Method and device for dividing point-of-interest cargo classification labels, equipment and storage medium

Abstract

The invention discloses an interest point cargo classification label division method and device, equipment and a storage medium. The method comprises the steps that interest point information of to-be-divided cargo classification is acquired; based on multi-dimensional data of the name information, the industry and commerce information and the Internet information of the points of interest, respectively calculating the classification label times of each cargo under different dimensions; classifying and summarizing the goods classification label times under different dimensions to obtain a numerical value sum of each goods classification label; and determining the cargo classification label of the interest point according to the numerical value of each cargo classification label and the source proportion of the cargo classification label. According to the scheme, the point-of-interest cargo classification labels can be divided in batches, the manual intervention degree is reduced, the error rate and the missing rate of the point-of-interest cargo labels under a single dimension are made up through multi-dimension data comprehensive evaluation, and the accuracy and the coverage rate of the cargo classification labels are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for dividing classification labels of goods at points of interest. Background Art

[0002] With the development of society and the advancement of technology, the demand for freight has increased dramatically. The analysis of the freight industry is expected to be more refined, and the freight market is expected to be understood from a global perspective. At present, the analysis of freight is mainly concentrated in industries or manufacturers with relatively good digital operations, and it is difficult to understand the overall freight market from various industry dimensions. The analysis of the freight industry is only limited to some industries with perfect digitalization, and it is difficult to conduct data analysis in many industries with imperfect economic output. In order to enrich the current analysis dimensions of the freight industry, the cargo classification label of interest points is introduced to analyze the various cargo market conditions and industry information of the national freight market, optimize the data structure of the freight industry, and enrich the dimensions of freight economic analysis.

[0003] However, in the prior art, manual marking is used to add cargo classification labels to points of interest. This method has low work efficiency and wastes manpower costs. In addition, the data dimension considered in the prior method is single, and errors and omissions are prone to occur during marking. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for dividing classification labels of goods at points of interest, so as to at least solve the technical problems in the related art that it is difficult to automatically add labels and the label coverage rate is low in a single dimension.

[0005] According to one aspect of an embodiment of the present application, a method for dividing a classification label of goods at a point of interest is provided, comprising:

[0006] Obtain information on points of interest for the classification of goods to be classified;

[0007] Based on the name information, business information and Internet information of the point of interest, the number of times each cargo classification label is obtained in different dimensions is calculated respectively;

[0008] Classify and summarize the times of each cargo classification label under the different dimensions to obtain the sum of the values ​​of each cargo classification label;

[0009] The cargo classification label of the point of interest is determined according to the value of each cargo classification label and the source ratio of the cargo classification label.

[0010] In an optional embodiment, based on the name information of the point of interest, calculating the number of times each cargo classification label corresponds to the name of the point of interest includes:

[0011] Segment the names of points of interest and extract keywords;

[0012] Matching corresponding cargo classification labels based on the keywords;

[0013] The ratio of 1 to the number of keywords with cargo classification tags in the name is calculated, and the number of times each cargo classification tag corresponds to the name of the point of interest is obtained based on the product of the ratio and the preset weight coefficient.

[0014] In an optional embodiment, based on the business information of the point of interest, the number of times each commodity classification label corresponding to the business information is calculated includes:

[0015] Analyze the industry classification information, business scope information, and company profile information in the industrial and commercial information;

[0016] Extract keywords from the industry classification information, business scope information, and company profile information respectively, and match them with corresponding goods classification labels;

[0017] Calculate the product of 1 and the preset weight coefficient to get the number of cargo classification labels corresponding to the industry;

[0018] Calculate the ratio of 1 to the number of keywords with goods classification tags in the business scope information, and obtain the number of each goods classification tag corresponding to the business scope based on the product of the ratio and the preset weight coefficient;

[0019] The ratio of 1 to the number of keywords with goods classification tags in the company profile information is calculated, and the number of times each goods classification tag corresponds to the company profile is obtained based on the product of the ratio and the preset weight coefficient.

[0020] In an optional embodiment, based on the Internet information of the point of interest, the number of times each cargo classification label corresponds to the enterprise official website information is calculated, including:

[0021] Search the official website of the company on the Internet according to the name of the point of interest;

[0022] Extract keywords of the goods that the enterprise operates and produces based on the information on the enterprise's official website;

[0023] Match the corresponding cargo classification labels according to the keywords;

[0024] The ratio of 1 to the number of keywords with cargo classification tags in the enterprise's official website information is calculated, and the number of times each cargo classification tag corresponds to the enterprise's official website information is obtained based on the product of the ratio and the preset weight coefficient.

[0025] In an optional embodiment, determining the cargo classification label of the point of interest according to the value of each cargo classification label and the source ratio of the cargo classification label includes:

[0026] Calculate the product of the value of the cargo classification label and the source ratio of the cargo classification label;

[0027] Sort the products from large to small to obtain a preset number of cargo classification labels in the front;

[0028] It is determined whether the source proportion of the front preset number of cargo classification labels is greater than a preset threshold, and the cargo classification labels greater than the preset threshold are used as the cargo classification labels of the points of interest.

[0029] In an optional embodiment, when the number of cargo labels cannot be calculated using the name information, business information, and Internet information multi-dimensional data of the point of interest, it also includes:

[0030] Obtain the vehicle and vehicle cargo classification labels that enter the POI to be divided within a preset time period;

[0031] According to the vehicle cargo classification labels, count the number of vehicles corresponding to each cargo classification label;

[0032] Get the top two cargo classification labels with higher vehicle counts;

[0033] Determine whether the number of vehicles corresponding to the first two cargo classification labels meets the preset proportion of the total number of vehicles with cargo classification labels;

[0034] If satisfied, the first two cargo classification labels are used as the cargo classification labels of the vehicle entering the point of interest;

[0035] If not, the cargo classification label with the highest number of vehicles is used as the cargo classification label of the vehicles entering the point of interest;

[0036] The cargo classification label of the vehicle entering the point of interest is used as the cargo classification label of the point of interest.

[0037] In an optional embodiment, when the classification label of the vehicle and cargo entering the point of interest cannot be calculated, the method further includes:

[0038] Obtaining points of interest within a preset range of points of interest to be divided and cargo classification labels corresponding to the points of interest;

[0039] According to the cargo classification labels corresponding to the points of interest within the preset range, the number of points of interest corresponding to each cargo classification label is counted;

[0040] Get the first two cargo classification labels with the highest number of points of interest;

[0041] Determine whether the number of points of interest corresponding to the first two cargo classification labels satisfies a preset proportion of the total number of points of interest with cargo classification labels;

[0042] If satisfied, the first two cargo classification labels are used as cargo classification labels for nearby points of interest;

[0043] If not, the cargo classification label with the highest number of points of interest is used as the cargo classification label of the nearby points of interest;

[0044] The cargo classification labels of the nearby points of interest are used as the cargo classification labels of the point of interest.

[0045] According to another aspect of the embodiment of the present application, the embodiment of the present application provides a device for dividing classification labels of goods at points of interest, including:

[0046] An acquisition module is used to obtain information of points of interest for the classification of goods to be classified;

[0047] A calculation module, used to calculate the number of each cargo classification label in different dimensions based on the name information, business information and Internet information multi-dimensional data of the point of interest;

[0048] A statistical module, used to classify and summarize the number of each cargo classification label under the different dimensions to obtain the sum of the values ​​of each cargo classification label;

[0049] The determination module is used to determine the cargo classification label of the point of interest according to the value of each cargo classification label and the source ratio of the cargo classification label.

[0050] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the method for dividing the classification labels of goods at points of interest through the computer program.

[0051] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for dividing the classification labels of goods at points of interest when running.

[0052] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0053] The method for dividing the cargo classification labels of points of interest provided in the embodiment of the present application is based on the name information, industrial and commercial information and Internet information of the points of interest, respectively calculates the number of each cargo classification label in different dimensions, conducts a comprehensive analysis of the data in different dimensions, and automatically generates cargo classification labels for the points of interest. This method solves the problem of low efficiency of manual labeling, is less affected by the deviation of a single data source, has a higher comprehensive accuracy, reduces the degree of manual intervention, improves the accuracy and coverage of cargo classification labels, and makes the overall evaluation of data more objective and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0055] Figure 1 is a flowchart of an optional method for dividing POI cargo classification labels according to an embodiment of the present application;

[0056] Figure 2 is a flowchart of another optional method for dividing POI cargo classification labels according to an embodiment of the present application;

[0057] Figure 3 is a structural diagram of an optional device for dividing POI cargo classification labels according to an embodiment of the present application;

[0058] Figure 4 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 creative work should fall within the scope of protection of the present application.

[0060] 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 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 device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0061] The present application relates to a method for dividing cargo classification labels at points of interest, and provides a method for dividing cargo classification labels based on multi-dimensional data such as point of interest names, industrial and commercial information, and Internet information.

[0062] By extracting the name keywords and mapping them to the corresponding goods classification labels, parsing the goods classification corresponding to each dimension of data in the industrial and commercial information, obtaining the main business in the Internet information of the point of interest, and parsing the corresponding goods classification labels through the main business content. Then comprehensively evaluate the goods classification results of the points of interest labels based on the goods classification labels of each dimension. According to this solution, the goods classification labels of the points of interest can be divided in batches, reducing the degree of manual intervention and improving the accuracy and coverage of the goods classification labels of the points of interest.

[0063] The following is combined with Figure 1 The method for dividing the POI cargo classification labels of the embodiment of the present application is described in detail. Figure 1 As shown, the method mainly includes the following steps:

[0064] S101 obtains information on points of interest for goods to be classified.

[0065] In an embodiment of the present application, data of points of interest that need to be divided into cargo classification labels are obtained. The points of interest can be company names, XX logistics park, XX base, and the points of interest should contain at least one of the point of interest name, point of interest latitude and longitude, and point of interest electronic fence.

[0066] Furthermore, the validity of the cargo label of the POI is determined. If the POI ends with the name of a non-cargo place such as a hotel, community, bank, or school, it is determined that the POI does not have cargo classification attributes and does not participate in the subsequent POI label division process. It can also be divided into non-cargo classification related labels and used as other label types of POIs.

[0067] S102 calculates the number of times each cargo classification label is used in different dimensions based on the name information, business information, and Internet information of the point of interest.

[0068] In an optional embodiment, based on the name information of the point of interest, the number of times each cargo classification label corresponds to the name of the point of interest includes: segmenting the name of the point of interest and extracting keywords. Matching the corresponding cargo classification label based on the keywords; calculating the ratio of 1 to the number of keywords with cargo classification labels in the name, and obtaining the number of times each cargo classification label corresponds to the name of the point of interest based on the product of the ratio and a preset weight coefficient.

[0069] Specifically, the precise segmentation mode of Jieba is used to split the segmentation results of the POI names, and the stop words and words irrelevant to the cargo classification labels, such as company, stock, administrative division names, etc., are removed from the POI names to obtain keywords. For example, if the POI name is "Air Conditioning Logistics Park", the keyword "Air Conditioning" is obtained, and the corresponding cargo label is Air Conditioning.

[0070] In one embodiment, if a point of interest name matches multiple cargo classification tags, and the sum of the numbers of the multiple cargo classification tags is 1, the number of each cargo classification tag is calculated according to the following formula:

[0071] L1=1 / n*m1;

[0072] Among them, L1 represents the number of times each cargo classification label corresponds to the name of the point of interest, 1 is a fixed value, indicating that the total number of times multiple cargo classification labels obtained by the point of interest name is 1, n represents the number of keywords with cargo classification labels, and m1 represents the weight coefficient corresponding to the point of interest name. In one embodiment, m1 can be 0.8.

[0073] In an optional embodiment, based on the business information of the point of interest, the number of times each cargo classification label corresponds to the business information is calculated, including: parsing the industry classification information, business scope information, and company profile information in the business information; extracting keywords in the industry classification information, business scope information, and company profile information respectively, and matching the corresponding cargo classification labels; calculating the product of 1 and a preset weight coefficient to obtain the number of cargo classification labels corresponding to the industry; calculating the ratio of 1 to the number of keywords with cargo classification labels in the business scope information, and obtaining the number of cargo classification labels corresponding to the business scope based on the product of the ratio and the preset weight coefficient; calculating the ratio of 1 to the number of keywords with cargo classification labels in the company profile information, and obtaining the number of cargo classification labels corresponding to the company profile based on the product of the ratio and the preset weight coefficient.

[0074] The number of cargo classification labels corresponding to the points of interest can be calculated based on the industry classification information, business scope information, and company profile information in the industrial and commercial information.

[0075] Specifically, the corresponding business information is queried according to the name of the point of interest. If the name of the point of interest completely matches the business information, the business information result is directly used. If the name of the point of interest partially matches the business information, the business information content with the highest similarity between the point of interest name and the business information name is used. If the highest similarity is lower than a certain threshold, it is considered to be invalid business information, and the point of interest label classification corresponding to the business information is not parsed.

[0076] Parse the industry classification information in the industrial and commercial information, and match the corresponding goods classification label according to the industry classification information. One industry classification information matches one goods classification label. Therefore, the number of goods classification labels corresponding to the industry classification information is:

[0077] L2=1*m2;

[0078] Among them, L2 represents the number of goods classification labels corresponding to the industry classification information, m2 represents the weight coefficient of the industry classification information, and m2 is less than m1. For example, m2 is 0.6.

[0079] Analyze the business scope information in the industrial and commercial information, clean the business scope information, and remove the description information that is not related to the goods; use the Jieba article keyword extraction function to extract the top 20 keywords in the business scope. According to the keyword results, match the corresponding goods classification label.

[0080] The number of cargo classification labels corresponding to the business scope is:

[0081] L3=1 / n*m3;

[0082] Among them, L3 represents the number of times each cargo classification label corresponds to the business scope, n represents the number of keywords with cargo classification labels in the business scope, and m3 represents the weight coefficient corresponding to the business scope. m3 is less than m2. For example, m3 is 0.5.

[0083] In one embodiment, the cargo keywords extracted from the business scope and the corresponding cargo classification labels are as follows:

[0084]

[0085]

[0086] As can be seen from the above table, 1 represents the total quantity, 4 represents the number of keywords with goods classification labels, and 0.5 represents the weight coefficient of the set business scope goods label.

[0087] Furthermore, the company profile information in the industrial and commercial information is parsed, and the company profile information is cleaned to extract only the description information related to the goods. The top 20 keywords in the profile are extracted using the Jieba article keyword extraction function. According to the keyword results, the corresponding goods classification labels are matched. The number of times each goods classification label corresponds to the company profile information is calculated according to the following formula:

[0088] L4=1 / n*m4;

[0089] Among them, L4 represents the number of times each commodity classification label corresponds to the enterprise profile, n represents the number of keywords with commodity classification labels in the enterprise profile, and m4 represents the weight coefficient corresponding to the enterprise profile. m4 is less than m3. For example, m4 is 0.3.

[0090] In one embodiment, the goods keywords extracted from the company profile and the corresponding goods classification labels are as follows:

[0091]

[0092]

[0093] As can be seen from the above table, 1 represents the total quantity, 3 represents the number of keywords with goods classification labels, and 0.3 represents the weight coefficient of the set enterprise profile goods classification label.

[0094] In an optional embodiment, the number of cargo classification tags in the official website information of the enterprise is calculated based on the Internet information of the point of interest, including: querying the official website information of the enterprise on the Internet according to the name of the point of interest; extracting keywords of the enterprise's operation and production of goods according to the official website information of the enterprise; matching the corresponding cargo classification tags according to the keywords; calculating the ratio of 1 to the number of keywords with cargo classification tags in the official website information of the enterprise, and obtaining the number of each cargo classification tag corresponding to the official website information of the enterprise based on the product of the ratio and the preset weight coefficient.

[0095] In an exemplary embodiment, the number of times each cargo classification label corresponds to the enterprise official website information is calculated according to the following formula:

[0096] L5=1 / n*m5;

[0097] Among them, L5 represents the number of times each commodity classification label corresponds to the enterprise official website information, n represents the number of keywords with commodity classification labels in the enterprise official website information, and m5 represents the weight coefficient of the enterprise official website information. m5 is less than m1, for example, m5 is 0.5.

[0098] This application calculates the number of cargo classification labels of points of interest from multiple dimensions, including point of interest name, industrial and commercial industry information, industrial and commercial business scope information, industrial and commercial enterprise profile information, and business cargo scope information on the official website of the enterprise.

[0099] S103 classifies and summarizes the number of times of each cargo classification label under different dimensions to obtain the sum of the values ​​of each cargo classification label.

[0100] In one embodiment of the present application, the values ​​of each cargo classification label under all modules are summarized as follows:

[0101] Ln=Rescale(L1+L2+L3+L4+L5);

[0102] Among them, Ln represents the value and label of a specific cargo classification, L1 represents the number of cargo classification labels corresponding to the name of the point of interest, L2 represents the number of cargo classification labels corresponding to the industry classification information, L3 represents the number of cargo classification labels corresponding to the business scope, L4 represents the number of cargo classification labels corresponding to the company profile, L5 represents the number of cargo classification labels corresponding to the company's official website information, and Rescale represents the output value range control operator.

[0103] For example, the number of times the POI name of the goods classification label "sofa" corresponds to the goods classification label is 0.8, the number of times the industry classification information corresponds to the goods classification label is 0.6, the number of times the business scope corresponds to the goods classification label is 0.4, the number of times the company profile corresponds to the goods classification label is 0.2, and the number of times the company official website information corresponds to the goods classification label is 0.3. Then the sum of the goods classification label values ​​of "sofa" is 2.3.

[0104] S104 determines the cargo classification label of the point of interest according to the value of each cargo classification label and the source ratio of the cargo classification label.

[0105] In an optional embodiment, the product of the value sum of the goods classification label and the source proportion of the goods classification label is calculated. The source proportion of each goods classification label is:

[0106] LnR = n1 / n2;

[0107] Among them, LnR represents the source ratio of the cargo classification labels, n1 represents the number of source channels of the cargo classification labels, and n2 represents the number of source channels with cargo classification labels.

[0108] Furthermore, the products are sorted from large to small to obtain a preset number of cargo classification labels in the front, for example, three cargo classification labels with larger product values ​​are obtained.

[0109] Further, it is determined whether the source proportion of the front preset number of cargo classification labels is greater than a preset threshold, and the cargo classification labels greater than the preset threshold are used as the cargo classification labels of the points of interest.

[0110] In an exemplary embodiment, the three goods classification labels with larger product values ​​are "air conditioner", "television" and "tea table", and it is determined whether the source proportion of these three goods classification labels is greater than the preset threshold. For example, "tea table" is only obtained from the official website of the enterprise, and there are a total of five sources. The source proportion of "tea table" is only 1 / 5, which is less than the threshold of 3 / 5, so the goods classification label "tea table" is removed. The preset threshold can be set according to the actual situation.

[0111] In an optional embodiment, when the name information, business information and Internet information of the point of interest cannot be used to calculate the number of cargo labels. For example, the name information, business information and Internet information of the point of interest cannot match the cargo classification label, it also includes:

[0112] Obtain the vehicles and vehicle cargo classification labels that enter the point of interest to be divided within the preset time period; count the number of vehicles corresponding to each cargo classification label based on the vehicle cargo classification label; obtain the first two cargo classification labels with higher vehicle numbers; determine whether the number of vehicles corresponding to the first two cargo classification labels meets the preset proportion in the total number of vehicles with cargo classification labels. For example, the number of vehicles corresponding to the cargo classification must be greater than 1 / 3 of the total number of vehicles with cargo classification. If satisfied, use the first two cargo classification labels as the vehicle cargo classification labels entering the point of interest; if not satisfied, use the cargo classification label with the highest number of vehicles as the vehicle cargo classification label entering the point of interest; use the vehicle cargo classification label entering the point of interest as the cargo classification label of the point of interest.

[0113] In an optional embodiment, when the classification label of the vehicle and cargo entering the point of interest cannot be calculated, the method further includes:

[0114] Obtain the points of interest within the preset range of the points of interest to be divided and the cargo classification labels corresponding to the points of interest; count the number of points of interest corresponding to each cargo classification label according to the cargo classification labels corresponding to the points of interest within the preset range; obtain the first two cargo classification labels with the highest number of points of interest; determine whether the number of points of interest corresponding to the first two cargo classification labels meets the preset proportion in the total number of points of interest with cargo classification labels. For example, the number of points of interest corresponding to the cargo classification must be greater than 1 / 3 of the total number of points of interest with cargo classification. If satisfied, use the first two cargo classification labels as the cargo classification labels for nearby points of interest; if not satisfied, use the cargo classification label with the highest number of points of interest as the cargo classification label for nearby points of interest; use the cargo classification label of the nearby point of interest as the cargo classification label for the point of interest.

[0115] By analyzing the cargo classification labels of points of interest near the points of interest and the cargo classification labels of vehicles entering the points of interest, a cargo classification label reference can be given when the cargo classification label cannot be matched based on the name information of the point of interest to avoid missing cargo classification labels. The data structure of the freight industry is optimized, the dimensions of freight economic analysis are enriched, and the accuracy and coverage of cargo labels are improved.

[0116] Figure 2 Another method of dividing cargo classification labels is shown, such as Figure 2 As shown, including:

[0117] S201 obtains information of points of interest for which goods need to be classified;

[0118] S202 parses the cargo classification label according to the name of the point of interest;

[0119] S203 analyzes the goods classification label according to the industrial and commercial information; including analyzing the goods classification label according to the industrial and commercial industry information, business scope information, and enterprise profile information;

[0120] S204 parses the cargo classification label according to the official website information;

[0121] S205 analyzes cargo classification labels of nearby points of interest;

[0122] S206 Analyze cargo classification labels of vehicles entering the point of interest;

[0123] S207 Determination of cargo classification labels at points of interest. First, the cargo classification label values ​​and are calculated based on multiple dimensional data, and the cargo classification labels at the points of interest are determined based on the value sum of each cargo classification label and the source proportion of the cargo classification labels. Secondly, when the number of cargo labels cannot be calculated using the name information, industrial and commercial information, and Internet information multi-dimensional data of the point of interest, the cargo classification labels of the vehicles entering the point of interest can also be used as the cargo classification labels of the point of interest. When the cargo classification labels of the vehicles entering the point of interest cannot be calculated, the cargo classification labels of nearby points of interest can also be used as the cargo classification labels of the point of interest.

[0124] In an exemplary scenario, the execution process of this point of interest label division is explained according to the actual point of interest cargo classification label requirements.

[0125] 1. Enter the name of the POI tag to be obtained;

[0126] Zhongshan Changhong Electric Co., Ltd.

[0127] 2. Name and classification analysis: Zhongshan Changhong Electric Co., Ltd., remove invalid words Zhongshan and Co., Ltd., split keywords: Changhong and Electric. Match each keyword to the corresponding goods classification label:

[0128]

[0129] Name Goods Classification Label Result:

[0130] (1) Mechanical equipment, electrical appliances - power equipment, electrical machinery and equipment - household appliances: 0.5;

[0131] (2) Mechanical equipment, electrical appliances - power equipment, electrical machinery and equipment - other electrical equipment: 0.5;

[0132] 3. Analysis of commodity classification based on industrial and commercial information;

[0133] 3.1 Query the corresponding business information according to the name of the point of interest;

[0134] 3.2 Analyze the industry classification in the industrial and commercial information, and obtain the corresponding goods classification label according to the industry classification; examples of goods classification labels corresponding to industries:

[0135]

[0136] Industry cargo classification label results:

[0137] Zhongshan Changhong Electric Co., Ltd. - Manufacturing > Electrical machinery and equipment manufacturing > Household electrical appliances manufacturing (C385) - Mechanical equipment, electrical appliances - Power equipment, electrical machinery and equipment - Household appliances: 0.8;

[0138] 3.3 Analyze the business scope information in the industrial and commercial information, split the business scope by keywords, and match the goods classification label corresponding to the business scope; the example uses jieba word segmentation to extract keywords from the business scope.

[0139] Example: [Manufacture: air conditioners, refrigerators, heat pumps, water heaters, air conditioning fans, electric fans, humidifiers, electric heaters, clothes dryers, dehumidifiers, air purifiers, air water makers, electric fireplaces, kitchen appliances and utensils, refrigeration units and spare parts for the above products; engage in the import and export of the company's own products and raw and auxiliary materials, equipment and technology; engage in software development and consulting. (Projects that require approval according to the law can only be carried out after approval by relevant departments.) (Projects that require approval according to the law can only be carried out after approval by relevant departments)]

[0140] 3.3.1 Carry out data cleaning on invalid information in the business scope and remove descriptive information that is not related to the production of goods; the processing results are: [Production: air conditioners, refrigerators and freezers, heat pumps, water heaters, air conditioning fans, electric fans, humidifiers, electric heaters, dryers, dehumidifiers, air purifiers, air water machines, electric fireplaces, kitchen appliances and utensils, refrigeration units and spare parts for the above products].

[0141] 3.3.2 Use the word segmenter (the example uses the jieba word segmenter) to extract the top N cargo nouns from the cleaned business scope: water machine, air, dryer, kitchen appliances, heat pump, freezer, air conditioner, purifier, humidifier, fireplace, electric heater, electric fan, refrigeration, spare parts, water heater, freezing, appliances, refrigerator, unit, air conditioning.

[0142] 3.3.3 Match the extracted cargo keywords with their corresponding POI tag classifications and set their coefficients.

[0143]

[0144] 3.4 Analyze the enterprise profile information in the industrial and commercial information, extract keywords from the business goods content in the enterprise profile content, and match the keywords with the corresponding goods classification labels.

[0145] Sample data [...It is mainly a production and operation center integrating the research and development, production, processing and sales of air conditioners, small household appliances and other products. It has now become the export base of Changhong air conditioning products...].

[0146] 3.4.1 Carry out data cleaning on enterprise profile information;

[0147] Cleaning result: A production and operation center integrating R&D, production, processing and sales of air conditioners, small household appliances and other products.

[0148] 3.4.2 Extract the cleaned introduction data (the example uses the jieba word segmenter) to extract the topN of cargo nouns: air conditioner, small household appliances, products, production, processing, sales, integrated, production, operation, center.

[0149]

[0150] 4. Classification and analysis of goods from official website information;

[0151] According to the name of the point of interest, query its official website information on the Internet, extract its main business and production goods according to the content of the official website information, and match the corresponding goods classification labels of its goods. Use the word segmenter to extract the keyword results: air conditioner, Zhongshan City, 2020, Zhongshan, product, production, home use.

[0152]

[0153] 5: Classification and clustering analysis of goods at nearby points of interest;

[0154] Assume that the query points of interest and goods near the point of interest are classified as follows:

[0155]

[0156] The classification labels of nearby goods and the corresponding points of interest are as follows:

[0157] Mechanical equipment, electrical appliances - power equipment, electrical machinery and equipment - household appliances: 2;

[0158] Light industry, pharmaceutical products - daily industrial products - metal products: 1;

[0159] Other goods-other unclassified items: 1;

[0160] The results of the classification and clustering of goods at points of interest are: mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-household appliances.

[0161] 6. Points of interest enter vehicle and cargo classification clustering;

[0162] Assume that the vehicles and cargo entering the POI in the past month are classified as follows:

[0163]

[0164]

[0165] The cargo classification labels and corresponding vehicle numbers are as follows:

[0166] Mechanical equipment, electrical appliances - power equipment, electrical machinery and equipment - household appliances: 2;

[0167] Light industry, pharmaceutical products - daily industrial products - metal products: 2;

[0168] The results of the vehicle cargo classification clustering are: mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-household appliances; light industry, pharmaceutical products-daily industrial products-metal products.

[0169] 7. Comprehensive assessment of cargo classification;

[0170] Mechanical equipment, electrical appliances - power equipment, electrical machinery and equipment - household appliances;

[0171] Name of goods classification value (0.5) + industry of goods classification value (0.8) + business scope of goods classification value (1 / 16 / *0.3*13) + official website information classification value (0.4) + other sources of goods classification value (0) = 1.54*5 / 5 = 1.54.

[0172] Mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-other electrical appliances;

[0173] Name of goods classification value (0.5) + industry of goods classification value (0) + business scope of goods classification value (1 / 16 / *0.3*1) + official website information classification value (0) + other sources of goods classification value (0) = 0.518*1 / 5 = 0.1036;

[0174] Comprehensive evaluation results: The cargo classification results of Zhongshan Changhong Electric Co., Ltd. are: mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-household appliances.

[0175] If the company fails to obtain cargo classification through name, industrial and commercial information, and official website information, the cargo classification clustering results of nearby points of interest are obtained: mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-household appliances; if there is no clustering result for cargo classification of nearby points of interest, the cargo classification clustering results of entering the vehicle are used: mechanical equipment, electrical appliances-power equipment, electrical machinery and equipment-household appliances; light industry, pharmaceutical products-daily industrial products-metal products as the cargo classification label result of the point of interest.

[0176] If the above processes do not obtain the cargo classification and clustering results, there is no cargo classification result for this point of interest.

[0177] According to another aspect of the embodiment of the present application, a device for dividing the point of interest cargo classification labels for implementing the above-mentioned method for dividing the point of interest cargo classification labels is also provided. Figure 3 As shown, the device comprises:

[0178] An acquisition module 301 is used to acquire information of points of interest for the classification of goods to be classified;

[0179] A calculation module 302 is used to calculate the number of each cargo classification label in different dimensions based on the name information, business information and Internet information of the point of interest;

[0180] The statistical module 303 is used to classify and summarize the number of each cargo classification label under different dimensions to obtain the sum of the values ​​of each cargo classification label;

[0181] The determination module 304 is used to determine the cargo classification label of the point of interest according to the value of each cargo classification label and the source ratio of the cargo classification label.

[0182] It should be noted that the device for dividing the classification labels of goods at points of interest provided in the above-mentioned embodiment only uses the division of the above-mentioned functional modules as an example when executing the method for dividing the classification labels of goods at points of interest. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for dividing the classification labels of goods at points of interest provided in the above-mentioned embodiment and the method for dividing the classification labels of goods at points of interest belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0183] According to another aspect of the embodiments of the present application, an electronic device corresponding to the method for dividing the classification labels of goods at points of interest provided in the above embodiments is also provided to execute the above method for dividing the classification labels of goods at points of interest.

[0184] Please refer to Figure 4 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 4 As shown, the electronic device includes: a processor 400, a memory 401, a bus 402 and a communication interface 403, and the processor 400, the communication interface 403 and the memory 401 are connected via the bus 402; the memory 401 stores a computer program that can be run on the processor 400, and when the processor 400 runs the computer program, it executes the method for dividing the point of interest cargo classification labels provided in any of the aforementioned embodiments of the present application.

[0185] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0186] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 401 is used to store programs, and the processor 400 executes the program after receiving the execution instruction. The method for dividing the classification labels of goods at the point of interest disclosed in any implementation of the embodiment of the present application may be applied to the processor 400, or implemented by the processor 400.

[0187] The processor 400 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 400. The above processor 400 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.

[0188] The electronic device provided in the embodiment of the present application and the method for dividing the POI cargo classification labels provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0189] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium corresponding to the method for dividing the classification labels of goods at points of interest provided in the aforementioned embodiments, on which a computer program (i.e., a program product) is stored. When the computer program is executed by a processor, it will execute the method for dividing the classification labels of goods at points of interest provided in any of the aforementioned embodiments.

[0190] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0191] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for dividing the classification labels of goods at points of interest provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0192] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0193] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for dividing the classification labels of goods at points of interest, characterized in that: include: Obtain information on points of interest for the classification of goods to be classified; Based on the name information, business information and Internet information of the point of interest, the number of times each cargo classification label is obtained in different dimensions is calculated respectively; Classify and summarize the times of each cargo classification label under the different dimensions to obtain the sum of the values ​​of each cargo classification label; The cargo classification label of the point of interest is determined according to the value of each cargo classification label and the source ratio of the cargo classification label.

2. The method according to claim 1, characterized in that: Based on the name information of the point of interest, the number of times each cargo classification label corresponds to the name of the point of interest is calculated, including: Segment the names of points of interest and extract keywords; Matching corresponding cargo classification labels based on the keywords; The ratio of 1 to the number of keywords with cargo classification tags in the name is calculated, and the number of times each cargo classification tag corresponds to the name of the point of interest is obtained based on the product of the ratio and the preset weight coefficient.

3. The method according to claim 1, characterized in that Based on the business information of the point of interest, the number of times each cargo classification label corresponds to the business information is calculated, including: Analyze the industry classification information, business scope information, and company profile information in the industrial and commercial information; Extract keywords from the industry classification information, business scope information, and company profile information respectively, and match them with corresponding goods classification labels; Calculate the product of 1 and the preset weight coefficient to get the number of cargo classification labels corresponding to the industry; Calculate the ratio of 1 to the number of keywords with goods classification tags in the business scope information, and obtain the number of each goods classification tag corresponding to the business scope based on the product of the ratio and the preset weight coefficient; The ratio of 1 to the number of keywords with goods classification tags in the company profile information is calculated, and the number of times each goods classification tag corresponds to the company profile is obtained based on the product of the ratio and the preset weight coefficient.

4. The method according to claim 1, characterized in that: Based on the Internet information of the point of interest, the number of times each cargo classification label corresponds to the company's official website information is calculated, including: Search the official website of the company on the Internet according to the name of the point of interest; Extract keywords of the goods that the enterprise operates and produces based on the information on the enterprise's official website; Match the corresponding cargo classification labels according to the keywords; The ratio of 1 to the number of keywords with cargo classification tags in the enterprise's official website information is calculated, and the number of times each cargo classification tag corresponds to the enterprise's official website information is obtained based on the product of the ratio and the preset weight coefficient.

5. The method according to claim 1, characterized in that According to the value of each cargo classification label and the source ratio of the cargo classification label, the cargo classification label of the point of interest is determined, including: Calculate the product of the value of the cargo classification label and the source ratio of the cargo classification label; Sort the products from large to small to obtain a preset number of cargo classification labels in the front; It is determined whether the source proportion of the front preset number of cargo classification labels is greater than a preset threshold, and the cargo classification labels greater than the preset threshold are used as the cargo classification labels of the points of interest.

6. The method according to claim 1, characterized in that When the number of cargo labels cannot be calculated using the name information, business information, and Internet information of the point of interest, it also includes: Obtain the vehicle and vehicle cargo classification labels that enter the POI to be divided within a preset time period; According to the vehicle cargo classification labels, count the number of vehicles corresponding to each cargo classification label; Get the top two cargo classification labels with higher vehicle counts; Determine whether the number of vehicles corresponding to the first two cargo classification labels meets the preset proportion of the total number of vehicles with cargo classification labels; If satisfied, the first two cargo classification labels are used as the cargo classification labels of the vehicle entering the point of interest; If not, the cargo classification label with the highest number of vehicles is used as the cargo classification label of the vehicles entering the point of interest; The cargo classification label of the vehicle entering the point of interest is used as the cargo classification label of the point of interest.

7. The method according to claim 6, characterized in that When the cargo classification label of the vehicle entering the POI cannot be calculated, it also includes: Obtaining points of interest within a preset range of points of interest to be divided and cargo classification labels corresponding to the points of interest; According to the cargo classification labels corresponding to the points of interest within the preset range, the number of points of interest corresponding to each cargo classification label is counted; Get the first two cargo classification labels with the highest number of points of interest; Determine whether the number of points of interest corresponding to the first two cargo classification labels satisfies a preset proportion of the total number of points of interest with cargo classification labels; If satisfied, the first two cargo classification labels are used as cargo classification labels for nearby points of interest; If not, the cargo classification label with the highest number of points of interest is used as the cargo classification label of the nearby points of interest; The cargo classification labels of the nearby points of interest are used as the cargo classification labels of the point of interest.

8. A device for dividing cargo classification labels at points of interest, characterized in that: include: An acquisition module is used to obtain information of points of interest for the classification of goods to be classified; A calculation module, used to calculate the number of each cargo classification label in different dimensions based on the name information, business information and Internet information multi-dimensional data of the point of interest; A statistical module, used to classify and summarize the number of each cargo classification label under the different dimensions to obtain the sum of the values ​​of each cargo classification label; The determination module is used to determine the cargo classification label of the point of interest according to the value of each cargo classification label and the source ratio of the cargo classification label.

9. An electronic device, characterized in that: The invention comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the method for dividing the point of interest cargo classification labels as claimed in any one of claims 1 to 7 when executing the program instructions.

10. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a method for dividing point-of-interest cargo classification labels as described in any one of claims 1 to 7.

Images