial intelligence. Specifically, big data refers to a collection of data that cannot be captured, managed and processed by conventional software tools within a certain time frame. It is a massive, high-growth and diversified information asset that requires a new processing model to have stronger decision-making power, insight discovery and process optimization capabilities. With the advent of the cloud era, big data has also attracted more and more attention. Big data requires special technologies to effectively process large amounts of data within a tolerable time. Technologies suitable for big data include large-scale parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the Internet and scalable storage systems.

[0039] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level technology and software-level technology. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The embodiments of this specification mainly involve machine learning / deep learning in artificial intelligence software technology.

[0040] The following describes a business object sorting method of this application. Figure 2It is a flowchart of a business object sorting method provided in an embodiment of the present application. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only execution order. When the actual system or server product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, in a parallel processor or multi-threaded processing environment). Specifically, Figure 2 As shown, the method may include:

[0041] S201: Acquire a target public opinion dataset of multiple business objects in a target area.

[0042] In the embodiment of this specification, each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area. Specifically, the multiple business objects in the target area can be all business objects in at least one business promotion platform, or all business objects of a certain category in at least one business promotion platform. In a specific embodiment, Figure 3 As shown, obtaining a target public opinion dataset of multiple business objects in a target area may include:

[0043] S2011: Use crawler technology to obtain the original public opinion content set of multiple business objects in the target area;

[0044] S2013: preprocessing the original public opinion content set to obtain a preprocessed public opinion content set;

[0045] S2015: performing business filtering on the pre-processed public opinion content set to obtain a target public opinion content set;

[0046] S2017: Perform object area labeling processing on the target public opinion content set to obtain a target public opinion data set for multiple business objects in the target area.

[0047] In the embodiments of this specification, crawler technology can be combined to crawl the original public opinion content set of multiple business objects in the target area from the terminal side of at least one business promotion platform. In other embodiments, when the server that performs business promotion sorting is itself the background of the business promotion platform, the original public opinion content set can also be directly retrieved.

[0048] In actual applications, in order to ensure the timeliness of data, data within a preset period is often obtained at a certain period as a basis for promotion in the next period. Accordingly, the above-mentioned original public opinion content set can be an original public opinion content set of multiple business objects in the target area generated by at least one business promotion platform within the preset period.

[0049] In the embodiment of the present specification, each original public opinion content in the original public opinion content set may be an information stream formed by user-generated content (UGC) in the business promotion platform. Accordingly, the information stream may include user-generated content, user account information, geographic location information (user location information when posting user-generated content), content address information, forwarding, likes, comments and other information sets in the process of user-generated content dissemination.

[0050] In practical applications, in order to ensure that the original public opinion content in the original public opinion content set can be accurately read, the original public opinion content set can be preprocessed. For details, the preprocessing process can be found in Figure 4 :

[0051] S401: Convert the format of the original public opinion content set to generate a first public opinion content set in a preset format;

[0052] S403: identifying special characters in the first public opinion content set in the preset format, deleting the identified special characters, and obtaining a second public opinion content set;

[0053] S405: performing anomaly detection on the second public opinion content set based on a preset rule, deleting public opinion content with anomalies, and obtaining a third public opinion content set;

[0054] S407: De-duplication processing is performed on the third public opinion content set to obtain the pre-processed public opinion content set.

[0055] In actual applications, when crawler technology is used to obtain the original public opinion content set, the data format of the original public opinion content set is generally a csv (Comma-Separated Values) file; in order to facilitate reading the public opinion content in the file, the original public opinion content set can be format converted into a preset format that is easier to read. Specifically, the preset format may include but is not limited to a txt file.

[0056] In actual applications, some special characters are not related to public opinion content, but they can easily lead to incorrect distinction between different texts when analyzing public opinion content, resulting in erroneous analysis results. Accordingly, these special characters can be deleted. In a specific embodiment, special characters may include but are not limited to "U+200B" (no width character), "U+2028" (row separator), "\\n" (escape line break, which will be mistaken for line break during analysis), "U+00A0" (invisible space), "U+7F6EU+9876U+000AU+0020..." ('top \n' followed by 120 spaces).

[0057] In the embodiments of this specification, in order to ensure the validity and integrity of the acquired public opinion content, the public opinion content set can be detected for anomalies in combination with preset rules, and abnormal public opinion content can be deleted. Specifically, the content items to be included in each public opinion content can be set in combination with actual application requirements, and public opinion content with missing content items can be determined as abnormal public opinion content.

[0058] In the embodiments of the present specification, the public opinion content set may also be deduplicated. Specifically, deduplication may be performed based on the content address information (such as URL) and publication time of each public opinion content.

[0059] In addition, it should be noted that the above Figure 4 This is only an embodiment of preprocessing the original public opinion content set. In practical applications, more or fewer preprocessing steps may be included in combination with actual needs.

[0060] In actual applications, the original public opinion content set crawled by crawler technology relies on external search interfaces, and the external interfaces are all fuzzy matching. Therefore, there are some data in the returned original public opinion content set that are irrelevant to the business object or irrelevant to the volume analysis. Accordingly, the pre-processed public opinion content set can be filtered for business purposes in combination with the actual characteristics of the business object to ensure the validity of the public opinion content in the target public opinion content set after business filtering and the processing efficiency of the subsequent volume analysis. In a specific embodiment, the business filtering of the pre-processed public opinion content set to obtain the target public opinion content set may include:

[0061] 1) based on the designated public opinion content, selecting the public opinion content including the designated public opinion content from the pre-processed public opinion content set;

[0062] 2) Performing business object relevance analysis on the public opinion content including the designated public opinion content to obtain the target public opinion content set.

[0063] In actual applications, some fields (columns) in the public opinion content are useless for volume analysis. Removing them can reduce the size of the data packet and improve analysis efficiency. Accordingly, the specified public opinion content can be set in combination with the data requirements for volume analysis to filter the public opinion content. In the embodiments of this specification, the specified public opinion content can be the demand data for volume analysis of the business object. Specifically, the specified public opinion content can include but is not limited to user-generated content, geographic location information, forwarding, likes, comments, etc.

[0064] In actual applications, some of the public opinion content returned by the crawler data does not actually hit the keywords related to the business object and is irrelevant data. Some data, although it hits the keywords related to the business object, is not relevant data due to the ambiguity of the keywords themselves. Accordingly, in order to better ensure the relevance and data quality between the public opinion content and the business object, the public opinion content can be analyzed for business object relevance. In a specific embodiment, the business object relevance analysis is performed on the public opinion content including the specified public opinion content to obtain the target public opinion content set, which may include:

[0065] 1) Acquire designated keywords and designated reverse words corresponding to the plurality of business objects;

[0066] 2) screening the public opinion content including the specified public opinion content based on the specified keywords and the specified antonym to obtain the target public opinion content set;

[0067] In the embodiments of this specification, the designated keywords may be keywords related to the business object. For example, if the business object is a certain brand, the designated keywords may include the brand name, the category to which the brand belongs (e.g., clothing), etc. In the embodiments of this specification, the designated reverse words may be partially the same as the designated keywords, but may be ambiguous with the designated keywords. For example, if the business object is game A, the name of game A and the name of mobile phone A have the same partial keywords, the overall name of mobile phone A may be a pointing reverse word. Specifically, the designated keywords and designated reverse words here may be pre-set in combination with the actual business object.

[0068] In the embodiments of this specification, public opinion content with specified keywords can be retained, and public opinion content with specified opposite words can be eliminated.

[0069] In other embodiments, machine learning / deep learning may be combined to perform business object relevance analysis. Specifically, the public opinion content including the specified public opinion content may be input into a business relevance filtering model, and a relevance filtering analysis may be performed on the public opinion content including the specified public opinion content in the business relevance filtering model to obtain the target public opinion content set;

[0070] The business relevance filtering model is obtained by training a preset machine learning model based on business positively relevant public opinion content and business negatively relevant public opinion content. Specifically, business positively relevant public opinion content can be public opinion content that includes specified keywords and excludes specified antonyms; business negatively relevant public opinion content can be public opinion content that does not include specified keywords and / or has specified antonyms.

[0071] Furthermore, the target public opinion content set may be subjected to object area labeling processing to obtain a target public opinion data set of multiple business objects in the target area.

[0072] In the embodiments of the present specification, each public opinion content in the target public opinion content set may include user-generated content. Generally, user-generated content includes business objects (business object names). Accordingly, the business object names included in the user-generated content can be combined to label each public opinion content in the target public opinion content set with business objects, and the business object tags (business object names) can be added to the public opinion content.

[0073] In practical applications, each public opinion content in the target public opinion content set may include geographic location information; accordingly, the public opinion content may be regionally labeled using the geographic location information in the public opinion content. Generally, the geographic location information belongs to a certain sub-region. Accordingly, the sub-region may be used as a regional label (for example, city A), and the regional label may be added to the public opinion content.

[0074] Accordingly, in the embodiment of this specification, each public opinion data in the target public opinion data set may include: public opinion content, regional label and business object label;

[0075] In the embodiments of this specification, by marking the object areas for the initial public opinion content set, a mapping relationship between each public opinion content in the initial public opinion content set and the business object, as well as the region, can be established to facilitate subsequent analysis of the public opinion content by business object or region.

[0076] In addition, it should be noted that the above Figure 3 The corresponding embodiment of obtaining a target public opinion data set for multiple business objects in a target area is merely an example. In practical applications, more or fewer steps may be included in combination with actual needs.

[0077] S203: Using the target public opinion data set, determine the absolute volume of each business object in the target sub-area, the absolute volume of the multiple business objects in the target sub-area, the absolute volume of each business object in the target area, and the absolute volume of the multiple business objects in the target area.

[0078] In the embodiment of this specification, the target sub-region is any sub-region of the target region. In a specific embodiment, Figure 5 As shown, using the target public opinion data set to determine the absolute volume of each business object in the target sub-area, the absolute volume of the multiple business objects in the target sub-area, the absolute volume of each business object in the target area, and the absolute volume of the multiple business objects in the target area may include:

[0079] S2031: Generate the absolute volume of the multiple business objects in the target area by using the public opinion content of each public opinion data in the target public opinion data set.

[0080] S2033: Constructing a public opinion dataset of the target sub-region based on the regional label of each public opinion data in the target public opinion dataset.

[0081] S2035: Constructing a public opinion dataset for each business object based on the business object label of each public opinion data in the target public opinion dataset.

[0082] S2037: Determine the public opinion content of each business object in the target sub-region according to the region label in the public opinion data set of each business object.

[0083] S2039: Generate the absolute volume of each business object in the target sub-area using the public opinion content of each business object in the target sub-area.

[0084] S20311: Generate the absolute volume of each business object in the target area using the public opinion content in the public opinion data set of each business object.

[0085] S20313: Generate the absolute volume of the multiple business objects in the target sub-area by using the public opinion content in the public opinion data set of the target sub-area.

[0086] In the embodiment of this specification, the public opinion datasets of different sub-regions or the public opinion datasets of different business objects are constructed by combining the regional labels or business object labels in each public opinion data in the target public opinion dataset;

[0087] In other embodiments, public opinion datasets of different categories may be constructed in combination with the categories to which the business objects belong.

[0088] In some embodiments, the information of likes, forwarding and comments in the public opinion content can be used as the basis for calculating the absolute volume, that is, the publication of user-generated content, each comment, each like and each forwarding can be used as a volume; specifically, the absolute volume of a piece of public opinion content can be the sum of the number of comments, likes, forwarding and 1 (the original number of publications) of the public opinion content. Correspondingly, the absolute volume of each business object in the target sub-area can be the sum of the volume of the public opinion content of the business object in the target sub-area. The absolute volume of each business object in the target area can be the sum of the volume of the public opinion content of the business object in the target area. The absolute volume of multiple business objects in the target sub-area can be the sum of the volume of the public opinion content of multiple business objects in the target sub-area. The absolute volume of multiple business objects in the target area can be the sum of the volume of the public opinion content of multiple business objects in the target area.

[0089] In actual applications, the public opinion data set of each business object can be counted at a certain period (for example, daily), and the absolute volume of each business object in different sub-areas and the absolute volume of each business object in the target area can be counted, so as to timely analyze the daily trend of the absolute volume of each business object. In addition, the daily absolute volume can also be output to the business side to help the business side understand the overall market trend.

[0090] In practical applications, the public opinion data set of each sub-region can be counted at a certain period (for example, weekly), and the absolute volume of each business object in each sub-region within a week can be calculated, so as to analyze the attention paid to business objects in different sub-regions. Correspondingly, the absolute volume within the week can also be output to the business party to help the business party understand the situation in the past week.

[0091] S205: Selecting a plurality of target business objects corresponding to the target sub-area based on the absolute sound volume of each business object in the target sub-area.

[0092] In the embodiment of the present specification, the absolute volume of each business object in the target sub-area can be combined to count several target business objects with a high degree of attention in each target sub-area. Specifically, a larger preset number of business objects can be selected as the multiple target business objects based on the absolute volume of each business object in the target sub-area.

[0093] S207: Determine the relative sound volume of each target business object in the target sub-area according to the absolute sound volume of each target business object in the target sub-area, the absolute sound volume of each target business object in the target area, the absolute sound volumes of the multiple business objects in the target sub-area and the absolute sound volumes of the multiple business objects in the target area.

[0094] Specifically, Figure 6 Determining the relative volume of a target service object in a target sub-area may include:

[0095] S2071: Determine a sub-area volume proportion of each target business object in the target sub-area according to the absolute volume of each target business object in the target sub-area and the absolute volume of the multiple business objects in the target sub-area.

[0096] Specifically, the quotient of the absolute sound volume of each target business object in the target sub-area and the absolute sound volumes of the multiple business objects in the target sub-area may be used as the sub-area sound volume proportion of each target business object in the target sub-area.

[0097] S2073: Determine an average volume proportion of each target business object in the target area according to the absolute volume of each target business object in the target area and the absolute volume of the multiple business objects in the target area;

[0098] Specifically, the quotient of the absolute sound volume of each target business object in the target area and the absolute sound volumes of the multiple business objects in the target area may be used as the average sound volume proportion of each target business object in the target area.

[0099] S2075: Determine the relative volume of each target business object in the target sub-area according to the sub-area volume proportion and the average volume proportion.

[0100] Specifically, the quotient of the sub-region volume ratio and the average volume ratio may be used as the relative volume of each target service object in the target sub-region.

[0101] In the embodiments of the present specification, the relative voice can characterize the relative degree of attention paid to the business object in the target sub-area relative to other sub-areas in the target area (sub-areas in the target area except the target sub-area). That is, "the voice share of the business object in a certain sub-area (sub-area voice share)" is higher or lower than "the voice share of the business object in the entire market (target area)". "The voice share of the business object in the entire market (target area) (average voice share)" can be understood as the average voice level of the business object in different sub-areas of the target area. If "the voice share of the business object in a certain sub-area" is higher than "the average voice level of the business object in the entire market", it means that the development of the business object in this sub-area is better than its development in other sub-areas. Accordingly, for the business party, this sub-area can be used as a candidate "advantage" area.

[0102] S209: Sort the multiple target business objects based on the absolute sound volume and relative sound volume of each target business object in the target sub-area to obtain a business object sequence of the target sub-area.

[0103] In the embodiments of this specification, Figure 7 As shown, sorting the multiple target business objects based on the absolute sound volume and relative sound volume of each target business object in the target sub-area to obtain the business object sequence of the target sub-area may include:

[0104] S2091: De-dimensionalizing the absolute sound volume and the relative sound volume in the target sub-area based on each target business object;

[0105] S2093: generating a comprehensive sound volume of each target business object based on the absolute sound volume after dimensionless processing and the relative sound volume after dimensionless processing corresponding to each target business object;

[0106] S2095: Sort the multiple target business objects from large to small according to the size of the comprehensive sound volume to obtain a business object sequence of the target sub-area.

[0107] In the embodiments of this specification, since the dimensions of the relative sound volume and the absolute sound volume are inconsistent, after de-dimensionalization, the absolute sound volume and the relative sound volume after the de-dimensionalization processing can be combined to generate the comprehensive sound volume of each target business object as the basis for sorting. In a specific embodiment, the product of the absolute sound volume after the de-dimensionalization processing and the relative sound volume after the de-dimensionalization processing can be used as the comprehensive sound volume. In addition, the sum of the absolute sound volume after the de-dimensionalization processing and the relative sound volume after the de-dimensionalization processing can also be used as the comprehensive sound volume.

[0108] In the embodiments of this specification, the specific dimension removal scheme is not limited, and any dimension removal method can be adopted. In a specific embodiment, a deviation normalization method can be adopted to map the relative sound volume and the absolute sound volume to between [0, 1]. Specifically, the following formula can be referred to:

[0109] In which, taking the dimensionless absolute sound volume as an example, x' represents the dimensionless absolute sound volume of any target business object in the target sub-area; x can represent the absolute sound volume of any target business object in the target sub-area, x min is the minimum absolute sound volume among the absolute sound volumes of the target service objects in the target sub-area, x max It is the maximum absolute sound volume among the absolute sound volumes of multiple target business objects in the target sub-area.

[0110] In some other embodiments, the method may further include: promoting the business object in the target sub-area based on the business object sequence of the target sub-area.

[0111] In practical applications, the absolute volume and relative volume of each target business object in the target sub-area can be counted periodically to sort multiple target business objects, obtain a business object sequence for the target sub-area, and promote the business objects in the target sub-area based on the business object sequence in the next period.

[0112] It can be seen from the technical solutions provided in the above embodiments of this specification that this specification calculates the absolute voice and relative voice indicators of business objects in different sub-regions through public opinion data. By combining the absolute voice and relative voice indicators, it is possible to form a better representation of users in the entire mainstream market, and to rank multiple target business objects with higher absolute voice in each sub-region by combining the absolute voice and relative voice indicators. This can accurately determine the ranking of business objects in each sub-region that are popular in the entire mainstream market, reduce the deviation between actual users of business objects and users in the mainstream market, and greatly improve the recommendation effect of business objects.

[0113] The present application also provides a business object sorting device, such as Figure 8 As shown, the device comprises:

[0114] The target public opinion data set acquisition module 810 may be used to acquire a target public opinion data set of multiple business objects in a target area, wherein each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area;

[0115] The absolute volume determination module 820 may be used to determine the absolute volume of each business object in a target sub-area, the absolute volumes of the multiple business objects in the target sub-area, the absolute volume of each business object in the target area, and the absolute volume of the multiple business objects in the target area using the target public opinion dataset, wherein the target sub-area is any sub-area in the target area;

[0116] The target business object selection module 830 may be used to select a plurality of target business objects corresponding to the target sub-area based on the absolute sound volume of each business object in the target sub-area;

[0117] The relative sound volume determination module 840 may be used to determine the relative sound volume of each target business object in the target sub-area according to the absolute sound volume of each target business object in the target sub-area, the absolute sound volume of each target business object in the target area, the absolute sound volumes of the multiple business objects in the target sub-area, and the absolute sound volumes of the multiple business objects in the target area;

[0118] The sorting module 850 may be used to sort the multiple target business objects based on the absolute volume and relative volume of each target business object in the target sub-area to obtain a business object sequence in the target sub-area.

[0119] In some embodiments, the relative sound volume determination module may include:

[0120] a sub-region volume ratio determination unit, configured to determine a sub-region volume ratio of each target business object in the target sub-region according to the absolute volume of each target business object in the target sub-region and the absolute volume of the multiple business objects in the target sub-region;

[0121] an average volume ratio determination unit, configured to determine an average volume ratio of each target business object in the target area according to the absolute volume of each target business object in the target area and the absolute volumes of the multiple business objects in the target area;

[0122] A relative volume determination unit, configured to determine a relative volume of each target service object in the target sub-area according to the sub-area volume proportion and the average volume proportion;

[0123] In some embodiments, the sorting module may include:

[0124] A dimension removal processing unit, configured to perform dimension removal processing on the absolute sound volume and the relative sound volume in the target sub-area based on each target business object;

[0125] A comprehensive sound volume generating unit, configured to generate a comprehensive sound volume for each target business object based on the absolute sound volume after dimension removal processing and the relative sound volume after dimension removal processing corresponding to each target business object;

[0126] The sorting unit is used to sort the multiple target business objects from large to small according to the size of the comprehensive sound volume to obtain a business object sequence of the target sub-area.

[0127] In some embodiments, the target public opinion data set acquisition module may include:

[0128] A data crawling unit, used to obtain original public opinion content sets of multiple business objects in a target area using crawler technology;

[0129] A preprocessing unit, used to preprocess the original public opinion content set to obtain a preprocessed public opinion content set;

[0130] A business filtering unit, used to perform business filtering on the pre-processed public opinion content set to obtain a target public opinion content set;

[0131] The marking processing unit is used to perform object area marking processing on the target public opinion content set to obtain a target public opinion data set of multiple business objects in the target area.

[0132] In some embodiments, the pre-processing unit may include:

[0133] A format conversion unit, used to convert the format of the original public opinion content set to generate a first public opinion content set in a preset format;

[0134] A special character processing unit, used to identify special characters in the first public opinion content set in the preset format, delete the identified special characters, and obtain a second public opinion content set;

[0135] an anomaly detection unit, configured to perform anomaly detection on the second public opinion content set based on a preset rule, delete the public opinion content with anomalies, and obtain a third public opinion content set;

[0136] A deduplication processing unit is used to perform deduplication processing on the third public opinion content set to obtain the pre-processed public opinion content set.

[0137] In some embodiments, the service filtering unit includes:

[0138] A first data screening unit, configured to screen out public opinion content including the designated public opinion content from the pre-processed public opinion content set based on the designated public opinion content;

[0139] The correlation analysis unit is used to perform business object correlation analysis on the public opinion content including the designated public opinion content to obtain the target public opinion content set.

[0140] In some embodiments, the correlation analysis unit may include:

[0141] A related word acquisition unit, used to acquire designated keywords and designated reverse words corresponding to the plurality of business objects;

[0142] A second data screening unit, configured to screen the public opinion content including the specified public opinion content based on the specified keywords and the specified antonym, to obtain the target public opinion content set;

[0143] or,

[0144] A relevance filtering and analysis unit, configured to input the public opinion content including the designated public opinion content into a business relevance filtering model, and perform relevance filtering and analysis on the public opinion content including the designated public opinion content in the business relevance filtering model to obtain the target public opinion content set;

[0145] The business relevance filtering model is obtained by training a preset machine learning model based on business positively relevant public opinion content and business negatively relevant public opinion content.

[0146] In some embodiments, each public opinion data in the target public opinion data set includes: public opinion content, regional label and business object label; the absolute volume determination module may include:

[0147] A first absolute volume generating unit, configured to generate the absolute volumes of the plurality of business objects in the target area by using the public opinion content of each public opinion data in the target public opinion data set;

[0148] A sub-region public opinion data set construction unit, used to construct the public opinion data set of the target sub-region based on the region label of each public opinion data in the target public opinion data set;

[0149] A business object public opinion data set construction unit, used to construct a public opinion data set for each business object based on the business object label of each public opinion data in the target public opinion data set;

[0150] A sub-region public opinion content determination unit, configured to determine the public opinion content of each business object in the target sub-region according to the region label in the public opinion data set of each business object;

[0151] A second absolute volume generating unit is used to generate an absolute volume of each business object in the target sub-area by using the public opinion content of each business object in the target sub-area;

[0152] A third absolute volume generating unit is used to generate an absolute volume of each business object in the target area by using the public opinion content in the public opinion data set of each business object;

[0153] The fourth absolute volume generation unit is used to generate the absolute volumes of the multiple business objects in the target sub-area by using the public opinion content in the public opinion data set of the target sub-area.

[0154] In some embodiments, the apparatus may further include:

[0155] The business object promotion module is used to promote the business objects in the target sub-area based on the business object sequence of the target sub-area.

[0156] The device and method embodiments in the device embodiments are based on the same application concept.

[0157] An embodiment of the present application provides a business object sorting server, which includes a processor and a memory, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the business object sorting method provided in the above method embodiment.

[0158] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0159] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Fig. 9 1 is a hardware structure diagram of a server for implementing a method for sorting business objects provided in an embodiment of the present application. Fig. 9 As shown, the server 900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 910 (the processor 910 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 930 for storing data, and one or more storage media 920 (such as one or more mass storage devices) for storing application programs 923 or data 922. Among them, the memory 930 and the storage medium 920 can be short-term storage or permanent storage. The program stored in the storage medium 920 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 910 can be configured to communicate with the storage medium 920 and execute a series of instruction operations in the storage medium 920 on the server 900. The server 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input and output interfaces 940, and / or, one or more operating systems 921, such as Windows Server TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM etc.

[0160] The input / output interface 940 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 900. In one example, the input / output interface 940 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 940 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0161] It can be understood by those skilled in the art that Fig. 9 The structure shown is only for illustration and does not limit the structure of the above electronic device. Fig. 9 More or fewer components as shown, or with Fig. 9 Different configurations are shown.

[0162] An embodiment of the present application also provides a storage medium, which can be set in a device to store at least one instruction or at least one program related to a business object sorting method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the business object sorting method provided by the above method embodiment.

[0163] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0164] It can be seen from the embodiments of the business object ranking method, device, equipment or storage medium provided by the present application that the present application can accurately determine the ranking of business objects that are popular in the entire mainstream market in each sub-region, narrow the deviation between the actual users of the business objects and the mainstream market users, and greatly improve the business object recommendation effect.

[0165] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0166] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, server, equipment or storage medium embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0167] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0168] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for sorting business objects, characterized in that: The method comprises: Acquire a target public opinion data set of multiple business objects in a target area, wherein each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area; each public opinion data in the target public opinion data set includes: public opinion content, an area label and a business object label; Using the public opinion content, generating the absolute volume of the multiple business objects in the target area; Based on the regional labels, construct a public opinion dataset of the target sub-region; Based on the business object labels, construct a public opinion dataset for each business object; Determine the public opinion content of each business object in the target sub-area according to the area label in the public opinion data set of each business object; Generate the absolute volume of each business object in the target sub-area by using the public opinion content of each business object in the target sub-area; Using the public opinion content in the public opinion data set of each business object, generate the absolute volume of each business object in the target area; Generate the absolute volume of the multiple business objects in the target sub-region by using the public opinion content in the public opinion data set of the target sub-region, where the target sub-region is any sub-region in the target region; Based on the absolute sound volume of each business object in the target sub-area, selecting a plurality of target business objects corresponding to the target sub-area; Determine a sub-area volume proportion of each target business object in the target sub-area according to the absolute volume of each target business object in the target sub-area and the absolute volume of the multiple business objects in the target sub-area; Determine an average volume proportion of each target business object in the target area according to the absolute volume of each target business object in the target area and the absolute volume of the multiple business objects in the target area; Determine the relative volume of each target service object in the target sub-area according to the sub-area volume ratio and the average volume ratio; The multiple target business objects are sorted based on the absolute sound volume and the relative sound volume of each target business object in the target sub-area to obtain a business object sequence of the target sub-area.

2. The method according to claim 1, characterized in that The step of sorting the plurality of target business objects based on the absolute sound volume and the relative sound volume of each target business object in the target sub-area to obtain a business object sequence of the target sub-area comprises: De-dimensionalize the absolute sound volume and the relative sound volume in the target sub-area based on each target business object; Generate a comprehensive sound volume of each target business object based on the absolute sound volume after dimensioning and the relative sound volume after dimensioning corresponding to each target business object; According to the size of the comprehensive sound volume, the multiple target business objects are sorted from large to small to obtain a business object sequence of the target sub-area.

3. The method according to claim 1, characterized in that The step of obtaining a target public opinion data set of multiple business objects in a target area includes: Use crawler technology to obtain the original public opinion content set of multiple business objects in the target area; Preprocessing the original public opinion content set to obtain a preprocessed public opinion content set; Performing business filtering on the pre-processed public opinion content set to obtain a target public opinion content set; The target public opinion content set is subjected to object area labeling processing to obtain a target public opinion data set of multiple business objects in the target area.

4. The method according to claim 3, characterized in that The preprocessing of the original public opinion content set to obtain the preprocessed public opinion content set includes: Performing format conversion on the original public opinion content set to generate a first public opinion content set in a preset format; Identify special characters in the first public opinion content set in the preset format, delete the identified special characters, and obtain a second public opinion content set; Performing anomaly detection on the second public opinion content set based on preset rules, deleting public opinion content with anomalies, and obtaining a third public opinion content set; The third public opinion content set is deduplicated to obtain the pre-processed public opinion content set.

5. The method according to claim 3, characterized in that: The business filtering of the pre-processed public opinion content set to obtain the target public opinion content set includes: Based on the designated public opinion content, filter out the public opinion content including the designated public opinion content from the pre-processed public opinion content set; Business object correlation analysis is performed on the public opinion content including the designated public opinion content to obtain the target public opinion content set.

6. The method according to claim 5, characterized in that The business object correlation analysis is performed on the public opinion content including the designated public opinion content to obtain the target public opinion content set, including: Acquire specified keywords and specified reverse words corresponding to the plurality of business objects; Based on the specified keywords and the specified antonym, the public opinion content including the specified public opinion content is screened to obtain the target public opinion content set; or, Inputting the public opinion content including the designated public opinion content into a business relevance filtering model, performing relevance filtering analysis on the public opinion content including the designated public opinion content in the business relevance filtering model, and obtaining the target public opinion content set; The business relevance filtering model is obtained by training a preset machine learning model based on business positively relevant public opinion content and business negatively relevant public opinion content.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Business object promotion is performed in the target sub-area based on the business object sequence of the target sub-area.

8. A business object sorting device, characterized in that: The device comprises: A target public opinion data set acquisition module, used to acquire a target public opinion data set of multiple business objects in a target area, wherein each public opinion data in the target public opinion data set corresponds to a business object and a sub-area of ​​the target area; An absolute volume determination module, wherein each public opinion data in the target public opinion data set includes: public opinion content, area label and business object label; the absolute volume determination module includes: a first absolute volume generation unit, which is used to generate the absolute volume of the multiple business objects in the target area by using the public opinion content; A sub-region public opinion data set construction unit, used to construct a public opinion data set of a target sub-region based on the region label; A business object public opinion data set construction unit, used to construct a public opinion data set for each business object based on the business object label; a sub-region public opinion content determination unit, used to determine the public opinion content of each business object in the target sub-region according to the region label in the public opinion data set of each business object; a second absolute volume generation unit, used to generate the absolute volume of each business object in the target sub-region using the public opinion content of each business object in the target sub-region; a third absolute volume generation unit, used to generate the absolute volume of each business object in the target region using the public opinion content in the public opinion data set of each business object; a fourth absolute volume generation unit, used to generate the absolute volumes of the multiple business objects in the target sub-region using the public opinion content in the public opinion data set of the target sub-region; A target business object selection module, configured to select a plurality of target business objects corresponding to the target sub-area based on the absolute sound volume of each business object in the target sub-area; A relative sound volume determination module, the relative sound volume determination module comprising: a sub-area sound volume ratio determination unit, used to determine the sub-area sound volume ratio of each target business object in the target sub-area according to the absolute sound volume of each target business object in the target sub-area and the absolute sound volumes of the multiple business objects in the target sub-area; an average sound volume ratio determination unit, used to determine the average sound volume ratio of each target business object in the target area according to the absolute sound volume of each target business object in the target area and the absolute sound volumes of the multiple business objects in the target area; a relative sound volume determination unit, used to determine the relative sound volume of each target business object in the target sub-area according to the sub-area sound volume ratio and the average sound volume ratio; The sorting module is used to sort the multiple target business objects based on the absolute sound volume and relative sound volume of each target business object in the target sub-area to obtain a business object sequence in the target sub-area.

9. The device according to claim 8, characterized in that The sorting module comprises: A dimension removal processing unit, configured to perform dimension removal processing on the absolute sound volume and the relative sound volume in the target sub-area based on each target business object; A comprehensive sound volume generating unit, configured to generate a comprehensive sound volume for each target business object based on the absolute sound volume after dimension removal processing and the relative sound volume after dimension removal processing corresponding to each target business object; The sorting unit is used to sort the multiple target business objects from large to small according to the size of the comprehensive sound volume to obtain a business object sequence of the target sub-area.

10. The device according to claim 8, characterized in that The target public opinion data set acquisition module includes: A data crawling unit, used to obtain original public opinion content sets of multiple business objects in a target area using crawler technology; A preprocessing unit, used to preprocess the original public opinion content set to obtain a preprocessed public opinion content set; A business filtering unit, used to perform business filtering on the pre-processed public opinion content set to obtain a target public opinion content set; The marking processing unit is used to perform object area marking processing on the target public opinion content set to obtain a target public opinion data set of multiple business objects in the target area.

11. The device according to claim 10, characterized in that The pre-processing unit comprises: A format conversion unit, used to convert the format of the original public opinion content set to generate a first public opinion content set in a preset format; A special character processing unit, used to identify special characters in the first public opinion content set in the preset format, delete the identified special characters, and obtain a second public opinion content set; an anomaly detection unit, configured to perform anomaly detection on the second public opinion content set based on a preset rule, delete the public opinion content with anomalies, and obtain a third public opinion content set; A deduplication processing unit is used to perform deduplication processing on the third public opinion content set to obtain the pre-processed public opinion content set.

12. The device according to claim 10, characterized in that The service filtering unit comprises: A first data screening unit, configured to screen out public opinion content including the designated public opinion content from the pre-processed public opinion content set based on the designated public opinion content; The correlation analysis unit is used to perform business object correlation analysis on the public opinion content including the designated public opinion content to obtain the target public opinion content set.

13. The device according to claim 12, characterized in that The correlation analysis unit comprises: A related word acquisition unit, used to acquire designated keywords and designated reverse words corresponding to the plurality of business objects; A second data screening unit, configured to screen the public opinion content including the specified public opinion content based on the specified keywords and the specified antonym, to obtain the target public opinion content set; or, A relevance filtering and analysis unit, configured to input the public opinion content including the designated public opinion content into a business relevance filtering model, and perform relevance filtering and analysis on the public opinion content including the designated public opinion content in the business relevance filtering model to obtain the target public opinion content set; The business relevance filtering model is obtained by training a preset machine learning model based on business positively relevant public opinion content and business negatively relevant public opinion content.

14. The device according to any one of claims 8 to 13, characterized in that The device also includes: The business object promotion module is used to promote the business objects in the target sub-area based on the business object sequence of the target sub-area.

15. A business object sorting device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the business object sorting method as described in any one of claims 1-7.

16. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the business object sorting method according to any one of claims 1 to 7.

Images