Vehicle and cargo market label matching method and device, equipment and storage medium

Abstract

The invention discloses a vehicle and cargo market label matching method and device, equipment and a storage medium, and the method comprises the steps: adding a subdivided market label for an electronic fence, determining a suspected loading and unloading place based on vehicle parking data, and searching for the electronic fence corresponding to the suspected loading and unloading place; according to the subdivided market labels of the corresponding electronic fences and the upstream and downstream directions of the suspected loading and unloading places; counting the total number of each subdivision market label, the total number of forward subdivision market labels, the total number of reverse subdivision market labels, the total number of forward parking, the total number of reverse parking, the total number of unjudged flow parking, the total number of suspected loading places and the total number of parking with subdivision market labels of the suspected loading places within a period of time; and inputting the statistical data into the comprehensive evaluation model, and outputting a subdivided market label matched with the vehicle. Based on the subdivided market type to which the historical parking position of the vehicle belongs, the market information to which the vehicle transported goods belong is deduced in combination with the upstream and downstream relationship of the market, and the dependence on the historical waybill information of the vehicle is reduced.

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 matching vehicle and cargo market labels. Background Art

[0002] With the development of society and the advancement of technology, the transportation industry is developing day by day, and freight transportation is growing rapidly. In the actual transportation process, due to the diversity of cargo types and vehicle types, it is impossible to obtain market segment information of the cargo that vehicles often transport in most scenarios. This leads to low accuracy in matching freight market cargo transportation, and even difficulty in matching suitable vehicles for freight market cargo transportation.

[0003] In order to achieve accurate matching of vehicle and cargo transportation, existing technical solutions mainly analyze the cargo information transported by the vehicle through waybills. It is impossible to perform corresponding analysis on vehicles without waybill information; or only vehicles that have long-term cooperation with specific factories to transport goods can know the market segmentation of the vehicle. It has certain limitations and cannot perform an overall analysis of the entire cargo vehicle.

[0004] In addition, in areas such as commercial vehicle market forecasting and freight finance, there is a lack of more refined classification of vehicle market segments for data analysis and research applications. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and storage medium for matching vehicle and cargo market labels, so as to at least solve the technical problem in the related art that it is difficult to accurately match vehicles with market segments in the absence of waybill information.

[0006] According to one aspect of an embodiment of the present application, the present application provides a method for matching a vehicle with a cargo market tag, comprising:

[0007] Obtaining an electronic fence, and adding a market segment tag to the electronic fence;

[0008] Determine a suspected loading and unloading location based on the vehicle parking data, and search for an electronic fence corresponding to the suspected loading and unloading location;

[0009] According to the market segment labels of the electronic fence corresponding to the suspected loading and unloading place, and the upstream and downstream directions of the suspected loading and unloading place, the total number of market segment labels corresponding to the vehicles at the suspected loading place within a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels are counted;

[0010] The total number of market segment labels corresponding to vehicles at suspected loading locations within the preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels are input into a preset comprehensive evaluation model to output the market segment labels matching the vehicles.

[0011] In one embodiment, before obtaining the electronic fence, the method further includes:

[0012] Based on the existing electronic fence data and vehicle parking data, the parking data outside the electronic fence is obtained;

[0013] Aggregating the parking data outside the electronic fence to generate an incremental electronic fence;

[0014] Determine the name of the incremental electronic fence according to the information of the point of interest closest to the longitude and latitude of the center of the incremental electronic fence;

[0015] The incremental geo-fence is added to the existing geo-fence set.

[0016] In one embodiment, adding a market segment tag to the electronic fence includes:

[0017] According to the name keyword of the electronic fence, a corresponding market segment label is matched to obtain a market segment label result corresponding to the name;

[0018] Acquire the business information corresponding to the name of the electronic fence, and parse the business information to obtain a market segment label result corresponding to the business information;

[0019] The market segment label of the electronic fence is obtained according to the market segment label result corresponding to the name and the market segment label result corresponding to the industrial and commercial information.

[0020] In one embodiment, determining a suspected loading and unloading location based on vehicle stop data includes:

[0021] Based on the vehicle stop data and point of interest information, the stop points for non-freight scenarios are obtained;

[0022] Deleting the stop point of the non-freight scenario to obtain the suspected loading location;

[0023] The next stop of the suspected loading place is used as the suspected unloading place.

[0024] In one embodiment, before counting the total number of market segment labels corresponding to vehicles at the suspected loading place within a preset time period based on the market segment labels of the electronic fence corresponding to the suspected loading and unloading place and the upstream and downstream directions of the suspected loading and unloading place, the method further includes:

[0025] Determine the upstream and downstream directions of the suspected loading and unloading location based on the market segment tags of the electronic fences corresponding to the suspected loading and unloading location;

[0026] Based on the upstream and downstream directions of the suspected loading and unloading locations and the corresponding market segment labels, the number of each market segment label corresponding to each suspected loading location is calculated.

[0027] In one embodiment, the number of market segment tags corresponding to each electronic fence of each suspected loading location is calculated according to the following formula:

[0028] Y=1 / s / n*a

[0029] Among them, Y represents the number of market segment labels corresponding to a single electronic fence of the suspected loading place, a represents the preset weight coefficient, the weight coefficient when the suspected loading and unloading place is in the positive direction of upstream and downstream is greater than the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction, and the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction is greater than the weight coefficient when the suspected loading and unloading place is in the reverse direction of upstream and downstream; when it is in the positive direction, s represents the number of electronic fences corresponding to the positive market segment label, n represents the number of different positive labels in the electronic fence where the positive market segment label is located, when it is in the reverse direction or the flow direction cannot be determined, s represents the number of electronic fences corresponding to the loading place, and n represents the number of different market segment labels of each fence of the loading place;

[0030] The number of labels of each market segment corresponding to all electronic fences of the suspected loading location is summed up to obtain the number of labels of each market segment corresponding to each suspected loading location.

[0031] In one embodiment, before calculating the number of tags of each market segment of a single electronic fence corresponding to each suspected loading location, the method further includes:

[0032] Determine the priority according to the upstream and downstream relationship of the suspected loading and unloading place; the priority of the suspected loading and unloading place in the positive upstream and downstream direction is higher than the priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined; the priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined is higher than the priority of the suspected loading and unloading place in the reverse upstream and downstream direction;

[0033] In the case where the upstream and downstream relationships of the suspected loading and unloading places include multiple types, only the number of labels of each market segment corresponding to the case with the highest priority is calculated.

[0034] In one embodiment, the total number of market segment labels, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels corresponding to vehicles at suspected loading places within a preset time period are counted, including:

[0035] Sum up the number of labels of each market segment corresponding to the suspected loading place within the preset time period to obtain the total number of labels of each market segment;

[0036] Sum the number of positive market segment labels corresponding to all electronic fences at the loading places in the suspected loading and unloading places in the upstream and downstream directions, and obtain the total number of positive market segment labels;

[0037] Sum the number of reverse market segment labels corresponding to all electronic fences at the loading places in the upstream and downstream suspected loading and unloading places, and obtain the total number of labels for each reverse market segment;

[0038] Sum the number of suspected loading places in the upstream and downstream directions to get the total number of forward stops;

[0039] Sum the number of suspected loading places in the upstream and downstream directions to get the total number of reverse stops;

[0040] The number of suspected loading places whose upstream and downstream flow directions cannot be determined is summed to obtain the total number of stops whose flow directions cannot be determined;

[0041] Sum the number of all suspected loading locations to get the total number of suspected loading locations;

[0042] Sum the number of loading points with market segment labels to get the total number of stops with market segment labels.

[0043] In one embodiment, the total number of market segment labels, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels corresponding to vehicles at suspected loading places within the preset time period are input into a preset comprehensive evaluation model, and the market segment labels matched by the vehicles are output, including:

[0044] The comprehensive evaluation model is used to determine whether the ratio of the total number of stops with market segment labels to the total number of suspected loading locations is greater than a first threshold;

[0045] If it is greater than the first threshold, determine whether the total number of positive stops meets the preset proportion of the total number of stops with market segment labels. If so, obtain the top three in the ranking of the total number of positive market segment labels, and respectively determine whether the total number of the top three positive market segment labels meets the preset proportion of the total number of positive stops. The market segment labels that meet the preset proportion of the total number of positive market segment labels in the total number of positive stops among the top three are used as the market segment labels matched by the vehicle. If none of the top three meet the requirements, take the market segment label with the highest total number of positive market segment labels as the market segment label matched by the vehicle.

[0046] If the total number of forward stops does not meet the preset proportion of the total number of stops with market segment labels, determine whether the total number of reverse stops meets the preset proportion of the total number of stops with market segment labels, and the total number of reverse stops is greater than 2 times the total number of forward stops, and the total number of reverse stops is greater than 2 times the total number of stops that cannot determine the flow direction; if so, obtain the top three reverse market segment label totals, and determine whether the top three reverse market segment label totals meet the preset proportion of the reverse market segment totals, and use the top three reverse market segment label that meets the preset proportion of the reverse market segment label totals as the vehicle matching market segment label; if none of the top three meet, use the market segment label with the highest reverse market segment label totals as the vehicle matching market segment label;

[0047] If the total number of reverse stops does not meet the preset proportion of the total number of stops with segmented market labels, and the total number of reverse stops is greater than twice the total number of forward stops, and the total number of reverse stops is greater than twice the total number of stops where the flow direction cannot be determined, then obtain the top three total number of segmented market labels corresponding to the vehicle, and determine whether the total number of the first three segmented market labels meets the preset proportion in the total number of stops with segmented market labels. The segmented market labels that meet the preset proportion in the total number of stops with segmented market labels among the first three are used as the segmented market labels matching the vehicle. If none of the first three meet the requirements, take the segmented market label with the highest total number of segmented market labels as the segmented market label matching the vehicle.

[0048] According to another aspect of an embodiment of the present application, a device for matching a vehicle with a cargo market tag is provided, comprising:

[0049] A construction module is used to obtain an electronic fence and add a market segment tag to the electronic fence;

[0050] An analysis module, used to determine a suspected loading and unloading location based on the vehicle stop data, and to find an electronic fence corresponding to the suspected loading and unloading location;

[0051] A statistics module is used to count the total number of market segment labels corresponding to vehicles in the suspected loading place in a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels, according to the market segment labels of the electronic fence corresponding to the suspected loading place and the upstream and downstream directions of the suspected loading and unloading place;

[0052] The comprehensive evaluation module is used to input the total number of market segment labels corresponding to vehicles at suspected loading locations within the preset time period, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels into a preset comprehensive evaluation model, and output the market segment labels matching the vehicles.

[0053] 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 above-mentioned method for matching vehicle and cargo market tags through the computer program.

[0054] According to another aspect of the embodiment 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 matching vehicle and cargo market tags when running.

[0055] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0056] The method for matching vehicle and cargo market labels provided in this application uses the market segment labels added by the electronic fence, the fence data where the vehicle has stopped, and the upstream and downstream relationships in the industry to construct a detailed classification label list of the market segment to which the vehicle has stopped. By summarizing the market segment classification labels, the frequency share of each market segment within the vehicle cycle can be analyzed. In the case of large amounts of data, the market segment classification that meets a certain threshold can be regarded as the market segment to which the vehicle belongs, as the market segment label for the vehicle within a specific time period. This method can infer the market segment to which the vehicle's transported goods belongs without relying on the actual waybill information of the vehicle's transported goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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:

[0058] Figure 1 is a flow chart of an optional method for matching vehicle and cargo market tags according to an embodiment of the present application;

[0059] Figure 2 is a schematic diagram of an optional incremental electronic fence acquisition method according to an embodiment of the present application;

[0060] Figure 3 is a schematic diagram of an optional method for constructing electronic fence market segment labels according to an embodiment of the present application;

[0061] Figure 4 is a flow chart of an optional method for matching vehicle and cargo market tags according to an embodiment of the present application;

[0062] Figure 5 is a schematic diagram of an optional vehicle market segmentation application prospect according to an embodiment of the present application;

[0063] Figure 6 is a schematic diagram of an optional matching device for a vehicle and a cargo market tag according to an embodiment of the present application;

[0064] Figure 7 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0065] 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.

[0066] 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.

[0067] This application aims to analyze the vehicle parking data, use the electronic fence to which the vehicle is parked, and analyze the market segment label of the goods transported by the vehicle according to the market segment type label (including but not limited to national cargo classification, national industry classification, etc.) to which the electronic fence belongs. By summarizing and counting all the fence information that the vehicle has effectively parked within a certain time range according to the market segment classification, the frequency and proportion of the market segment label of the vehicle in the cycle are obtained, and the data that meets the requirements is extracted as the vehicle's market segment label according to the actual use needs. Analyze the vehicle's own market segment range and provide it to the logistics platform for multi-scenario application. The current capacity push, vehicle-cargo matching, etc. can only be pushed based on the static data of the vehicle, covering a wide range of vehicles, and cannot achieve refined push based on the characteristics of the vehicle's own transportation of goods. It may push a food freight information to a vehicle that often pulls coal. After this application constructs a market segment label for the vehicle, it can achieve the push of cargo information related to the historical vehicle's transportation of goods, achieve the purpose of accurate push, optimize the matching degree of vehicles and goods, and improve the vehicle and freight information achievement rate, so that cargo owners spend less time looking for vehicles and car owners spend less time looking for goods.

[0068] The following is combined with Figure 1-5 , the method for matching the vehicle and cargo market labels in the embodiment of the present application is introduced in detail, such as Figure 1 As shown, the method mainly includes the following steps:

[0069] S101 obtains the electronic fence and adds a market segment tag to the electronic fence.

[0070] In an optional embodiment, before obtaining the real electronic fence data of the existing freight yard of the project, it also includes constructing an incremental electronic fence.

[0071] Specifically, based on the existing electronic fence data and vehicle parking data, the parking data outside the electronic fence is obtained. According to the parking point data, the electronic fence to which the parking point belongs is calculated, and the parking data within the existing electronic fence is filtered out. The remaining parking data is the parking data outside the fence. The parking data outside the electronic fence is aggregated to generate an incremental electronic fence. According to the information of the point of interest closest to the longitude and latitude of the center of the incremental electronic fence, the name of the incremental electronic fence is determined, and the incremental electronic fence is added to the existing electronic fence set.

[0072] In one embodiment, the H3 algorithm is used to calculate the H3 index of each stop, and then the number of parked vehicles and the number of stops are summarized and counted according to the H3 index. The H3 index exceeding a certain threshold is defined as a new electronic fence, and the name of the point of interest closest to the center longitude and latitude of the fence is searched as the fence name, and then the electronic fence is added to the existing electronic fence data.

[0073] Figure 2 FIG. 1 is a schematic diagram of an optional incremental electronic fence acquisition method according to an embodiment of the present application. Figure 2 As shown, the parking data of the vehicle is obtained, the electronic fence to which the parking point belongs is determined based on the point-surface relationship, the parking data within the existing electronic fence is filtered out, and the parking data outside the electronic fence is obtained. According to the parking data of non-public places outside the fence, a new electronic fence is generated. For example, the parking data of public places such as gas stations and service areas are removed to generate an electronic fence related to freight. The newly added electronic fence is added to the fence table.

[0074] By generating incremental electronic fences, existing electronic fence data can be expanded and the coverage of electronic fences to vehicle freight sites can be increased.

[0075] Furthermore, a market segment tag is added to the electronic fence. In an optional embodiment, adding a market segment tag to the electronic fence includes: matching the corresponding market segment tag according to the name keyword of the electronic fence to obtain the market segment tag result corresponding to the name; obtaining the business information corresponding to the name of the electronic fence, parsing the business information to obtain the market segment tag result corresponding to the business information; obtaining the market segment tag of the electronic fence according to the market segment tag result corresponding to the name and the market segment tag result corresponding to the business information.

[0076] Figure 3 FIG. 1 is a schematic diagram of an optional method for constructing electronic fence market segment labels according to an embodiment of the present application. Figure 3 As shown, the market segmentation labels are constructed based on the fence name, the market segmentation labels are constructed based on the industrial and commercial industry information, the market segmentation labels are constructed based on the industrial and commercial business scope information, and the market segmentation labels are constructed based on the industrial and commercial enterprise profile information.

[0077] In one embodiment, the fence name is split by keywords, and the corresponding market segment labels are matched according to the keywords to obtain the market segment label results corresponding to the name. For example, if the fence name is Furniture City, the market segment label can be "furniture". Search the industrial and commercial information corresponding to the fence name, parse the industrial and commercial industry information to obtain the corresponding market segment label, parse the industrial and commercial business scope information to obtain the corresponding market segment label, parse the industrial and commercial enterprise profile information to obtain the corresponding market segment label, and determine the final market segment label result of the fence based on the name and the market segment label of the industrial and commercial information. For example, if the information corresponding to the fence is "Shanxi Coal Making Plant", the market segment label can be "coal".

[0078] S102 determines a suspected loading and unloading location based on the vehicle parking data, and searches for an electronic fence corresponding to the suspected loading and unloading location.

[0079] In an optional embodiment, determining a suspected loading and unloading location based on vehicle stop data includes: obtaining a stop point of a non-freight scenario based on the vehicle stop data and information about points of interest, deleting the stop point of the non-freight scenario, and obtaining a suspected loading location. Using the next stop point of the suspected loading location as the suspected unloading location.

[0080] Specifically, the stop data that meets certain conditions is filtered out, such as the stop duration exceeding a certain threshold. According to the point of interest information of the stop points, the stop points for non-freight scenarios are removed, such as gas stations, service areas, repair shops, etc., and the valid stop data is retained as the suspected loading location data of the vehicle.

[0081] In an embodiment of the present application, the suspected loading and unloading places include loading places and unloading places, which are grouped according to the unique vehicle code. According to the stop time of the vehicle, the stops of the suspected loading and unloading places are sorted in chronological order from front to back, and the current stop is used as the suspected loading place, and the next stop of the current stop is used as the suspected unloading place.

[0082] For example, the valid stops include s1, s2, s3, s4, s5, and s6. Then s1, s2, s3, s4, s5, and s6 are all loading places, s2 is the unloading place of s1, and s3 is the unloading place of s2.

[0083] The electronic fence to which the stop point belongs is obtained through the point-to-surface calculation formula. If the suspected loading and unloading site is covered by both the real fence (actual fence data) and the incremental electronic fence, the market segment label of the real fence is used as the attached information of the loading and unloading site.

[0084] S103 counts the total number of market segment labels corresponding to vehicles at the suspected loading place within a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops where the flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels based on the market segment labels of the electronic fence corresponding to the suspected loading and unloading place, and the upstream and downstream directions of the suspected loading and unloading place.

[0085] In one embodiment, the upstream and downstream directions of the suspected loading and unloading location are determined according to the market segment tags of the electronic fences corresponding to the suspected loading and unloading locations.

[0086] For example, if the label of the electronic fence at the loading site is a mixing plant, and the label of the electronic fence at the unloading site is a construction site, the loading site and the unloading site are in the positive upstream and downstream directions. If the label of the electronic fence at the loading site is a mixing plant, and the label of the electronic fence at the unloading site is a gravel plant, then the loading site and the unloading site are in the reverse upstream and downstream directions.

[0087] Furthermore, based on the upstream and downstream directions of the suspected loading and unloading locations and the corresponding market segment labels, the number of each market segment label corresponding to each suspected loading location is calculated.

[0088] Specifically, in a loading and unloading stop, a stop may correspond to multiple electronic fences or multiple market segment tags. However, in theory, there should be only one market segment tag for a loading and unloading stop. Therefore, if there are multiple market segment tags, the sum of the number of multiple market segment tags is 1. In a suspected loading and unloading stop, the number of each market segment tag corresponding to a single electronic fence at each suspected loading place is calculated according to the following formula:

[0089] Y = 1 / s / n*a;

[0090] Among them, Y represents the number of market segment labels corresponding to a single electronic fence of the suspected loading place, a represents the preset weight coefficient, the weight coefficient when the suspected loading and unloading place is in the positive upstream and downstream direction is greater than the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction, the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction is greater than the weight coefficient when the suspected loading and unloading place is in the reverse upstream and downstream; when it is in the positive direction, s represents the number of electronic fences corresponding to the positive market segment label, n represents the number of different positive labels in the electronic fence where the positive market segment label is located, when it is in the reverse direction or the flow direction cannot be determined, s represents the number of electronic fences corresponding to the loading place, and n represents the number of different market segment labels in each fence of the loading place.

[0091] The number of labels of each market segment corresponding to all electronic fences of the suspected loading location is summed up to obtain the number of labels of each market segment corresponding to each suspected loading location.

[0092] In an exemplary scenario, the loading and unloading stops are as follows: s1[f1:l1;l2]-s2[f2:l3,f3:l4].

[0093] Among them, s1 represents the loading point, s2 represents the unloading point; f1 represents the fence to which the stop point s1 belongs, l1 represents the market segment label 1 of fence f1, l2 represents the market segment label 2 of fence f1; f2 represents the fence 1 to which the stop point s2 belongs, l3 represents the market segment label of fence f2; f3 represents the fence 2 to which the stop point s2 belongs, and l4 represents the market segment label of fence f3.

[0094] The upstream and downstream data examples are shown in the following table:

[0095]

[0096] The priority is determined according to the upstream and downstream relationship of the suspected loading and unloading place. The priority of the suspected loading and unloading place in the positive upstream and downstream direction is higher than the priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined. The priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined is higher than the priority of the suspected loading and unloading place in the reverse upstream and downstream direction. When there are multiple upstream and downstream relationships of the suspected loading and unloading place, only the number of labels of each market segment corresponding to the case with the highest priority is calculated.

[0097] If there is a positive upstream and downstream relationship between the loading and unloading market segment labels, for example, l1 is a mixing plant, l3 is a construction site, and l4 is a sand and gravel plant, l1 and l3 are positive upstream and downstream, l1 and l4 are reverse upstream and downstream, and the upstream and downstream relationship of other market segment labels is unknown, then the number of market segment labels corresponding to the loading and unloading places is as follows:

[0098] s1[l1]-s2[l3];

[0099] Segmented market label: Mixing station = 1 (number of stops) / 1 (number of loading place forward label fences) / 1 (number of different forward labels in the fence where the loading place forward label is located) * 0.8, where 0.8 is the preset weight coefficient. Assuming that l2 is also a mixing station, and the two labels in f1 are the same, the number of different forward labels in the fence where the loading place forward label is located should be 1. If the loading place stop and the unloading place stop segmented market label cannot determine the upstream and downstream relationship, for example, l1 is steel, l2 is furniture, l3 is a mixing station, and l4 is wood, the upstream and downstream relationships between l1 and l3, l1 and l4, and l2 and l3 are unknown, and l2 and l4 are upstream and downstream reverse relationships, then the number of segmented market labels corresponding to the loading and unloading places is as follows:

[0100] s1[l1]-s2[l3\l4];

[0101] Market segment label: Steel = 1 (number of stops) / 1 (number of fences corresponding to the loading place stop) / 2 (number of different market segment labels within the loading place stop fence) * 0.5, where 0.5 is the preset weight coefficient.

[0102] If the loading and unloading market segment labels only have an upstream and downstream reverse relationship, for example, l1 is furniture, l2 is doors and windows, l3 is veneer, and l4 is artificial board, and l1 and l3, l1 and l4, l2 and l3, and l2 and l4 are all upstream and downstream reverse, then the number of market segment labels corresponding to the loading and unloading places is as follows:

[0103] s1[l1,l2]-s2[l3\l4];

[0104] Segment market label: Furniture = 1 (number of stops) / 1 (number of fences corresponding to the stops) / 2 (number of different segment market labels within the fence) * 0.2, where 0.2 is the preset weight coefficient.

[0105] Market segment label: Doors and windows = 1 (number of stops) / 1 (number of fences corresponding to the stops) / 2 (number of different market segment labels within the fence) * 0.2, where 0.2 is the preset weight coefficient.

[0106] Furthermore, the total number of market segment labels corresponding to vehicles at suspected loading locations within a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels are counted.

[0107] The numbers of labels of each market segment corresponding to the suspected loading places within the preset time period are summed up respectively to obtain the total number of labels of each market segment; the numbers of forward market segment labels corresponding to all electronic fences of the loading places in the suspected loading and unloading places in the forward direction of the upstream and downstream are summed up respectively to obtain the total number of forward market segment labels; the numbers of reverse market segment labels corresponding to all electronic fences of the loading places in the suspected loading and unloading places in the reverse direction of the upstream and downstream are summed up respectively to obtain the total number of reverse market segment labels; the numbers of suspected loading places in the forward direction of the upstream and downstream are summed up to obtain the total number of forward stops; the numbers of suspected loading places in the reverse direction of the upstream and downstream are summed up to obtain the total number of reverse stops; the numbers of suspected loading places whose upstream and downstream flow directions cannot be determined are summed up to obtain the total number of stops whose flow directions cannot be determined; the numbers of all suspected loading places are summed up to obtain the total number of suspected loading places; the numbers of loading places with market segment labels are summed up to obtain the total number of stops with market segment labels.

[0108] For example, the data within a preset month is summarized to obtain the frequency share of each market segment for the vehicle within that month.

[0109] S104 inputs the total number of market segment labels corresponding to vehicles at suspected loading locations within a preset time period, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels into a preset comprehensive evaluation model, and outputs the market segment labels matching the vehicles.

[0110] In an optional embodiment, the comprehensive evaluation model is used to determine whether the ratio of the total number of stops with market segment labels to the total number of suspected loading places is greater than a first threshold. If it is less than the first threshold, it is considered that the market segment labels do not cover the vehicle stops sufficiently, and priority is given to specifying its market segment through vehicle static data. The specific value of the first threshold can be set according to actual conditions. For example, the first threshold is 60%.

[0111] If it is greater than the first threshold, determine whether the total number of positive stops meets the preset proportion of the total number of stops with market segment labels. If so, obtain the top three total numbers of positive market segment labels, and determine whether the total numbers of the top three positive market segment labels meet the preset proportion of the total number of positive stops. The market segment labels that meet the preset proportion of the total number of positive market segment labels in the total number of positive stops among the top three are used as the market segment labels matched by the vehicle. If none of the top three meet the requirements, take the market segment label with the highest total number of positive market segment labels as the market segment label matched by the vehicle.

[0112] For example, if the total number of forward stops is greater than the total number of stops with market segment labels / 3, the top 3 forward label times are used, and the top three must satisfy the total number of forward labels in the market segment / the total number of forward stops>30%. If none of them meet the requirement, the market segment label with the highest total number of forward labels is used as the market segment label matched by the vehicle. The specific values ​​can be set by technicians in this field.

[0113] Assume that the summary results of car A are as follows: total number of positive stops = 11, total number of stops with market segmentation labels = 30, total number of steel positive labels = 4, total number of coal positive labels = 4, total number of wood positive labels = 2, total number of light industry positive labels = 1; then the final market segmentation labels of car A are steel and coal.

[0114] Assume that the summary results of car A are as follows: total number of positive stops = 11, total number of stops with market segment labels = 30, total number of steel positive labels = 5, total number of coal positive labels = 3, total number of wood positive labels = 2, total number of light industry positive labels = 1; then the final market segment label of car A is steel.

[0115] If the total number of forward stops does not meet the preset proportion of the total number of stops with segmented market labels, determine whether the total number of reverse stops meets the preset proportion of the total number of stops with segmented market labels, and the total number of reverse stops is greater than 2 times the total number of forward stops, and the total number of reverse stops is greater than 2 times the total number of stops that cannot determine the flow direction; if the conditions are met, obtain the top three total number of reverse segmented market labels, and determine whether the total number of the top three reverse segmented market labels meets the preset proportion in the total number of reverse stops, and use the segmented market labels that meet the preset proportion of the total number of reverse segment labels in the total number of reverse stops as the segmented market labels matched by the vehicle; if none of the top three meet the conditions, use the segmented market label with the highest total number of reverse segment labels as the segmented market label matched by the vehicle.

[0116] If the total number of reverse stops > the total number of stops with segment labels / 2, the total number of reverse stops > the total number of forward stops * 2, and the total number of reverse stops > the total number of stops where the flow direction cannot be determined * 2, then the top 3 reverse segment label times are used, and the number of stops for the segment label / the reverse number > 30% must be met. If none of them are met, the segment label with the highest total number of reverse labels is taken as the segment label matching the vehicle.

[0117] Assume that the summary results of car A are as follows: total forward stops = 5, total reverse stops = 20, total stops where the flow direction cannot be determined = 5, number of stops with segmented market labels = 30, number of reverse labels for steel = 12, number of reverse labels for coal = 7, number of reverse labels for wood = 1; then the final segmented market labels for car A are steel and coal.

[0118] If the total number of reverse stops does not meet the preset proportion of the total number of stops with segmented market labels, and the total number of reverse stops is greater than twice the total number of forward stops, and the total number of reverse stops is greater than twice the total number of stops where the flow direction cannot be determined, then obtain the top three total number of segmented market labels corresponding to the vehicle, and determine whether the total number of the first three segmented market labels meets the preset proportion in the total number of stops with segmented market labels. The segmented market labels that meet the preset proportion in the total number of stops with segmented market labels among the first three are used as the segmented market labels matching the vehicle. If none of the first three meet the requirements, take the segmented market label with the highest total number of segmented market labels as the segmented market label matching the vehicle.

[0119] Assume that the summary results of car A are as follows: total number of forward stops = 3, total number of reverse stops = 3, total number of stops where the flow direction cannot be determined = 5, total number of stops with market segment labels = 11, total number of steel market segment labels = 4, total number of coal market segment labels = 3, total number of wood market segment labels = 4; then the final market segment labels of car A are steel and wood.

[0120] In order to facilitate understanding of the method provided in the embodiment of the present application, Figure 4 Further description, such as Figure 4 As shown, first, obtain the stop point data, determine the public place stop based on the stop point POI (point of interest) information, remove the public place stop, and obtain the effective stop. Build an electronic fence, add a market segment label to the electronic fence, and determine the electronic fence to which the stop point belongs and the corresponding market segment label.

[0121] Further, the suspected loading and unloading site is confirmed, the upstream and downstream relationship of the suspected loading and unloading site is confirmed, the number of market segment labels of the suspected loading and unloading site is calculated, and further, within a preset time period, multi-dimensional data of the market segment labels are summarized, and the market segment label results to which the vehicle belongs are comprehensively evaluated based on the summarized data.

[0122] In an exemplary embodiment, based on actual supply matching requirements, the example supply data is used as an example to illustrate the execution process of matching the supply information with vehicles.

[0123] Vehicle A stops at points s1, s2, ..., sN respectively; calculate the public place labels (service areas, gas stations, parking lots, etc.) to which the stops belong, and select the stop data in non-public places as suspected loading places: s1, s2, s3, s4, s5....; take the next stop of the suspected loading place as the suspected unloading place. Calculate the fence to which the stop point belongs and obtain the market segment label for each stop: calculate s1[f1:l1;l2],s2[f2:l3,f3:l4],s3[f3:l5],...,sN[fN:ln] through the calculation formula of the point within the surface; obtain the next stop information of each stop point s1[f1:l1;l2]-s2[f2:l3,f3:l4],s2[f2:l3,f3:l4]-s3[f3:l5],...,s[fN:ln]-null; determine the upstream and downstream flow direction of each stop data and set the number of labels, s1[f1:l1;l2]-s2[f2:l3,f3:l4].

[0124] Case 1: Assuming that l1 and l3 are in the positive upstream and downstream direction, l1 and l4 are in the reverse upstream and downstream direction, and the upstream and downstream relationship of other market segment labels is unknown, the number and coefficient of market segment labels corresponding to s1 are as follows:

[0125] Number of labels in the s1[l1]-s2[l3] segment: 1(number of stops) / 1(number of positive label fences) / 1(number of different positive labels in the fence where the positive label is located)*0.8.

[0126] Case 2: Assuming that l1 and l3, l1 and l4, l2 and l3, l2 and l4 are upstream and downstream reverse, the number of market segment labels and coefficients corresponding to s1 are as follows:

[0127] Number of labels for s1[l1]-s2[l3\l4] segments: 1 / 1 / 2*0.2.

[0128] Number of labels for s1[l2]-s2[l3\l4] segments: 1 / 1 / 2*0.2.

[0129] Case 3: Assuming that the upstream and downstream relationships between l1 and l3, and l1 and l4 are unknown, and l2 and l3, and l2 and l4 are reverse upstream and downstream relationships, the number of market segment labels and coefficients corresponding to s1 are as follows:

[0130] Number of labels for s1[l1]-s2[l3\l4] segments: 1 / 1 / 1*0.5.

[0131] Furthermore, the total number of labels for each market segment of the vehicle is calculated, and the number of labels for each market segment corresponding to the suspected loading locations within the preset time period is summed up to obtain the total number of labels for each market segment. For example, the number of labels for doors and windows at all loading locations is summed up to obtain the total number of labels for doors and windows.

[0132] For the suspected loading and unloading places in the forward direction of the upstream and downstream, the number of forward market segment labels corresponding to all the electronic fences of the loading places are summed up respectively to obtain the total number of each forward market segment label; for the suspected loading and unloading places in the reverse direction of the upstream and downstream, the number of reverse market segment labels corresponding to all the electronic fences of the loading places are summed up respectively to obtain the total number of each reverse market segment label; sum the number of suspected loading places in the forward direction of the upstream and downstream to obtain the total number of forward stops; sum the number of suspected loading places in the reverse direction of the upstream and downstream to obtain the total number of reverse stops; sum the number of suspected loading places where the upstream and downstream flow directions cannot be determined to obtain the total number of stops where the flow direction cannot be determined; sum the number of all suspected loading places to obtain the total number of suspected loading places; sum the number of loading places with market segment labels to obtain the total number of stops with market segment labels.

[0133] Furthermore, the vehicle market segmentation labels are comprehensively evaluated. Assuming that the total number of effective stops of vehicle A is a, and the number of stops with labels is b, when b is less than a certain threshold, or b / a is less than a certain proportion threshold of 10%, it is considered that the market segmentation labels do not cover the vehicle stops sufficiently, and priority is given to setting its market segment through vehicle static data.

[0134] Assuming that the number of labeled stops of vehicle A meets the set threshold, the segmented market label result is directly evaluated: first determine that the number of forward stops > the number of stops with segmented market labels / 3, then use the TOP3 forward segmented market label times (need to satisfy the number of stops with the segmented market label / forward times > 30%, if neither of them is satisfied, take TOP1); secondly determine that the number of reverse stops > the number of stops with segmented market labels / 2, the number of reverse stops > the number of forward stops*2, the number of reverse stops > the number of flow directions that cannot be determined*2, then use the TOP3 reverse segmented market label times (need to satisfy the number of stops with the segmented market label / reverse times > 30%, if neither of them is satisfied, take TOP1); otherwise, use the TOP3 total number of segmented market labels (need to satisfy the number of stops with the segmented market label / the number of stops with the segmented market label > 30%, if neither of them is satisfied, take TOP1) as the segmented market result label of the vehicle.

[0135] Figure 5 It is the application prospect of vehicle segment market label, such as Figure 5As shown, through the construction of electronic fences, vehicle market segmentation calculations, cargo market segmentation calculations, cargo market segmentation can be determined based on industry knowledge. Commercial vehicle market forecasts, freight industry analysis, freight finance, vehicle and cargo market similarity calculations can be performed, and vehicle and cargo matching can be performed to quickly recommend vehicles for the freight market.

[0136] In the commercial vehicle market forecast analysis: Generally, car manufacturers will analyze the use and usage scenarios of vehicles. According to the vehicle market segmentation labels obtained in this application, they can obtain more accurate freight market transportation conditions of vehicles in the market. Based on this information, they can analyze and predict the market demand for various models, and assist in making some commercial vehicle R&D and production strategies.

[0137] Freight finance generally refers to the fact that financial companies will use it to comprehensively evaluate the economic attributes of a vehicle, such as the stability of the transported goods and the prospects of the industry to which the transported goods belong, as factors in the financial loan evaluation; they will also comprehensively evaluate the prospects of the industry's freight market and prepare some industry analysis reports; they will assist in analyzing the upstream and downstream cargo transportation data at the enterprise level and comprehensively evaluate the company's production and operation conditions.

[0138] According to another aspect of the embodiment of the present application, a vehicle and cargo market tag matching device for implementing the above-mentioned vehicle and cargo market tag matching method is also provided. Figure 6 As shown, the device comprises:

[0139] Building module 601, used for obtaining an electronic fence and adding a market segment tag to the electronic fence;

[0140] An analysis module 602 is used to determine a suspected loading and unloading location based on the vehicle parking data, and to find an electronic fence corresponding to the suspected loading and unloading location;

[0141] The statistics module 603 is used to count the total number of market segment labels corresponding to the vehicles in the suspected loading place in a preset time period, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels according to the market segment labels of the electronic fence corresponding to the suspected loading place and the upstream and downstream directions of the suspected loading and unloading place;

[0142] The comprehensive evaluation module 604 is used to input the total number of market segment labels corresponding to vehicles at suspected loading locations within the preset time period, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels into a preset comprehensive evaluation model, and output the market segment labels matching the vehicles.

[0143] It should be noted that the matching device for vehicle and cargo market labels provided in the above embodiment only uses the division of the above functional modules as an example when executing the matching method for vehicle and cargo market labels. In actual applications, the above functional distribution can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the matching device for vehicle and cargo market labels provided in the above embodiment and the matching method embodiment for vehicle and cargo market labels belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0144] According to another aspect of the embodiments of the present application, an electronic device corresponding to the vehicle and cargo market tag matching method provided in the above embodiments is also provided to execute the above vehicle and cargo market tag matching method.

[0145] Please refer to Figure 7 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 7 As shown, the electronic device includes: a processor 700, a memory 701, a bus 702 and a communication interface 703, and the processor 700, the communication interface 703 and the memory 701 are connected through the bus 702; the memory 701 stores a computer program that can be run on the processor 700, and when the processor 700 runs the computer program, it executes the vehicle and cargo market label matching method provided in any of the aforementioned embodiments of the present application.

[0146] The memory 701 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 703 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0147] The bus 702 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. The memory 701 is used to store programs, and the processor 700 executes the program after receiving the execution instruction. The vehicle and cargo market tag matching method disclosed in any implementation of the embodiment of the present application may be applied to the processor 700, or implemented by the processor 700.

[0148] The processor 700 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 700. The above processor 700 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 701, and the processor 700 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0149] The electronic device provided in the embodiment of the present application and the method for matching the vehicle and the cargo market tag 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.

[0150] According to another aspect of the embodiments of the present application, a computer-readable storage medium corresponding to the method for matching a vehicle with a cargo market label provided in the aforementioned embodiments is also provided, on which a computer program (i.e., a program product) is stored. When the computer program is executed by a processor, the method for matching a vehicle with a cargo market label provided in any of the aforementioned embodiments is executed.

[0151] 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.

[0152] The computer-readable storage medium provided in the above-mentioned embodiment of the present application and the method for matching vehicle and cargo market tags provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0153] The technical features of the above embodiments may be arbitrarily combined. 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.

[0154] 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 matching vehicle and cargo market labels, characterized in that: include: Obtaining an electronic fence, and adding a market segment tag to the electronic fence; Determine a suspected loading and unloading location based on the vehicle parking data, and search for an electronic fence corresponding to the suspected loading and unloading location; According to the market segment labels of the electronic fence corresponding to the suspected loading and unloading place, and the upstream and downstream directions of the suspected loading and unloading place, the total number of market segment labels corresponding to the vehicles at the suspected loading place within a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels are counted; The total number of market segment labels corresponding to vehicles at suspected loading locations within the preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels are input into a preset comprehensive evaluation model to output the market segment labels matching the vehicles.

2. The method according to claim 1, characterized in that Before getting an electric fence, also include: Based on the existing electronic fence data and vehicle parking data, the parking data outside the electronic fence is obtained; Aggregating the parking data outside the electronic fence to generate an incremental electronic fence; Determine the name of the incremental electronic fence according to the information of the point of interest closest to the longitude and latitude of the center of the incremental electronic fence; The incremental geo-fence is added to the existing geo-fence set.

3. The method according to claim 1, characterized in that Add segment tags to said geo-fence, including: According to the name keyword of the electronic fence, a corresponding market segment label is matched to obtain a market segment label result corresponding to the name; Acquire the business information corresponding to the name of the electronic fence, and parse the business information to obtain a market segment label result corresponding to the business information; The market segment label of the electronic fence is obtained according to the market segment label result corresponding to the name and the market segment label result corresponding to the industrial and commercial information.

4. The method according to claim 1, characterized in that: Identify suspected loading and unloading locations based on vehicle stop data, including: Based on the vehicle stop data and point of interest information, the stop points for non-freight scenarios are obtained; Deleting the stop point of the non-freight scenario to obtain the suspected loading location; The next stop of the suspected loading place is used as the suspected unloading place.

5. The method according to claim 1, characterized in that Before counting the total number of market segment labels corresponding to vehicles at the suspected loading place within a preset time period according to the market segment labels of the electronic fence corresponding to the suspected loading and unloading place and the upstream and downstream directions of the suspected loading and unloading place, the method further includes: Determine the upstream and downstream directions of the suspected loading and unloading location based on the market segment tags of the electronic fences corresponding to the suspected loading and unloading location; Based on the upstream and downstream directions of the suspected loading and unloading locations and the corresponding market segment labels, the number of each market segment label corresponding to each suspected loading location is calculated.

6. The method according to claim 5, characterized in that The number of market segment labels corresponding to each electronic fence at each suspected loading location is calculated according to the following formula: Y=1 / s / n*a Among them, Y represents the number of market segment labels corresponding to a single electronic fence of the suspected loading place, a represents the preset weight coefficient, the weight coefficient when the suspected loading and unloading place is in the positive direction of upstream and downstream is greater than the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction, and the weight coefficient when the suspected loading and unloading place cannot determine the upstream and downstream flow direction is greater than the weight coefficient when the suspected loading and unloading place is in the reverse direction of upstream and downstream; when it is in the positive direction, s represents the number of electronic fences corresponding to the positive market segment label, n represents the number of different positive labels in the electronic fence where the positive market segment label is located, when it is in the reverse direction or the flow direction cannot be determined, s represents the number of electronic fences corresponding to the loading place, and n represents the number of different market segment labels of each fence of the loading place; The number of labels of each market segment corresponding to all electronic fences of the suspected loading location is summed up to obtain the number of labels of each market segment corresponding to each suspected loading location.

7. The method according to claim 6, characterized in that Before calculating the number of tags for each segment of a single geo-fence corresponding to each suspected loading location, it also includes: Determine the priority according to the upstream and downstream relationship of the suspected loading and unloading place; the priority of the suspected loading and unloading place in the positive upstream and downstream direction is higher than the priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined; the priority of the suspected loading and unloading place when the upstream and downstream flow direction cannot be determined is higher than the priority of the suspected loading and unloading place in the reverse upstream and downstream direction; In the case where the upstream and downstream relationships of the suspected loading and unloading places include multiple types, only the number of labels of each market segment corresponding to the case with the highest priority is calculated.

8. The method according to claim 1, characterized in that: The total number of market segment labels, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops where the flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels corresponding to vehicles at suspected loading places within a preset time period are counted, including: Sum up the number of labels of each market segment corresponding to the suspected loading place within the preset time period to obtain the total number of labels of each market segment; Sum the number of positive market segment labels corresponding to all electronic fences at the loading places in the suspected loading and unloading places in the upstream and downstream directions, and obtain the total number of positive market segment labels; Sum the number of reverse market segment labels corresponding to all electronic fences at the loading places in the upstream and downstream suspected loading and unloading places, and obtain the total number of labels for each reverse market segment; Sum the number of suspected loading places in the upstream and downstream directions to get the total number of forward stops; Sum the number of suspected loading places in the upstream and downstream directions to get the total number of reverse stops; The number of suspected loading places whose upstream and downstream flow directions cannot be determined is summed to obtain the total number of stops whose flow directions cannot be determined; Sum the number of all suspected loading locations to get the total number of suspected loading locations; Sum the number of loading points with market segment labels to get the total number of stops with market segment labels.

9. The method according to claim 1, characterized in that: The total number of market segment labels, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels corresponding to vehicles at suspected loading places within the preset time period are input into the preset comprehensive evaluation model, and the market segment labels matched by the vehicles are output, including: The comprehensive evaluation model is used to determine whether the ratio of the total number of stops with market segment labels to the total number of suspected loading locations is greater than a first threshold; If it is greater than the first threshold, determine whether the total number of positive stops meets the preset proportion of the total number of stops with market segment labels. If so, obtain the top three in the ranking of the total number of positive market segment labels, and respectively determine whether the total number of the top three positive market segment labels meets the preset proportion of the total number of positive stops. The market segment labels that meet the preset proportion of the total number of positive market segment labels in the total number of positive stops among the top three are used as the market segment labels matched by the vehicle. If none of the top three meet the requirements, take the market segment label with the highest total number of positive market segment labels as the market segment label matched by the vehicle. If the total number of forward stops does not meet the preset proportion of the total number of stops with market segment labels, determine whether the total number of reverse stops meets the preset proportion of the total number of stops with market segment labels, and the total number of reverse stops is greater than 2 times the total number of forward stops, and the total number of reverse stops is greater than 2 times the total number of stops that cannot determine the flow direction; if so, obtain the top three reverse market segment label totals, and determine whether the top three reverse market segment label totals meet the preset proportion of the reverse market segment totals, and use the top three reverse market segment label that meets the preset proportion of the reverse market segment label totals as the vehicle matching market segment label; if none of the top three meet, use the market segment label with the highest reverse market segment label totals as the vehicle matching market segment label; If the total number of reverse stops does not meet the preset proportion of the total number of stops with segmented market labels, and the total number of reverse stops is greater than twice the total number of forward stops, and the total number of reverse stops is greater than twice the total number of stops where the flow direction cannot be determined, then obtain the top three total number of segmented market labels corresponding to the vehicle, and determine whether the total number of the first three segmented market labels meets the preset proportion in the total number of stops with segmented market labels. The segmented market labels that meet the preset proportion in the total number of stops with segmented market labels among the first three are used as the segmented market labels matching the vehicle. If none of the first three meet the requirements, take the segmented market label with the highest total number of segmented market labels as the segmented market label matching the vehicle.

10. A device for matching vehicle and cargo market tags, characterized in that: include: A construction module is used to obtain an electronic fence and add a market segment tag to the electronic fence; An analysis module, used to determine a suspected loading and unloading location based on the vehicle stop data, and to find an electronic fence corresponding to the suspected loading and unloading location; A statistics module is used to count the total number of market segment labels corresponding to vehicles in the suspected loading place in a preset time period, the total number of forward market segment labels, the total number of reverse market segment labels, the total number of forward stops, the total number of reverse stops, the total number of stops whose flow direction cannot be determined, the total number of suspected loading places, and the total number of stops with market segment labels, according to the market segment labels of the electronic fence corresponding to the suspected loading place and the upstream and downstream directions of the suspected loading and unloading place; The comprehensive evaluation module is used to input the total number of market segment labels corresponding to vehicles at suspected loading locations within the preset time period, the total number of positive market segment labels, the total number of reverse market segment labels, the total number of positive stops, the total number of reverse stops, the total number of stops with unknown flow directions, the total number of suspected loading locations, and the total number of stops with market segment labels into a preset comprehensive evaluation model, and output the market segment labels matching the vehicles.

11. 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 matching a vehicle with a cargo market tag according to any one of claims 1 to 9 when executing the program instructions.

12. 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 matching a vehicle with a cargo market tag as claimed in any one of claims 1 to 9.

Images