Method and apparatus for associating a point of interest with a shipping label, and electronic device

Abstract

The embodiment of the present disclosure relates to a method for associating a shipping order with a point of interest, comprising: obtaining description information of the shipping order and description information of the point of interest; obtaining at least one of description information of an entity object associated with the shipping order and description information of an entity object associated with the point of interest; determining whether the shipping order and the point of interest satisfy a set association condition based on the description information of the shipping order, the description information of the point of interest, and the at least one of the description information of the entity object associated with the shipping order and the description information of the entity object associated with the point of interest; and associating the shipping order with the point of interest when the association condition is satisfied. The technical solution of the present disclosure can improve the recall rate and accuracy of the shipping order association.

Description

Technical Field

[0001] This disclosure relates to the field of data mining technology, and more particularly to a method and apparatus for associating points of interest with waybills, as well as electronic devices, computer storage media, and computer program products. Background Technology

[0002] In existing technologies, during the construction of points of interest (POIs), waybills associated with POIs can be linked to those POIs. Since both waybills and POIs have corresponding address information, existing technologies typically perform semantic similarity matching between the address information of waybills and POIs to confirm whether they can be associated. However, the inventors have discovered that differences in the description methods of waybill and POI address information, and in some cases, ambiguity in address information description, can affect the accuracy of similarity matching, ultimately impacting the recall and accuracy of POI-linked waybill association. Summary of the Invention

[0003] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a method and apparatus for associating points of interest with waybills, as well as electronic devices, computer storage media, and computer program products.

[0004] This disclosure provides a method for associating points of interest with waybills, including:

[0005] Obtain the description information of the waybill and the description information of the point of interest;

[0006] Obtain at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest;

[0007] Based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity object associated with the waybill and the entity object associated with the point of interest, determine whether the waybill and the point of interest meet the set association conditions.

[0008] When the association conditions are met, the waybill is associated with the point of interest.

[0009] This disclosure also provides an apparatus for associating points of interest with waybills, including:

[0010] The first acquisition module is used to acquire the description information of the waybill and the description information of the point of interest;

[0011] The second acquisition module is used to acquire at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest;

[0012] The condition determination module is used to determine whether the waybill and the point of interest meet the set association conditions based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity object associated with the waybill and the entity object associated with the point of interest.

[0013] The association module is used to associate the waybill with the point of interest when the association conditions are met.

[0014] This disclosure also provides an electronic device, the electronic device comprising:

[0015] processor;

[0016] Memory used to store the processor's executable instructions;

[0017] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of linking points of interest to waybills as described above.

[0018] This disclosure also provides a computer-readable storage medium storing a computer program for executing the above-described method for associating points of interest with waybills.

[0019] This disclosure also provides a computer program product for executing the above-described method for associating points of interest with waybills.

[0020] The technical solution provided in the above embodiments of this disclosure no longer only considers semantic matching of the address information of waybills and points of interest, but further considers obtaining at least one of the description information of entity objects associated with waybills and entity objects associated with points of interest. This description information is then combined with the description information of the waybill and the point of interest to comprehensively determine whether the waybill and the point of interest meet the set association conditions. If the association conditions are met, the waybill is associated with the point of interest. The description information of the waybill can include the address information mentioned above, as well as other information. For example, in specific implementations, further behavioral information can be provided, such as the audience connected to a Wi-Fi device of a certain point of interest. The above-mentioned use of the description information of associated entity objects is equivalent to feature enhancement of waybills and points of interest, making fuller use of their features for similarity judgment. When the similarity judgment result meets the set association conditions, the waybill is associated with the point of interest, which can improve the recall and accuracy of waybill association. Attached Figure Description

[0021] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0022] Figure 1 A flowchart illustrating a method for associating points of interest with waybills, provided in an embodiment of this disclosure;

[0023] Figure 2 This is a schematic flowchart illustrating step 103 provided in an embodiment of the present disclosure;

[0024] Figure 3 This is a schematic diagram of the structure of the relationship network provided in the embodiments of this disclosure;

[0025] Figure 4 Feature vector graph of the relationship network provided in the embodiments of this disclosure;

[0026] Figure 5 This is a feature vector map of the association network after feature enhancement processing provided in the embodiments of this disclosure;

[0027] Figure 6 A flowchart illustrating a specific implementation method provided in the embodiments of this disclosure;

[0028] Figure 7 A schematic diagram of the structure of a device for associating points of interest with waybills, provided in an embodiment of this disclosure;

[0029] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0030] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0031] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0032] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0033] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0034] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0035] In existing technologies, when associating waybills with points of interest (POIs), semantic similarity matching is performed between the address information of the waybill and the address information of the POI to determine whether an association is possible. However, even if the two locations are actually the same, aliases or ambiguous addresses may be used in some cases, affecting the similarity matching results and ultimately impacting the recall and accuracy of waybill association. The technical solution provided in this disclosure goes beyond simply considering semantic matching of the address information of the waybill and the POI. Instead, it further considers obtaining at least one of the description information of the entity object associated with the waybill and the entity object associated with the POI. This description information is then combined with the description information of the waybill and the POI to determine whether the waybill and the POI meet the set association conditions. If the set association conditions are met, the waybill is associated with the POI. The description information of the waybill may include the aforementioned address information or other information. The description information of the entity objects associated with the waybill, or the description information of the entity objects associated with the point of interest, can enhance the similarity judgment between the waybill and the point of interest. Therefore, the technical solution of this embodiment can better associate waybills and points of interest with a certain relationship, thereby improving the recall rate and accuracy of waybill association.

[0036] Figure 1 This is a flowchart illustrating a method for associating points of interest with waybills, provided in an embodiment of this disclosure. This method can be executed on an electronic device, including but not limited to computers, mobile terminals, or servers. Figure 1 As shown, the steps include the following:

[0037] Step 101: Obtain the description information of the waybill and the description information of the points of interest;

[0038] The descriptive information obtained in this step for the waybill mainly includes the geographical location information filled in on the waybill, as well as the names of buildings, parks, scenic spots, schools, units, enterprises, and shops, and may also include coordinate information obtained by converting geographical information. Similarly, the descriptive information for points of interest can also include its geographical location information, as well as the names of buildings, parks, scenic spots, schools, units, enterprises, and shops, and may also include coordinate information obtained by converting geographical information. The aforementioned geographical location information and name information can be collectively referred to as address information.

[0039] Step 102: Obtain at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest;

[0040] In this step, the entity objects associated with the waybill can be obtained first. These are entity objects that have a certain relationship with the aforementioned waybill or point of interest. These entity objects include, but are not limited to, information about the audience, Wi-Fi, and point of interest. The relationship between these entity objects and the waybill or point of interest can be one-hop or multi-hop. A one-hop relationship means that the entity object has a direct relationship with the waybill or point of interest; this entity object can be called a directly associated entity object. A multi-hop relationship means that the two are indirectly associated through other entities; this entity object can be called an indirectly associated entity object. In this embodiment, descriptive information of entity objects within a two-hop relationship can be obtained. Therefore, obtaining the descriptive information of the entities associated with the waybill can include:

[0041] Obtain the description information of the directly associated entity objects of the waybill, as well as the description information of the indirectly associated entity objects;

[0042] The above-mentioned acquisition of descriptive information of entities associated with the point of interest may include:

[0043] Obtain description information of the directly associated entity objects of the point of interest, as well as description information of the indirectly associated entity objects of the point of interest.

[0044] For each entity, there are multiple association scenarios. For example, the audience associated with a waybill can be associated with the first hop of the waybill, such as the orderer or the recipient. Alternatively, based on information obtained in advance, the first audience can be associated with other audiences, such as relatives, friends, or roommates. The first audience can be associated with other audiences, i.e., the second audience, which is the entity associated with the second hop of the waybill. The first audience can also be associated with other entities, such as the Wi-Fi information frequently used by the first audience, the address information frequently searched or located when using navigation maps, the shops operated by the first audience, and the workplace of the first audience. The Wi-Fi information can include the Wi-Fi name, which can be associated with points of interest. The geographical location information, shops, or workplaces can all be points of interest. If they can be associated with the waybill, the similarity judgment between the waybill and the point of interest can be enhanced.

[0045] In some embodiments, for a waybill, its directly associated entity object can be a first audience, and the first audience can be further associated with a second audience, WIFI, or point of interest in one hop, and the second audience, WIFI, or point of interest is associated with the waybill in two hops.

[0046] For points of interest (POIs), the associated entities can include directly associated entities and indirectly associated entities. Directly associated entities, i.e., those linked in the first hop, can be third-party audiences, Wi-Fi networks, or other POIs. Specifically, if prior information reveals that the POI is a shop, its operator and employees can be identified as third-party audiences linked in the first hop. Referring to the above technical solution description, these third-party audiences can be further associated with indirectly associated entities, i.e., other entities linked in the second hop. Similarly, prior information can reveal the Wi-Fi information within the POI, and further, the fourth-party audiences who frequently connect to that Wi-Fi network can be identified. These fourth-party audiences can be indirectly associated entities linked in the second hop. In the case of POIs linked in the first hop, it mainly refers to addresses that are related. For example, one POI might be "...University," and another might be "...University Graduate School," forming a parent-child relationship.

[0047] In addition to the description information of the waybill and the description information of the point of interest, which can refer to the content disclosed in the above embodiments, the description information of WIFI can include information such as connection frequency, connection time distribution information or WIFI name, while the description information of the audience can be the relationship type of the audience.

[0048] Step 103: Based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity object associated with the waybill and the entity object associated with the point of interest, determine whether the waybill and the point of interest meet the set association conditions.

[0049] In this step, after obtaining the description information of the waybill, the description information of the point of interest, and the description information of the entity objects associated with the waybill and / or the entity objects associated with the point of interest through steps 101 and 102, the similarity between the waybill and the point of interest is determined by comprehensively utilizing the above information. If, as described in step 102, the description information of the associated entity objects can be used to enhance the determination of the similarity between the waybill and the point of interest, compared to the existing technology that only uses the address information of the waybill and the address information of the point of interest for semantic similarity matching to determine whether they can be associated, it obviously enhances the similarity between the two and more realistically reflects their actual similarity. At this time, judging whether the association conditions are met based on similarity can improve the recall rate and precision.

[0050] Step 104: When the above-set association conditions are met, associate the waybill with the point of interest. The technical solution provided in the above embodiments of this disclosure collects description information of entity objects associated with waybills and entity objects associated with points of interest, and then determines whether a waybill can be associated with a point of interest. This fully utilizes the description information of the associated entity objects to determine the similarity between the point of interest and the waybill. When the similarity determination result meets the association conditions, the waybill is associated with the point of interest, thereby improving the recall and accuracy of waybill association.

[0051] In the embodiments disclosed above, when determining whether a waybill and a point of interest meet the set association conditions based on the description information of the waybill, the description information of the point of interest, and the description information of the associated entity objects in step 103, it can be done by constructing an association network based on the waybill, the point of interest, and the entity objects associated with the waybill and the point of interest. The waybill, the point of interest, and the associated entity objects are all treated as entity objects on the association network. Then, feature vectors of the waybill, the point of interest, and the associated entity objects in the association network are further obtained. Finally, the method of determining whether the waybill and the point of interest meet the set association conditions is based on the feature vectors. This implementation method can be called a network representation learning technical solution. Figure 2 This is a detailed flowchart illustrating step 103 provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, it includes the following steps:

[0052] Step 201: Based on waybills, points of interest, and at least one of the entity objects associated with waybills and entity objects associated with points of interest, construct an association network;

[0053] Specifically, in the relationship network, each node represents an entity object. These entity objects can include the aforementioned waybill and point of interest, as well as at least one of other entity objects associated with waybills and entity objects associated with points of interest. The relationships between entity objects are represented by edges. Figure 3 This is a schematic diagram of the structure of the association network provided in the embodiments of this disclosure, such as... Figure 3 As shown, the association network includes six nodes: A, B, C, D, E, and F. Node C represents a point of interest; node F represents a waybill; node A represents the audience, which is associated with the waybill in one hop; node B represents Wi-Fi, which is associated with both the point of interest and the audience in one hop, equivalent to a two-hop association with the waybill; furthermore, the audience can also be associated with the point of interest in one hop. The above association is merely illustrative and may include other associations.

[0054] Step 202: Generate a feature vector of the waybill based on the description information of the waybill, generate a feature vector of the point of interest based on the description information of the point of interest, and generate a feature vector of the entity object associated with the waybill based on the description information of the entity object associated with the waybill and generate a feature vector of the entity object associated with the point of interest based on the description information of the entity object associated with the point of interest.

[0055] The descriptive information regarding waybills, points of interest, and associated entity objects can be found in the above embodiments. This step mainly involves generating corresponding feature vectors based on the descriptive information of waybills, points of interest, and associated entity objects.

[0056] After extracting vectors from each entity object in the network graph to obtain the corresponding feature vectors, they can be used as follows: Figure 4 As shown, Figure 4 The feature vector graph of the association network provided in this embodiment of the disclosure is provided, wherein for each entity object in the association network, a corresponding feature vector is extracted, such as the feature vector f corresponding to the waybill, the feature vector a corresponding to the audience, the feature vector b corresponding to WIFI, and the feature vector c corresponding to the point of interest.

[0057] Step 203: Based on the feature vector of the waybill, the feature vector of the point of interest, and at least one of the feature vectors of the entity objects associated with the waybill and the entity objects associated with the point of interest in the association network, determine whether the waybill and the point of interest meet the set association conditions.

[0058] The network representation learning technical implementation scheme provided in this disclosure is based on at least one of the feature vectors of waybills and interest points in the association network, as well as the feature vectors of entity objects associated with waybills and entity objects associated with interest points. This can also be considered as being based on the feature vector graph of the aforementioned association network to determine whether waybills and interest points meet the set association conditions. In its specific execution process, the association relationships between different entity objects can be fully utilized for vector enhancement. The feature vectors of waybills and interest points can be enhanced, and based on the enhanced feature vectors of waybills and interest points, it can be determined whether the association conditions are met. Specific implementation methods will be described in the following embodiments.

[0059] Since the associated entity objects used in this embodiment may include entity objects associated with waybills and / or entity objects associated with points of interest, and at least one of obtaining the feature vector of the entity object associated with the waybill and the feature vector of the entity object associated with the point of interest is obtained, step 203 above may include three cases during execution:

[0060] In the first scenario, feature enhancement processing is performed only on the feature vector of the waybill. That is, based on the feature vectors of the entity objects associated with the waybill, a graph embedding network is used to enhance the feature vector of the waybill, generating an enhanced feature vector for the waybill. In this case, the enhanced feature vector of the waybill and the feature vectors of the points of interest can be used to further determine whether the set association conditions are met. Specifically... Figure 5 The feature vector map of the association network after feature enhancement processing is provided for the embodiments of this disclosure, such as Figure 5 As shown, this scheme utilizes the feature vectors of entity objects associated with the waybill, such as the feature vector a of the audience, or possibly the feature vector b of WIFI, to perform feature enhancement processing on the feature vector f of the waybill, resulting in the feature enhancement vector "enhanced f" of the waybill. That is, it considers the similarity between the waybill and the point of interest from other factors, which can improve the similarity judgment result between the two, thereby improving the accuracy and recall of the final association.

[0061] The second scenario involves feature enhancement processing only on the feature vectors of the points of interest. This is achieved by using a graph embedding network to enhance the feature vectors of the points of interest based on the feature vectors of the entities associated with them, generating enhanced feature vectors for the points of interest. In this case, further analysis can be performed based on the feature vectors of the entities and the enhanced feature vectors of the points of interest to determine whether the established association conditions are met. Specifically, for example... Figure 5As shown, this scheme utilizes the feature vectors of entity objects associated with the point of interest, such as the feature vector b of WIFI, or may also include the feature vector a of the audience, to perform feature enhancement processing on the feature vector c of the point of interest, resulting in the feature enhancement vector "enhanced c" of the point of interest. That is, it considers the similarity between the waybill and the point of interest from other factors, which can improve the similarity judgment result between the two, thereby improving the accuracy and recall of the final association.

[0062] The third scenario combines the first and second scenarios, performing feature enhancement processing on both the waybill's feature vector *f* and the point of interest's feature vector *c*. Finally, based on the enhanced feature vectors *f* (enhanced) of the waybill and *c* (enhanced) of the point of interest, it is determined whether the set association conditions are met. This scheme simultaneously enhances the feature vectors of both the waybill and the point of interest, considering the similarity between them from other factors. This enhances the similarity determination result, thereby improving the accuracy and recall of the final association.

[0063] In some embodiments, Figure 6 This is a schematic diagram illustrating a specific implementation method provided in the embodiments of this disclosure, such as... Figure 6 As shown, for the above three cases, in the step of feature enhancement processing through graph embedding networks, the graph embedding network can specifically include at least one neighbor feature aggregation network. This neighbor feature aggregation network can enhance the target feature vector using the feature vectors of neighbor nodes in the network, achieving the effect of neighbor feature aggregation. In the case of determining whether a waybill and an interest point satisfy a set association condition based on the feature enhancement vector of either a waybill or an interest point, the association probability between the waybill and the interest point can be determined through a classification network. If the association probability meets a preset threshold, then the association condition is satisfied. Specifically, for the first case, the association probability between the waybill and the interest point is determined through a classification network based on the feature enhancement vector of the waybill and the feature vector of the interest point; for the second case, the association probability between the waybill and the interest point is determined through a classification network based on the feature vector of the waybill and the feature enhancement vector of the interest point; and for the third case, the association probability between the waybill and the interest point is determined through a classification network based on the feature enhancement vector of the waybill and the feature enhancement vector of the interest point.

[0064] like Figure 6 As shown, in some embodiments, in the first and third cases described above, performing feature enhancement processing on the feature vector of the waybill using a graph embedding network to obtain the enhanced feature vector of the waybill may include:

[0065] By using at least one neighbor feature aggregation network, the feature vector of the waybill is processed by neighbor feature aggregation using the feature vector of the entity object associated with the waybill, and the feature enhancement vector of the waybill is obtained.

[0066] In the first and third cases mentioned above, based on the feature vectors of the entity objects associated with the interest points, feature enhancement processing is performed on the feature vectors of the interest points through a graph embedding network to obtain the feature-enhanced vectors of the interest points, including:

[0067] By using at least one neighbor feature aggregation network, the feature vectors of the entity objects associated with the point of interest are aggregated with neighbor features to obtain the feature enhancement vector of the point of interest.

[0068] exist Figure 6 In the illustrated embodiment, two neighbor feature aggregation networks are used. The first neighbor feature aggregation network can be used to perform neighbor feature aggregation processing using the feature vectors of one-hop related entity objects, while the second neighbor feature aggregation network can be used to perform neighbor feature aggregation processing using the feature vectors of two-hop related entity objects.

[0069] In some embodiments, the neighbor feature aggregation network described above can be any one of the following: GeniePath network, GAT network, GraphSage network, and HeGnn network. GeniePath network is an adaptive path-aware graph neural network that can automatically learn and propagate neighbors that contribute significantly to the target node. GAT network, short for Graph Attention Network, can introduce a self-attention mechanism during propagation, where the hidden state of each node is calculated by paying attention to its neighbor nodes. GraphSage network is another type of graph neural network that combines topological structure and vertex attribute information to learn vertex representations. HeGnn network is also a type of graph neural network that can aggregate information about neighbor nodes on a graph network. Any one of the above-mentioned networks, or other networks capable of achieving the same function, can be used in the embodiments of this disclosure.

[0070] Furthermore, the graph embedding network may also include a Multi-Layer Perception (MLP), which can map multiple input feature vectors and output the mapped results to the aforementioned neighbor feature aggregation network. For example, in the above embodiment, at least one of the feature vectors of the waybill, the feature vector of the interest point, and the feature vectors of the entity objects associated with the waybill and the entity objects associated with the interest point from the association network is input to the multi-layer perceptron. Figure 6 The input vector [X1,X2,X3,X4L] shown is processed sequentially through at least one neighbor feature aggregation network to obtain a comprehensive vector [Node1,Node2] that includes the feature vectors after neighbor feature aggregation. These vectors represent the feature vectors of the waybill and the feature vectors of the interest points, respectively. Depending on whether the input is the feature vector of the entity associated with the waybill or the feature vector of the entity associated with the interest point, the feature vectors of the waybill and / or the feature vectors of the interest points are feature enhancement vectors.

[0071] In the above embodiments, the input vector [X1,X2,X3,X4L] input to the multilayer perceptron, where X1, X2, X3, and X4 can respectively refer to... Figure 4 The illustrated embodiment includes feature vectors for waybills, points of interest, Wi-Fi, and audiences. The feature vector for a waybill can include at least one of semantic vectors, locative terms, core name suffix descriptions, and coordinate vectors. The core name suffix primarily indicates the type of address; for example, if the core name is a company, the waybill would include "...Limited Company," and if the core name is a school, the waybill would include "...University," etc. The feature vector for a point of interest can include at least one of semantic vectors, point of interest type, and coordinate vectors. Point of interest type can include, for example, schools, companies, scenic spots, etc. The feature vector for Wi-Fi can include at least one of connection frequency, time distribution, and semantic vectors of the Wi-Fi name. The feature vector for an audience includes the audience relationship type, which can include, for example, spousal relationships, colleague relationships, cohabitation relationships, etc. In the above embodiments of this disclosure, the semantic vectors can be BERT semantic vectors or WordK2Vec semantic vectors.

[0072] In some embodiments, the classification network described above sequentially includes a fully connected layer, an MLP, and a binary cross-entropy loss function, wherein the binary cross-entropy loss function can be SoftMax Loss. The comprehensive vector [Node1, Node2] is input to the fully connected layer, and finally outputs a probability value by the binary cross-entropy loss function. This probability value can be used to characterize the similarity between the waybill and the point of interest. The greater the similarity, the greater the probability value, and vice versa. By comparing the above probability value with the association probability threshold, it can be determined whether the waybill and the point of interest meet the final association condition. Therefore, it can also be called the association probability.

[0073] The following are embodiments of the apparatus for linking points of interest to waybills provided in this disclosure. The specific content of these embodiments corresponds to the method embodiments described above. The explanations of the related technical solutions and the technical effects of their implementation can be found in the descriptions of the above embodiments. Figure 7 This is a schematic diagram of the structure of a device for associating points of interest with waybills, provided in an embodiment of this disclosure. Figure 7 As shown, the device includes a first acquisition module 11, a second acquisition module 12, a condition determination module 13, and an association module 14.

[0074] The first acquisition module 11 is used to acquire the description information of the waybill and the description information of the point of interest;

[0075] The second acquisition module 12 is used to acquire at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest;

[0076] The condition determination module 13 is used to determine whether the waybill and the point of interest meet the set association conditions based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity object associated with the waybill and the entity object associated with the point of interest.

[0077] The association module 14 is used to associate the waybill with the point of interest when the association conditions are met.

[0078] The technical solution provided in the above embodiments of this disclosure collects description information of entity objects associated with waybills and description information of entity objects associated with points of interest, and then determines whether waybills can be associated with points of interest. It can make full use of the description information of the associated entity objects to judge the similarity between points of interest and waybills, and when the result of the similarity judgment meets the association conditions, the waybill is associated with the point of interest, which can improve the recall rate and accuracy of waybill association.

[0079] In some embodiments, the second acquisition module described above is specifically used to acquire description information of entity objects associated with a single hop of a waybill and description information of entity objects associated with a second hop of a waybill; and to acquire description information of entity objects associated with a first hop of a point of interest and description information of entity objects associated with a second hop of a point of interest.

[0080] In some embodiments, the entity objects associated with the waybill include: directly associated entity objects and indirectly associated entity objects;

[0081] The direct associated entity of the waybill includes a first audience, and the indirect associated entity includes at least one of a second audience, WIFI, and point of interest.

[0082] The entity objects associated with the points of interest include: directly associated entity objects and indirectly associated entity objects;

[0083] The directly associated entity objects of the point of interest include at least one of the third audience, WIFI, and point of interest.

[0084] In some embodiments, the condition determination module 13 includes:

[0085] A network construction unit is used to construct an association network based on the waybill, the point of interest, and at least one of the entity objects associated with the waybill and the entity objects associated with the point of interest.

[0086] A feature vector generation unit is configured to generate a feature vector of the waybill based on the description information of the waybill, generate a feature vector of the point of interest based on the description information of the point of interest, and generate a feature vector of the entity object associated with the waybill based on the description information of the entity object associated with the waybill and generate a feature vector of the entity object associated with the point of interest based on the description information of the entity object associated with the point of interest.

[0087] The condition determination unit is used to determine whether the waybill and the point of interest meet the set association conditions based on at least one of the feature vector of the waybill, the feature vector of the point of interest, the feature vector of the entity object associated with the waybill, and the feature vector of the entity object associated with the point of interest in the association network.

[0088] In some embodiments, the condition determination unit is specifically used to perform feature enhancement processing on the feature vector of the entity object associated with the waybill through a graph embedding network to generate the feature enhancement vector of the waybill, and / or, based on the feature vector of the entity object associated with the point of interest, perform feature enhancement processing on the feature vector of the point of interest through a graph embedding network to generate the feature enhancement vector of the point of interest.

[0089] When generating the feature enhancement vector of the waybill, it is determined whether the association condition is met based on the feature enhancement vector of the waybill and the feature vector of the point of interest.

[0090] When generating the feature enhancement vector of the point of interest, it is determined whether the association condition is met based on the feature vector of the waybill and the feature enhancement vector of the point of interest.

[0091] When generating the feature enhancement vector of the waybill and the feature enhancement vector of the point of interest, it is determined whether the waybill and the point of interest meet the set association conditions based on the feature enhancement vector of the waybill and the feature enhancement vector of the point of interest.

[0092] In some embodiments, the condition determination unit is specifically configured to perform neighbor feature aggregation processing on the feature vector of the waybill using the feature vector of the entity object associated with the waybill through at least one neighbor feature aggregation network to obtain the feature enhancement vector of the waybill; and / or, perform neighbor feature aggregation processing on the feature vector of the point of interest using the feature vector of the entity object associated with the point of interest through at least one neighbor feature aggregation network to obtain the feature enhancement vector of the point of interest.

[0093] In some embodiments, the neighbor feature aggregation network includes any one of the GeniePath network, GAT network, GraphSage network, and HeGnn network.

[0094] In some embodiments, the condition determination unit is specifically used to determine the association probability between the waybill and the point of interest through a classification network. If the association probability meets a preset threshold, then the association condition is determined to be met. Specifically, it may include:

[0095] Based on the feature enhancement vector of the waybill and the feature vector of the point of interest, the association probability between the waybill and the point of interest is determined by a classification network. If the association probability meets a preset threshold, the association condition is determined to be met.

[0096] Alternatively, it can be used specifically to determine the association probability between the waybill and the point of interest through a classification network based on the feature vector of the waybill and the feature enhancement vector of the point of interest. If the association probability meets a preset threshold, then the association condition is determined to be met.

[0097] Alternatively, it can be used specifically to determine the association probability between the waybill and the point of interest based on the feature enhancement vector of the waybill and the feature enhancement vector of the point of interest through a classification network. If the association probability meets a preset threshold, then the association condition is determined to be met.

[0098] In some embodiments, the feature vector of the waybill includes at least one of semantic vector, locative words, core name suffix description, and coordinate vector; the feature vector of the point of interest includes at least one of semantic vector, point of interest type, and coordinate vector; the feature vector of the WIFI includes at least one of connection frequency, time distribution, and semantic vector of WIFI name; and the feature vector of the audience includes audience relationship type.

[0099] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. The scheme of associating waybills with points of interest described above in the embodiments of the present disclosure can be implemented on a cloud server or a local host. Therefore, the electronic device can be a cloud server, a local host, or a client device as described in the above embodiments.

[0100] The following detailed reference illustrates a structural diagram suitable for implementing the electronic device 500 in the embodiments of this disclosure. The electronic device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs, desktop computers, servers, etc. The illustrated electronic device is merely an example and should not impose any limitations on the functionality and scope of the embodiments of this disclosure.

[0101] As shown in the figure, electronic device 500 may include a processing device (e.g., CPU, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing device 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0102] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 500 with various devices is shown, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0103] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined above in the method for associating waybills with points of interest according to embodiments of this disclosure.

[0104] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0105] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0106] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0107] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0108] Obtain the description information of the waybill and the description information of the point of interest;

[0109] Obtain at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest;

[0110] Based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity object associated with the waybill and the entity object associated with the point of interest, determine whether the association condition is met.

[0111] When the association conditions are met, the waybill is associated with the point of interest.

[0112] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0114] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0115] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0116] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0117] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium storing a computer program for performing a method for associating point-of-interest (POI) waybills as described in any of the present disclosure.

[0118] According to one or more embodiments of this disclosure, this disclosure provides a computer program product for performing a method for associating point-of-interest waybills as described in any of the embodiments provided in this disclosure.

[0119] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0120] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0121] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for associating points of interest with waybills, comprising: Obtain the description information of the waybill and the description information of the point of interest; Obtain at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest, wherein the entity object associated with the waybill or point of interest includes: directly associated entity objects and / or indirectly associated entity objects, and the entity object includes at least one of audience, WIFI, and point of interest; Based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity objects associated with the waybill and the entity objects associated with the point of interest, a feature vector of the waybill, point of interest, and associated entity objects in the association relationship network is obtained by constructing an association relationship network based on the waybill, point of interest, and entity objects associated with the waybill and the point of interest. Based on the feature vector, it is determined whether the waybill and the point of interest meet the set association conditions. When the association conditions are met, the waybill is associated with the point of interest.

2. The method of claim 1, wherein, The method involves obtaining feature vectors of the waybill, the point of interest, and the associated entity objects based on at least one of the description information of the waybill, the point of interest, and the associated entity objects, through an association network constructed based on the waybill, the point of interest, and the associated entity objects. Based on these feature vectors, it determines whether the waybill and the point of interest meet the set association conditions, including: Based on the waybill, the point of interest, and at least one of the entity objects associated with the waybill and the entity objects associated with the point of interest, construct an association network; At least one of the following: generating a feature vector of the waybill based on the description information of the waybill; generating a feature vector of the point of interest based on the description information of the point of interest; generating a feature vector of the entity object associated with the waybill based on the description information of the entity object associated with the waybill; and generating a feature vector of the entity object associated with the point of interest based on the description information of the entity object associated with the point of interest. Based on at least one of the feature vectors of the waybill, the feature vector of the point of interest, the feature vectors of the entity objects associated with the waybill, and the feature vectors of the entity objects associated with the point of interest in the association network, it is determined whether the waybill and the point of interest meet the set association conditions.

3. The method of claim 2, wherein, The step of determining whether the waybill and the point of interest satisfy the set association conditions based on at least one of the feature vectors of the waybill, the feature vectors of the points of interest, the feature vectors of the entity objects associated with the waybill, and the feature vectors of the entity objects associated with the points of interest in the association network includes: Based on the feature vector of the entity object associated with the waybill, feature enhancement processing is performed on the feature vector of the waybill through a graph embedding network to generate the feature enhancement vector of the waybill; and / or, based on the feature vector of the entity object associated with the point of interest, feature enhancement processing is performed on the feature vector of the point of interest through a graph embedding network to generate the feature enhancement vector of the point of interest. When generating the feature enhancement vector of the waybill, based on the feature enhancement vector of the waybill and the feature vector of the point of interest, it is determined whether the waybill and the point of interest meet the set association conditions. When generating the feature enhancement vector of the point of interest, based on the feature vector of the waybill and the feature enhancement vector of the point of interest, it is determined whether the waybill and the point of interest meet the set association conditions. When generating the feature enhancement vector of the waybill and the feature enhancement vector of the point of interest, it is determined whether the waybill and the point of interest meet the set association conditions based on the feature enhancement vector of the waybill and the feature enhancement vector of the point of interest.

4. The method of claim 3, wherein, The graph embedding network includes at least one neighbor feature aggregation network. The step of performing feature enhancement processing on the feature vector of the waybill through the graph embedding network to obtain the enhanced feature vector of the waybill includes: By using at least one neighbor feature aggregation network, the feature vector of the waybill is processed by neighbor feature aggregation using the feature vector of the entity object associated with the waybill, and the feature enhancement vector of the waybill is obtained. The feature vector of the entity object associated with the point of interest is used to perform feature enhancement processing on the feature vector of the point of interest through a graph embedding network to obtain the feature enhancement vector of the point of interest, including: By using at least one neighbor feature aggregation network, the feature vector of the interest point is processed by neighbor feature aggregation using the feature vector of the entity object associated with the interest point, thereby obtaining the feature enhancement vector of the interest point.

5. The method of claim 4, wherein, The neighbor feature aggregation network includes any one of the following: GeniePath network, GAT network, GraphSage network, and HeGnn network.

6. The method of any one of claims 1-5, wherein, The determination of whether the waybill and the point of interest meet the set association conditions includes: The association probability between the waybill and the point of interest is determined by a classification network. If the association probability meets a preset threshold, then the waybill and the point of interest are determined to meet the set association conditions.

7. The method of any one of claims 2-5, wherein, The direct associated entity of the waybill includes a first audience, and the indirect associated entity includes at least one of a second audience, WIFI, and point of interest. The entity objects associated with the points of interest include: directly associated entity objects and indirectly associated entity objects; The directly associated entity objects of the point of interest include at least one of the third audience, WIFI, and point of interest.

8. The method of claim 7, wherein, The feature vector of the waybill includes at least one of semantic vector, directional words, core name suffix description, and coordinate vector; The feature vector of the interest point includes at least one of semantic vector, interest point type and coordinate vector; The feature vector of the WIFI includes at least one of connection frequency, time distribution, and semantic vector of the WIFI name; The feature vector of the audience includes the audience relationship type.

9. An apparatus for associating a point of interest with a waybill, comprising: The first acquisition module is used to acquire the description information of the waybill and the description information of the point of interest; The second acquisition module is used to acquire at least one of the description information of the entity object associated with the waybill and the description information of the entity object associated with the point of interest, wherein the entity object associated with the waybill or point of interest includes: directly associated entity objects and / or indirectly associated entity objects, and the entity object includes at least one of audience, WIFI, and point of interest. The condition determination module is used to obtain feature vectors of the waybill, the point of interest, and the entity objects associated with the waybill and the entity objects associated with the point of interest, based on at least one of the description information of the waybill, the description information of the point of interest, and the description information of the entity objects associated with the waybill and the entity objects associated with the point of interest, through an association relationship network constructed based on the waybill, the point of interest, and the entity objects associated with the waybill and the entity objects associated with the point of interest, and determine whether the waybill and the point of interest meet the set association conditions based on the feature vectors; The association module is used to associate the waybill with the point of interest when the association conditions are met.

10. A computer-readable storage medium storing a computer program for performing the method of any one of claims 1-8.

Images