Methods, apparatus, equipment and media for determining the relevance of advertising text

Abstract

This disclosure provides a method, apparatus, device, and medium for determining the relevance of advertising text, relating to the field of artificial intelligence technology, and particularly to the field of natural language processing technology. The implementation scheme includes: obtaining first and second feature vector representations corresponding to first and second advertising texts respectively; and determining the relevance between the first and second advertising texts based on the first and second feature vector representations, wherein the feature vector representations of the advertising texts are obtained using the following determination process: obtaining historical advertising data; obtaining revenue information of the advertising texts; determining at least one associated text corresponding to each advertising text based on the co-occurrence relationship among the multiple advertising texts in the historical advertising data; and determining the feature vector representation of each advertising text based on the semantic and revenue information of each advertising text and its corresponding associated texts.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to the field of natural language processing, specifically to a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the relevance of advertising text. Background Technology

[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0003] In advertising and marketing scenarios, it's often necessary to proactively recommend ads to users, especially ads related to specific content. Therefore, the recommendation strategy needs to be determined based on the relevance of candidate content to that specific content.

[0004] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, computer-readable storage medium, and computer program product for determining the relevance of advertising text.

[0006] According to one aspect of this disclosure, a method for determining the relevance of advertising text is provided, comprising: obtaining a first feature vector representation corresponding to a first advertising text and a second feature vector representation corresponding to a second advertising text; and determining the relevance between the first advertising text and the second advertising text based on the first feature vector representation and the second feature vector representation, wherein the first feature vector representation and the second feature vector representation are obtained by the following determination process: obtaining historical advertising data containing multiple advertising texts, the multiple advertising texts including the first advertising text and the second advertising text; obtaining revenue information for each of the multiple advertising texts; for each of the multiple advertising texts, determining at least one associated text corresponding to the advertising text from at least one other advertising text besides the advertising text based on the co-occurrence relationship between the multiple advertising texts in the historical advertising data; and for each of the multiple advertising texts, determining a feature vector representation corresponding to the advertising text based on the semantic and revenue information of the advertising text and the semantic and revenue information corresponding to the at least one associated text.

[0007] According to another aspect of this disclosure, an advertising text recommendation method is also provided, comprising: acquiring a target advertising text and a plurality of candidate advertising texts; determining the relevance between the target advertising text and the plurality of candidate advertising texts using the aforementioned advertising text relevance determination method; and determining at least one advertising text to be recommended from the plurality of candidate advertising texts based on the relevance between the target advertising text and the plurality of candidate advertising texts.

[0008] According to another aspect of this disclosure, an apparatus for determining the relevance of advertising text is provided, comprising: a first acquisition unit configured to acquire a first feature vector representation corresponding to a first advertising text and a second feature vector representation corresponding to a second advertising text; and a first determination unit configured to determine the relevance between the first advertising text and the second advertising text based on the first feature vector representation and the second feature vector representation, wherein the first feature vector representation and the second feature vector representation are obtained using the feature vector determination unit, the feature vector determination unit comprising: a first acquisition subunit configured to acquire historical advertising data containing multiple advertising texts, the multiple advertising texts including the first feature vector representation and the second feature vector representation ... subunit configured to acquire historical advertising data containing multiple advertising texts, the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation; and a first determination subunit configured to acquire historical advertising data containing multiple advertising texts, the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation; and a first determination subunit configured to acquire historical advertising data containing multiple advertising texts, the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation; and a first determination subunit configured to acquire historical advertising data containing multiple advertising texts, the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation; and a first determination subunit configured to acquire historical advertising data containing multiple advertising texts, the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second feature vector representation being obtained using the first feature vector representation and the second The system comprises: a first advertising text and a second advertising text; a second acquisition subunit configured to acquire revenue information for each of the plurality of advertising texts; a first determination subunit configured to, for each of the plurality of advertising texts, determine at least one associated text corresponding to the advertising text from at least one other advertising text besides the advertising text, based on the co-occurrence relationship between the plurality of advertising texts in the historical advertising data; and a second determination subunit configured to, for each of the plurality of advertising texts, determine a feature vector representation corresponding to the advertising text based on the semantic and revenue information of the advertising text and the semantic and revenue information corresponding to the at least one associated text.

[0009] According to another aspect of this disclosure, an advertising text recommendation apparatus is also provided, comprising: a second acquisition unit configured to acquire a target advertising text and a plurality of candidate advertising texts; an advertising text relevance determination apparatus as described above configured to determine the relevance between the target advertising text and the plurality of candidate advertising texts; and a second determination unit configured to determine at least one advertising text to be recommended from the plurality of candidate advertising texts based on the relevance between the target advertising text and the plurality of candidate advertising texts.

[0010] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein said memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the above-described method for determining the relevance of advertising text.

[0011] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the aforementioned method for determining the relevance of advertising text.

[0012] According to another aspect of this disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, is capable of implementing the above-described method for determining the relevance of advertising text.

[0013] According to one or more embodiments of this disclosure, the relevance between advertising texts can be determined more accurately.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0016] Figure 1 A schematic diagram of an exemplary system in which various methods described herein may be implemented, according to exemplary embodiments of the present disclosure;

[0017] Figure 2 A flowchart illustrating the process of determining the feature vector representation of advertising text according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 3 A flowchart illustrating a method for determining the relevance of advertising text according to an exemplary embodiment of the present disclosure is shown;

[0019] Figure 4 A schematic diagram of a text image according to an exemplary embodiment of the present disclosure is shown;

[0020] Figure 5 A structural block diagram of the feature vector determination unit according to an exemplary embodiment of the present disclosure is shown;

[0021] Figure 6 A structural block diagram of an advertising text relevance determination apparatus according to an exemplary embodiment of the present disclosure is shown;

[0022] Figure 7 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0025] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0026] In related technologies, one approach is to determine relevance by utilizing the semantic similarity between advertising texts, or by leveraging the co-occurrence relationships between advertising texts in historical data. However, both methods have limited ability to express the relevance features between multiple advertising texts and fail to consider the revenue information corresponding to the advertising texts.

[0027] Based on this, this disclosure provides a method for determining the relevance of advertising text. It constructs a text graph by utilizing the co-occurrence relationship between multiple advertising texts in historical advertising data. By using the semantic and revenue information of each node in the text graph and its associated nodes, the feature vector representation of the advertising text corresponding to each node is determined. Then, the relevance between advertising texts is determined by using the feature vector representation. This method can further combine revenue information to determine the relevance between advertising texts based on the relationship between texts represented by the graph structure of the text graph, thereby improving accuracy.

[0028] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0029] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0030] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of a method for determining the relevance of advertising text.

[0031] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105, and / or 106 under a Software as a Service (SaaS) model.

[0032] exist Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0033] Users can use client devices 101, 102, 103, 104, 105, and / or 106 to send advertising text. The client devices can provide an interface that allows users to interact with the client devices. The client devices can also output information to users through this interface. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0034] Client devices 101, 102, 103, 104, 105, and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various categories and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices can run a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short message service (SMS) applications, and can use various communication protocols.

[0035] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0036] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0037] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0038] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0039] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0040] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different categories. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0041] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be different categories of databases, such as key-value stores, object stores, or regular stores supported by a file system.

[0042] Figure 1The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0043] Figure 2 A flowchart illustrating a process 200 for determining the feature vector representation of advertising text according to an exemplary embodiment of the present disclosure is shown. Figure 2 As shown, process 200 includes:

[0044] Step S201: Obtain historical advertising data containing multiple advertising texts, wherein the multiple advertising texts include the first advertising text and the second advertising text;

[0045] Step S202: Obtain the revenue information for each of the multiple advertising texts;

[0046] Step S203: For each of the plurality of advertising texts, based on the co-occurrence relationship among the plurality of advertising texts in the historical advertising data, determine at least one associated text corresponding to that advertising text from at least one other advertising text besides that advertising text; and

[0047] Step S204: For each of the plurality of advertising texts, based on the semantic and revenue information of the advertising text and the semantic and revenue information of at least one associated text, determine the feature vector representation corresponding to the advertising text.

[0048] Figure 3 A flowchart of an advertising text relevance determination method 300 according to an exemplary embodiment of the present disclosure is shown. Figure 3 As shown, method 300 includes:

[0049] Step S301: Obtain the first feature vector representation corresponding to the first advertisement text and the second feature vector representation corresponding to the second advertisement text, wherein the first feature vector representation and the second feature vector representation are obtained using process 200; and

[0050] Step S302: Determine the relevance between the first advertising text and the second advertising text based on the first feature vector representation and the second feature vector representation.

[0051] Therefore, based on the aforementioned determination process 200, the co-occurrence relationships among multiple advertising texts in historical advertising data can be used to determine the associated texts corresponding to each advertising text. Furthermore, based on the semantic and revenue information of each advertising text and its associated texts, a feature vector representation of each advertising text is determined. This allows the feature vector representation of the advertising text to more accurately characterize the relevance features of the advertising text to other advertising texts, while simultaneously representing the revenue information of the advertising text. Further, by utilizing the aforementioned feature vector representation to determine the relevance between advertising texts, the accuracy is improved by combining revenue information with the co-occurrence relationships indicating the relevance between advertising texts.

[0052] In some examples, the advertising text may be, for example, the name of an advertisement recommended to a user, or the name of a product actively queried by the user, as long as it can represent the relevant information of the target audience of the advertisement. This disclosure does not limit this.

[0053] In some examples, when the ad text is the name of an ad recommended to a user, the revenue information of the ad text can be determined based on the cost of that ad. It should be understood that the revenue information of the ad text can also include other content, such as revenue information corresponding to the marketing target represented by the ad text, such as product sales, page views, video views, etc., and this disclosure does not impose any limitations on this.

[0054] In some examples, determining the relevance between the first and second advertising texts based on the first and second feature vector representations in step S302 may include: determining the relevance between the first and second advertising texts based on the similarity between the first and second feature vector representations. The similarity may be determined, for example, by calculating the Euclidean distance between the first and second feature vector representations, or by calculating indices such as cosine similarity or Manhattan distance.

[0055] In some examples, after determining the feature vector representations of multiple advertising texts using process 200, the multiple advertising texts and their corresponding feature vector representations can be stored in a database. This allows the database to be queried in step S301 based on the first and second advertising texts, thereby improving the efficiency of determining the relevance of the advertising texts.

[0056] According to some embodiments, step S203, for each of the plurality of advertising texts, determining at least one associated text corresponding to that advertising text from at least one other advertising text besides that advertising text based on the co-occurrence relationship between the plurality of advertising texts in the historical advertising data, includes: constructing a text graph containing a plurality of nodes corresponding one-to-one with the plurality of advertising texts based on the co-occurrence relationship between the plurality of advertising texts in the historical advertising data, wherein, for any two advertising texts of the plurality of texts, in response to determining that the co-occurrence relationship between the two advertising texts satisfies a preset condition, establishing a connection edge based on the nodes corresponding to the two advertising texts; and for each of the plurality of nodes, determining at least one associated node corresponding to that node from at least one other node based on the connection relationship between the plurality of nodes, so as to obtain at least one associated text corresponding to the corresponding advertising text.

[0057] Therefore, based on the aforementioned determination process 200, a text graph can be constructed using the co-occurrence relationships among multiple advertising texts in historical advertising data. By utilizing the semantic and revenue information of each node in the text graph and its associated nodes, the feature vector representation of the advertising text corresponding to each node can be determined. This allows the feature vector representation of the advertising text to more accurately characterize the relevance features of the advertising text to other advertising texts, while simultaneously representing the revenue information of the advertising text. Furthermore, by using the aforementioned feature vector representation to determine the relevance between advertising texts, the accuracy can be improved by combining revenue information with the text graph structure representing the relationships between texts.

[0058] According to some embodiments, step 204, for each of the plurality of advertising texts, determines the feature vector representation of the advertising text based on its semantic and revenue information, and the semantic and revenue information of at least one corresponding associated text. This includes: for each of the at least one connecting edge between the node corresponding to the advertising text and the at least one corresponding associated node, determining the edge vector representation of the connecting edge based on the semantic and revenue information of the advertising texts corresponding to the two endpoints of the connecting edge; and determining the feature vector representation of the advertising text based on the edge vector representation of the at least one connecting edge. Therefore, the edge vector representation can be used to characterize the relevance features of the advertising texts corresponding to the two endpoints of each edge, and then the multiple edge vectors between each node and its associated nodes can be aggregated to obtain a more accurate feature vector representation of the text corresponding to each node.

[0059] In some examples, determining the feature vector representation of the advertising text corresponding to the node based on the edge vector representation of the at least one connected edge may include: calculating the average value of the edge vector representations of the at least one connected edge to obtain the feature vector representation of the advertising text corresponding to the node. This step can also be performed using other methods, such as calculating based on the edge vector representation of the at least one connected edge and a preset formula to obtain the feature vector representation of the advertising text corresponding to the node.

[0060] According to some embodiments, determining the edge vector representation of the connecting edge based on the semantic and revenue information of the advertising texts corresponding to the two endpoints of the connecting edge includes: determining the semantic similarity between the advertising texts corresponding to the two endpoints; and determining the edge vector representation of the connecting edge based on the semantic similarity and the revenue information of the advertising texts corresponding to the two endpoints. Therefore, semantic similarity can be used to characterize the relevance between the advertising texts corresponding to the two endpoints, which is more convenient and accurate.

[0061] In some examples, the semantic feature vector representations of the advertising text corresponding to the two endpoints can be determined, and then the semantic similarity can be determined based on the similarity between the two semantic feature vector representations. The semantic feature vector representation can be implemented, for example, by inputting the advertising text into a language model, or by querying a database that stores multiple texts and their corresponding semantic feature vectors; this disclosure does not limit this.

[0062] According to some embodiments, determining the semantic similarity between the advertising texts corresponding to the two endpoints includes: inputting the advertising texts corresponding to the two endpoints of the connecting edge into a pre-trained language model to obtain the semantic similarity output by the pre-trained language model, wherein the pre-trained language model is trained using labeled corpus data. Therefore, the semantic similarity between two advertising texts can be obtained using a pre-trained language model, improving efficiency and accuracy.

[0063] In some examples, the pre-trained language model may be, for example, the Ernie model.

[0064] According to some embodiments, the determination process 200 further includes: for each of at least one connection edge between a node corresponding to the advertising text and at least one associated node, determining the co-occurrence frequency between the advertising texts corresponding to the two endpoints of the connection edge, and wherein the edge vector representation of the connection edge is determined based on the semantic and revenue information of the advertising texts corresponding to the two endpoints of the connection edge and the co-occurrence frequency. Thus, by combining the co-occurrence frequencies of the advertising texts corresponding to the two endpoints, the correlation between them can be indicated more accurately.

[0065] In some examples, the co-occurrence frequency can be the number of co-occurrences, cnt. Therefore, the fusion information S of the number of co-occurrences, cnt, and the revenue information, acp, can be determined based on the following formula:

[0066] S = a*cnt + b*acp

[0067] In this example, 'a' and 'b' in the formula can be weight values ​​set according to actual needs.

[0068] According to some embodiments, the determination process 200 further includes: performing normalization processing on the co-occurrence frequency and the revenue information respectively to obtain normalized co-occurrence frequency and normalized revenue information, wherein, based on the semantics of the advertising text corresponding to the two endpoints of the connecting edge, the normalized revenue information, and the normalized co-occurrence frequency, the edge vector representation of the connecting edge is determined. This allows the numerical range of the co-occurrence frequency and revenue information to be scaled to the same interval, simplifying the calculation process and obtaining a more accurate edge vector representation.

[0069] In some examples, normalization can be performed using the following formula:

[0070]

[0071] In the formula, x represents the initial revenue information or co-occurrence frequency. min x represents the minimum value of revenue information or co-occurrence frequency across all data. max X' represents the maximum value of the revenue information or co-occurrence frequency in all data, and X′ represents the normalized revenue information or normalized co-occurrence frequency.

[0072] According to some embodiments, determining the edge vector representation of the connection edge based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connection edge includes: inputting the advertising text corresponding to the two endpoints of the connection edge and its revenue information into an edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model, wherein the edge vector encoding model is trained in the following manner: obtaining a sample text graph containing multiple nodes corresponding one-to-one with multiple sample texts and revenue information of each sample text in the multiple sample texts, wherein the sample text graph includes multiple connection edges for connecting the multiple nodes; for each connection edge included in the sample text graph, The sample texts and their reward information corresponding to the two endpoints of the connecting edges are input into the edge vector encoding model to obtain the edge vector representation of the connecting plate output by the edge vector encoding model. Based on the edge vector representations of the multiple connecting edges, the feature vector representations of the multiple sample texts corresponding to the multiple nodes are determined. The true relevance between the first sample text and the second sample text among the multiple sample texts is obtained. Based on the first feature vector representation and the second feature vector representation corresponding to the first sample text and the second sample text respectively, the predicted relevance between the first sample text and the second sample text is determined. And based on the true relevance and the predicted relevance, the parameters of the edge vector encoding model are adjusted. Thus, the edge vector representation can be obtained using the edge vector encoding model, and the relevance prediction task between texts can be performed using the edge vector representation output by the edge vector encoding model. Based on this, model training can be performed, improving efficiency and accuracy.

[0073] In some examples, the co-occurrence frequencies of the advertising texts corresponding to the two endpoints of the connecting edge can also be input into the edge vector encoding model. For example, the fusion information S described above can be input into the edge vector encoding model to obtain an edge vector representation that can more accurately characterize the relevance features between the two advertising texts.

[0074] According to some embodiments, the plurality of advertising texts includes a plurality of historical query texts and a plurality of historical recommendation texts. The historical advertising data includes a plurality of text pairs, each of which includes a historical query text and a historical recommendation text recommended to the user based on the historical query text. Furthermore, the step of constructing edges of a text graph with the nodes corresponding to the two advertising texts as vertices in response to determining that the historical advertising data includes text pairs composed of the two advertising texts includes constructing edges of a text graph with the nodes corresponding to the two advertising texts as vertices. Thus, the correlation represented by the mapping relationship between historical query texts and historical recommendation texts in the historical advertising data can be fully utilized, and the edges of the text graph can be constructed based on this, so that the edges in the text graph can accurately indicate the correlation between two endpoint nodes.

[0075] In some examples, the co-occurrence frequency between two ad texts can be determined based on the frequency of each text pair in historical ad data.

[0076] According to some embodiments, determining at least one associated node from a plurality of other nodes for each node in the text graph, based on the connection relationships between the plurality of nodes, includes: for each of the plurality of other nodes, determining that other node is the associated node in response to the connection hop count between the other node and the node not exceeding a preset threshold. This allows other nodes closer to the node to be identified as associated nodes, avoiding the influence of distant nodes on the feature vector representation of the node's advertising text, and improving accuracy.

[0077] According to some embodiments, determining at least one associated node corresponding to each node in the text graph based on the connection relationships between the plurality of nodes includes: determining the sampling probability of each of the plurality of other nodes based on the connection relationships between the plurality of nodes and a preset rule, wherein, according to the preset rule, the sampling probability of a node with a smaller connection hop count to the node is greater than the sampling probability of a node with a larger connection hop count to the node; and randomly sampling the plurality of other nodes based on the sampling probabilities to obtain the at least one associated node. Thus, hierarchical random sampling can be used to obtain the associated node corresponding to each node, with nodes that are closer in distance having a higher sampling probability, reducing the number of associated nodes, simplifying the vector calculation process, and ensuring accuracy.

[0078] Figure 4A schematic diagram of a text graph according to an exemplary embodiment of the present disclosure is shown. In this example, for a central node a, sampling can be performed on its two adjacent neighboring nodes. Specifically, nodes b, c, and d with a hop count of one are first-layer nodes, and nodes e, f, and g with a hop count of two are second-layer nodes. The sampling frequency corresponding to each layer of nodes can decrease as the number of layers increases, for example, the sampling frequency corresponding to each layer of nodes can be determined based on an exponential decay function.

[0079] In this example, by utilizing the steps described above, the edge vector representations of edges ab, ac, ad, be, df, and dg can be obtained respectively. Therefore, aggregation can be performed on nodes at each layer, that is, the feature vector representation of a node at that layer can be determined based on the edge vector representation of the connection between a node at that layer and a node at the next layer, and the feature vector representation of the node at the next layer. For example, the feature vector representation of node d can be determined based on the edge vector representations of edges df and dg, and the feature vector representation of the advertisement text corresponding to node a can be determined based on the edge vector representations of edges ab, ac, and ad, and the feature vector representations of nodes b, c, and d.

[0080] According to another aspect of this disclosure, an advertising text recommendation method is also provided, comprising: acquiring a target advertising text and a plurality of candidate advertising texts; determining the relevance between the target advertising text and the plurality of candidate advertising texts using the aforementioned advertising text relevance determination method; and determining at least one advertising text to be recommended from the plurality of candidate advertising texts based on the relevance between the target advertising text and the plurality of candidate advertising texts.

[0081] In some examples, the candidate ad texts may be sorted based on the relevance between the target ad text and the candidate ad texts, and at least one ad text to be recommended may be determined based on the sorting results.

[0082] According to another aspect of this disclosure, an apparatus for determining the relevance of advertising text is also provided. Figure 5 A structural block diagram of a feature vector determination unit 500 according to an exemplary embodiment of the present disclosure is shown. Figure 6 A structural block diagram of an advertising text relevance determination apparatus 600 according to an exemplary embodiment of the present disclosure is shown.

[0083] like Figure 5 As shown, the feature vector determination unit 500 includes:

[0084] The first acquisition subunit 501 is configured to acquire historical advertising data containing multiple advertising texts, the multiple advertising texts including the first advertising text and the second advertising text;

[0085] The second acquisition subunit 502 is configured to acquire revenue information for each of the plurality of advertising texts;

[0086] The first determining subunit 503 is configured to, for each of the plurality of advertising texts, determine at least one associated text corresponding to the advertising text from at least one other advertising text besides the advertising text, based on the co-occurrence relationship between the plurality of advertising texts in the historical advertising data; and

[0087] The second determining subunit 504 is configured to, for each of the plurality of advertising texts, determine a feature vector representation corresponding to the advertising text based on the semantic and revenue information of the advertising text and the semantic and revenue information of at least one associated text.

[0088] The operations of units 501-504 of unit 500 are similar to the operations of steps S201-S204 described above, and will not be repeated here.

[0089] like Figure 6 As shown, the advertising text relevance determination device 600 includes:

[0090] The first acquisition unit 601 is configured to represent a first feature vector corresponding to the first advertisement text and a second feature vector corresponding to the second advertisement text; and

[0091] The first determining unit 602 is configured to determine the relevance between the first advertising text and the second advertising text based on the first feature vector representation and the second feature vector representation, wherein the first feature vector representation and the second feature vector representation are obtained using unit 200.

[0092] The operation of units 601-602 of device 600 is similar to the operation of steps S301-S302 described above, and will not be repeated here.

[0093] According to some embodiments, the first determining subunit includes: a construction module configured to construct a text graph containing multiple nodes corresponding one-to-one with the multiple advertising texts based on the co-occurrence relationship between the multiple advertising texts in the historical advertising data, wherein, for any two advertising texts of the multiple texts, in response to determining that the co-occurrence relationship between the two advertising texts satisfies a preset condition, a connection edge is established based on the nodes corresponding to the two advertising texts; and a first determining module configured to, for each of the multiple nodes, determine at least one associated node corresponding to that node from at least one other node based on the connection relationship between the multiple nodes, so as to obtain at least one associated text corresponding to the corresponding advertising text.

[0094] According to some embodiments, the second determining subunit includes: a second determining module configured to determine the edge vector representation of each connecting edge between a node corresponding to the advertising text and at least one associated node, based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connecting edge; and a third determining module configured to determine the feature vector representation of the advertising text based on the edge vector representation of the at least one connecting edge.

[0095] According to some embodiments, the second determining module is configured to: determine the semantic similarity between the advertising texts corresponding to the two endpoints respectively; and determine the edge vector representation of the connection edge based on the semantic similarity and the revenue information of the advertising texts corresponding to the two endpoints respectively.

[0096] According to some embodiments, the second determining module is configured to: input the advertising text corresponding to the two endpoints of the connection edge into a pre-trained language model to obtain the semantic similarity output by the pre-trained language model, wherein the pre-trained language model is trained using labeled corpus data.

[0097] According to some embodiments, the feature vector determination unit further includes: a third determination subunit, configured to determine the co-occurrence frequency between the advertising texts corresponding to the two endpoints of each connection edge between the node corresponding to the advertising text and the corresponding at least one associated node, and wherein the second determination module is configured to determine the edge vector representation of the connection edge based on the semantic and revenue information of the advertising texts corresponding to the two endpoints of the connection edge and the co-occurrence frequency.

[0098] According to some embodiments, the feature vector determination unit further includes: a processing subunit configured to perform normalization processing on the co-occurrence frequency and the revenue information respectively to obtain normalized co-occurrence frequency and normalized revenue information, wherein the first determination module is configured to determine the edge vector representation of the connection edge based on the semantics of the advertising text corresponding to the two endpoints of the connection edge, the normalized revenue information, and the normalized co-occurrence frequency.

[0099] According to some embodiments, the second determining module is configured to: input the advertising texts and their revenue information corresponding to the two endpoints of the connecting edge into an edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model, wherein the edge vector encoding model is trained in the following manner: obtaining a sample text graph containing multiple nodes corresponding one-to-one with multiple sample texts and revenue information of each sample text in the multiple sample texts, wherein the sample text graph includes multiple connecting edges for connecting the multiple nodes; for each connecting edge included in the multiple connecting edges in the sample text graph, input the advertising texts and their revenue information corresponding to the two endpoints of the connecting edge into an edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model, wherein the edge vector encoding model is trained in the following manner: obtaining a sample text graph containing multiple nodes corresponding one-to-one with multiple sample texts and revenue information of each sample text in the multiple sample texts, wherein the sample text graph includes multiple connecting edges for connecting the multiple nodes; and inputting the advertising texts and their revenue information corresponding to the two endpoints of the connecting edge into an edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model. The text and its revenue information are input into the edge vector encoding model to obtain the edge vector representation of the connecting board output by the edge vector encoding model; based on the edge vector representation of the multiple connecting edges, the feature vector representation of multiple sample texts corresponding to the multiple nodes is determined; the true relevance between the first sample text and the second sample text in the multiple sample texts is obtained; based on the first feature vector representation and the second feature vector representation corresponding to the first sample text and the second sample text respectively, the predicted relevance between the first sample text and the second sample text is determined; and based on the true relevance and the predicted relevance, the parameters of the edge vector encoding model are adjusted.

[0100] According to some embodiments, the plurality of advertising texts includes a plurality of historical query texts and a plurality of historical recommendation texts, the historical advertising data includes a plurality of text pairs, each of the plurality of text pairs including a historical query text and a historical recommendation text recommended to the user based on the historical query text, and wherein the construction module is configured to: in response to determining that the historical advertising data includes a text pair consisting of the two advertising texts, construct an edge of a text graph with the nodes corresponding to the two advertising texts as vertices.

[0101] According to some embodiments, the first determining module is configured to: for each of the plurality of other nodes, in response to the connection hop count between the other node and the node not being greater than a preset threshold, determine the other node as the associated node.

[0102] According to some embodiments, the first determining module is configured to: determine the sampling probability of each of the plurality of other nodes based on the connection relationship between the plurality of nodes and a preset rule, wherein, according to the preset rule, the sampling probability of a node with a smaller connection hop number to the node is greater than the sampling probability of a node with a larger connection hop number to the node; and randomly sample the plurality of other nodes based on the sampling probability to obtain the at least one associated node.

[0103] According to another aspect of this disclosure, an advertising text recommendation apparatus is also provided, comprising: a second acquisition unit configured to acquire a target advertising text and a plurality of candidate advertising texts; an advertising text relevance determination apparatus as described above configured to determine the relevance between the target advertising text and the plurality of candidate advertising texts; and a second determination unit configured to determine at least one advertising text to be recommended from the plurality of candidate advertising texts based on the relevance between the target advertising text and the plurality of candidate advertising texts.

[0104] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described method for determining the relevance of advertising text.

[0105] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the above-described method for determining the relevance of advertising text.

[0106] According to another aspect of this disclosure, a computer program product is also provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the above-described method for determining the relevance of advertising text.

[0107] refer to Figure 7 The present invention describes a structural block diagram of an electronic device 700 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0108] like Figure 7As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0109] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, output unit 707, storage unit 708, and communication unit 709. Input unit 706 can be any type of device capable of inputting information to device 700. Input unit 706 can receive input numerical or character information and generate key signal inputs related to user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 707 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 708 may include, but is not limited to, a hard disk and an optical disk. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0110] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the advertising text relevance determination method. For example, in some embodiments, the advertising text relevance determination method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by computing unit 701, one or more steps of the advertising text relevance determination method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the advertising text relevance determination method by any other suitable means (e.g., by means of firmware).

[0111] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] 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.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0115] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0116] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0117] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0118] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A method for determining the relevance of advertising text, comprising: Obtain the first feature vector representation corresponding to the first advertisement text and the second feature vector representation corresponding to the second advertisement text; as well as Based on the first feature vector representation and the second feature vector representation, the relevance between the first advertising text and the second advertising text is determined. The first feature vector representation and the second feature vector representation are obtained using the following determination process: Obtain historical advertising data containing multiple advertising texts, wherein the multiple advertising texts include the first advertising text and the second advertising text; Obtain the revenue information for each of the multiple advertising texts; For each of the plurality of advertising texts, based on the co-occurrence relationships among the plurality of advertising texts in the historical advertising data, at least one associated text corresponding to that advertising text is determined from at least one other advertising text besides that advertising text; and For each of the plurality of advertising texts, based on the semantic and revenue information of that advertising text and the semantic and revenue information of at least one corresponding associated text, a feature vector representation corresponding to that advertising text is determined, including: Determine the semantic similarity between each of the at least one associated texts and the advertising text; and Based on the semantic similarity of each of the at least one associated text and the revenue information of each of the at least one associated text, a feature vector representation corresponding to the advertisement text is determined.

2. The method of claim 1, wherein, The step of determining at least one associated text corresponding to each of the plurality of advertising texts, based on the co-occurrence relationship among the plurality of advertising texts in the historical advertising data, from at least one other advertising text besides the advertising text includes: Based on the co-occurrence relationships among the multiple advertising texts in the historical advertising data, a text graph is constructed containing multiple nodes that correspond one-to-one with each of the multiple advertising texts. Specifically, for any two advertising texts among the multiple texts, in response to determining that the co-occurrence relationship between the two advertising texts satisfies a preset condition, a connection edge is established based on the nodes corresponding to the two advertising texts; and For each of the plurality of nodes, based on the connection relationship between the plurality of nodes, at least one associated node corresponding to that node is determined from at least one other node to obtain at least one associated text corresponding to the corresponding advertising text.

3. The method of claim 2, wherein, The step of determining the feature vector representation of each of the plurality of advertising texts, based on the semantic and revenue information of that advertising text and the semantic and revenue information of at least one corresponding associated text, includes: For each of the at least one connecting edges between the node corresponding to the advertisement text and at least one associated node, the edge vector representation of the connecting edge is determined based on the semantic and revenue information of the advertisement text corresponding to the two endpoints of the connecting edge; and The feature vector representation of the advertising text is determined based on the edge vector representation of the at least one connected edge.

4. The method of claim 3, wherein, The step of determining the edge vector representation of the connection edge based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connection edge includes: Determine the semantic similarity between the advertising texts corresponding to the two endpoints; and Based on the semantic similarity and the revenue information of the advertising texts corresponding to the two endpoints, the edge vector representation of the connection edge is determined.

5. The method of claim 4, wherein, Determining the semantic similarity between the advertising texts corresponding to the two endpoints includes: The advertising text corresponding to the two endpoints of the connection edge is input into a pre-trained language model to obtain the semantic similarity output by the pre-trained language model, wherein the pre-trained language model is trained using labeled corpus data.

6. The method according to any one of claims 3-5, wherein, The determination process also includes: For each connection edge between the node corresponding to the advertisement text and at least one associated node, determine the co-occurrence frequency between the advertisement texts corresponding to the two endpoints of the connection edge. Furthermore, the edge vector representation of the connection edge is determined based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connection edge, as well as the co-occurrence frequency.

7. The method of claim 6, wherein, The determination process also includes: The co-occurrence frequency and the revenue information are respectively normalized to obtain normalized co-occurrence frequency and normalized revenue information. Furthermore, the edge vector representation of the connection edge is determined based on the semantics and normalized revenue information of the advertising texts corresponding to the two endpoints of the connection edge, as well as the normalized co-occurrence frequency.

8. The method of claim 3, wherein, The step of determining the edge vector representation of the connection edge based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connection edge includes: The advertising text and its revenue information corresponding to the two endpoints of the connecting edge are input into the edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model. The edge vector encoding model is trained using the following method: Obtain a sample text graph containing multiple nodes that correspond one-to-one with multiple sample texts and the revenue information of each sample text in the multiple sample texts. The sample text graph includes multiple connection edges for connecting the multiple nodes. For each of the multiple connecting edges included in the sample text graph, the sample text and its revenue information corresponding to the two endpoints of the connecting edge are respectively input into the edge vector encoding model to obtain the edge vector representation of the connecting edge output by the edge vector encoding model; Based on the edge vector representations of the multiple connected edges, the feature vector representations of the multiple sample texts corresponding to the multiple nodes are determined; Obtain the true correlation between the first and second sample texts from the plurality of sample texts; Based on the first feature vector representation and the second feature vector representation corresponding to the first sample text and the second sample text, respectively, the predicted relevance between the first sample text and the second sample text is determined; and The parameters of the side vector encoding model are adjusted based on the true relevance and the predicted relevance.

9. The method of claim 2, wherein, The multiple advertising texts include multiple historical query texts and multiple historical recommendation texts. The historical advertising data includes multiple text pairs, and each text pair includes a historical query text and historical recommendation texts recommended to the user based on the historical query text. Furthermore, the step of establishing edges in a text graph with the nodes corresponding to the two advertising texts as vertices, in response to determining that the co-occurrence relationship between the two advertising texts satisfies a preset condition, includes: In response to determining that the historical advertising data includes a text pair consisting of the two advertising texts, an edge graph is constructed with the nodes corresponding to the two advertising texts as vertices.

10. The method of claim 2, wherein, For each node in the text graph, determining at least one associated node corresponding to that node from a plurality of other nodes based on the connection relationships between the plurality of nodes includes: For each of the plurality of other nodes, in response to the fact that the number of connection hops between the other node and the node is not greater than a preset threshold, the other node is determined to be the associated node.

11. The method of claim 2, wherein, For each node in the text graph, determining at least one associated node corresponding to that node from a plurality of other nodes based on the connection relationships between the plurality of nodes includes: Based on the connection relationships between the plurality of nodes and preset rules, the sampling probability of each of the plurality of other nodes is determined, wherein, according to the preset rules, the sampling probability of a node with a smaller connection hop count to the node being described is greater than the sampling probability of a node with a larger connection hop count to the node being described; and Based on the sampling probability, random sampling is performed on the plurality of other nodes to obtain the at least one associated node.

12. An advertising text recommendation method, comprising: Retrieve the target ad text and multiple candidate ad texts; Using the method of any one of claims 1-11, determine the relevance between the target advertising text and the plurality of candidate advertising texts; as well as Based on the relevance between the target ad text and the plurality of candidate ad texts, at least one ad text to be recommended is determined from the plurality of candidate ad texts.

13. A device for determining the relevance of advertising text, comprising: The first acquisition unit is configured to acquire a first feature vector representation corresponding to the first advertising text and a second feature vector representation corresponding to the second advertising text; as well as The first determining unit is configured to determine the relevance between the first advertising text and the second advertising text based on the first feature vector representation and the second feature vector representation. The first feature vector representation and the second feature vector representation are obtained using a feature vector determination unit, which includes: The first acquisition subunit is configured to acquire historical advertising data containing multiple advertising texts, the multiple advertising texts including the first advertising text and the second advertising text; The second acquisition subunit is configured to acquire revenue information for each of the plurality of advertising texts; A first determining subunit is configured to, for each of the plurality of advertising texts, determine at least one associated text corresponding to the advertising text from at least one other advertising text besides the advertising text, based on the co-occurrence relationship between the plurality of advertising texts in the historical advertising data; and The second determining subunit is configured to, for each of the plurality of advertising texts, determine a feature vector representation corresponding to that advertising text based on the semantic and revenue information of that advertising text and the semantic and revenue information of at least one associated text. The second determining subunit is further configured to: Determine the semantic similarity between each of the at least one associated texts and the advertising text; and Based on the semantic similarity of each of the at least one associated text and the revenue information of each of the at least one associated text, a feature vector representation corresponding to the advertisement text is determined.

14. The apparatus of claim 13, wherein, The first determining subunit includes: The construction module is configured to construct a text graph containing multiple nodes corresponding one-to-one with the multiple advertising texts based on the co-occurrence relationships among the multiple advertising texts in the historical advertising data. Specifically, for any two advertising texts among the multiple texts, in response to determining that the co-occurrence relationship between the two advertising texts satisfies a preset condition, a connection edge is established based on the nodes corresponding to the two advertising texts; and The first determining module is configured to, for each of the plurality of nodes, determine at least one associated node corresponding to that node from at least one other node based on the connection relationship between the plurality of nodes, so as to obtain at least one associated text corresponding to the corresponding advertising text.

15. The apparatus of claim 14, wherein, The second determining subunit includes: The second determining module is configured to, for each of at least one connecting edge between the node corresponding to the advertising text and at least one associated node, determine the edge vector representation of the connecting edge based on the semantic and revenue information of the advertising text corresponding to the two endpoints of the connecting edge; and The third determining module is configured to determine the feature vector representation of the advertising text based on the edge vector representation of the at least one connecting edge.

16. The apparatus of claim 15, wherein, The second determining module is configured as follows: Determine the semantic similarity between the advertising texts corresponding to the two endpoints; and Based on the semantic similarity and the revenue information of the advertising texts corresponding to the two endpoints, the edge vector representation of the connection edge is determined.

17. The apparatus of claim 16, wherein, The second determining module is configured as follows: The advertising text corresponding to the two endpoints of the connection edge is input into a pre-trained language model to obtain the semantic similarity output by the pre-trained language model, wherein the pre-trained language model is trained using labeled corpus data.

18. The apparatus according to any one of claims 15-17, wherein, The feature vector determination unit further includes: The third determining subunit is configured to determine, for each of at least one connection edge between the node corresponding to the advertisement text and at least one associated node, the co-occurrence frequency between the advertisement texts corresponding to the two endpoints of the connection edge. Furthermore, the second determining module is configured to determine the edge vector representation of the connecting edge based on the semantic and revenue information of the advertising texts corresponding to the two endpoints of the connecting edge, as well as the co-occurrence frequency.

19. The apparatus of claim 18, wherein, The feature vector determination unit further includes: The processing subunit is configured to perform normalization processing on the co-occurrence frequency and the revenue information respectively, to obtain normalized co-occurrence frequency and normalized revenue information. Furthermore, the first determining module is configured to determine the edge vector representation of the connecting edge based on the semantics and normalized revenue information of the advertising texts corresponding to the two endpoints of the connecting edge, as well as the normalized co-occurrence frequency.

20. The apparatus of claim 15, wherein, The second determining module is configured as follows: The advertising text and its revenue information corresponding to the two endpoints of the connecting edge are input into the edge vector encoding model to obtain the edge vector representation output by the edge vector encoding model. The edge vector encoding model is trained using the following method: Obtain a sample text graph containing multiple nodes that correspond one-to-one with multiple sample texts and the revenue information of each sample text in the multiple sample texts. The sample text graph includes multiple connection edges for connecting the multiple nodes. For each of the multiple connecting edges included in the sample text graph, the sample text and its revenue information corresponding to the two endpoints of the connecting edge are respectively input into the edge vector encoding model to obtain the edge vector representation of the connecting edge output by the edge vector encoding model; Based on the edge vector representations of the multiple connected edges, the feature vector representations of the multiple sample texts corresponding to the multiple nodes are determined; Obtain the true correlation between the first and second sample texts from the plurality of sample texts; Based on the first feature vector representation and the second feature vector representation corresponding to the first sample text and the second sample text, respectively, the predicted relevance between the first sample text and the second sample text is determined; and The parameters of the side vector encoding model are adjusted based on the true relevance and the predicted relevance.

21. The apparatus of claim 14, wherein, The multiple advertising texts include multiple historical query texts and multiple historical recommendation texts. The historical advertising data includes multiple text pairs, and each text pair includes a historical query text and historical recommendation texts recommended to the user based on the historical query text. Furthermore, the building module is configured as follows: In response to determining that the historical advertising data includes a text pair consisting of the two advertising texts, an edge graph is constructed with the nodes corresponding to the two advertising texts as vertices.

22. The apparatus of claim 14, wherein, The first determining module is configured as follows: For each of the plurality of other nodes, in response to the fact that the number of connection hops between the other node and the node is not greater than a preset threshold, the other node is determined to be the associated node.

23. The apparatus of claim 14, wherein, The first determining module is configured as follows: Based on the connection relationships between the plurality of nodes and preset rules, the sampling probability of each of the plurality of other nodes is determined, wherein, according to the preset rules, the sampling probability of a node with a smaller connection hop count to the node being described is greater than the sampling probability of a node with a larger connection hop count to the node being described; and Based on the sampling probability, random sampling is performed on the plurality of other nodes to obtain the at least one associated node.

24. An advertising text recommendation device, comprising: The second acquisition unit is configured to acquire the target ad text and multiple candidate ad texts. ； The apparatus of any one of claims 13-23 is configured to determine the relevance between the target advertising text and the plurality of candidate advertising texts; as well as The second determining unit is configured to determine at least one advertisement text to be recommended from the plurality of candidate advertisement texts based on the relevance between the target advertisement text and the plurality of candidate advertisement texts.

25. An electronic device, comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.

26. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-12.

27. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method according to any one of claims 1-12.

Images