Data determination method, apparatus, and computer program product

Abstract

The present disclosure provides a data determination method and device, electronic equipment, storage medium and computer program product, relates to the technical field of artificial intelligence, in particular to the technical field of large models, data recommendation, natural language understanding, and can be applied to a data recommendation scene. The specific implementation scheme is as follows: determining a geographical position corresponding to a target user; generating an interest tree representing interest information of the target user through a large language model according to user data of the target user; and determining to-be-recommended data related to the geographical position through a pre-trained data recommendation model according to the interest tree. The present disclosure improves the accuracy of the to-be-recommended data based on the interest tree generated by the large language model and the geographical position corresponding to the target user.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to the fields of large models, data recommendation, and natural language understanding, and particularly to a data determination method, device, electronic device, storage medium, and computer program product that can be applied to data recommendation scenarios. Background Technology

[0002] Data-driven recommendation systems can predict and push personalized content or services to users, and are widely used in e-commerce, social media, video platforms, and other fields to improve user experience and enhance user engagement. Currently, the accuracy of recommendation data for users is insufficient. Summary of the Invention

[0003] This disclosure provides a data determination method, apparatus, electronic device, storage medium, and computer program product.

[0004] According to the first aspect, a data determination method is provided, including: determining the geographical location corresponding to the target user; generating an interest tree representing the target user's interest information based on the user data of the target user through a large language model; and determining the data to be recommended related to the geographical location based on the interest tree through a pre-trained data recommendation model.

[0005] According to the second aspect, a data determination apparatus is provided, comprising: a location determination unit configured to determine the geographical location corresponding to a target user; an interest tree generation unit configured to generate an interest tree representing the target user's interest information based on the target user's user data using a large language model; and a data determination unit configured to determine data to be recommended related to the geographical location based on the interest tree using a pre-trained data recommendation model.

[0006] According to a third aspect, an electronic device is 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 a method as described in any implementation of the first aspect.

[0007] According to a fourth aspect, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing a computer to perform the method described in any implementation of the first aspect.

[0008] According to a fifth aspect, a computer program product is provided, comprising: a computer program that, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0009] 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

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This is an exemplary system architecture diagram that can be applied to an embodiment of this disclosure;

[0012] Figure 2 This is a flowchart of one embodiment of the data determination method according to this disclosure;

[0013] Figure 3 This is a schematic diagram of the control shown in the overview of this embodiment;

[0014] Figure 4 This is a schematic diagram of the details display interface under the animation display method of this embodiment;

[0015] Figure 5 This is a schematic diagram of the detailed display interface of the route recommendation data according to this embodiment;

[0016] Figure 6 This is a schematic diagram illustrating an application scenario of the data determination method according to this embodiment;

[0017] Figure 7 This is a flowchart of yet another embodiment of the data determination method based on this disclosure;

[0018] Figure 8 This is a structural diagram of one embodiment of the data determination device based on this disclosure;

[0019] Figure 9 This is a schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure. Detailed Implementation

[0020] 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 and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0022] Figure 1 An exemplary architecture 100 is shown for which the data determination method and apparatus of this disclosure can be applied.

[0023] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The communication connections between terminal devices 101, 102, and 103 form a network topology. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0024] Terminal devices 101, 102, and 103 can be hardware or software that supports network connectivity for data interaction and processing. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices that support network connectivity, information acquisition, interaction, display, and processing functions, including but not limited to smartphones, tablets, e-book readers, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices. They can be implemented as, for example, multiple software programs or software modules to provide distributed services, or as a single software program or software module. No specific limitations are imposed here.

[0025] Server 105 can be a server that provides various services, such as a backend processing server that acquires user data of target users based on terminal devices 101, 102, and 103, generates an interest tree through a large language model, and determines the data to be recommended based on the interest tree and the geographical location corresponding to the target user. As an example, server 105 can be a cloud server.

[0026] It should be noted that a server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules (such as software programs or software modules used to provide distributed services), or as a single software program or software module. No specific limitations are made here.

[0027] It should also be noted that the data determination method provided in the embodiments of this disclosure is generally executed by a server, but the possibility of it being executed by a terminal device, or by a server and a terminal device cooperating with each other, is not excluded. Accordingly, all parts (e.g., units) of the data determination device can be located entirely in the server, entirely in the terminal device, or separately in the server and the terminal device.

[0028] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included. When the electronic devices on which the data determination method runs do not need to transmit data with other electronic devices, the system architecture may only include the electronic devices (e.g., terminal devices or servers) on which the data determination method runs.

[0029] Please refer to Figure 2 , Figure 2 A flowchart of a data determination method provided in this embodiment of the disclosure. Flowchart 200 includes the following steps:

[0030] Step 201: Determine the geographical location of the target user.

[0031] In this embodiment, the execution body of the data determination method (e.g., Figure 1 The server in the system can determine the geographical location of the target user.

[0032] As an example, the aforementioned executing entity can determine the geographical location of the target user based on the geographical location of the terminal device corresponding to the target user. For instance, in response to the target user's terminal device being located in a geographical location for a period exceeding a preset duration, the aforementioned geographical location is determined as the geographical location of the target user, i.e., the geographical location of the target user.

[0033] As another example, the geographical location searched or specified by the target user is determined as the geographical location corresponding to the target user. For example, the geographical location searched or specified by the target user on an electronic map.

[0034] Step 202: Using a large language model, generate an interest tree that represents the target user's interest information based on the target user's user data.

[0035] In this embodiment, the aforementioned execution entity can generate an interest tree representing the target user's interest information based on the target user's user data using a large language model.

[0036] User data can include basic attribute data, behavioral data, preference data, transaction data, etc., related to the target user. With the authorization of the target user, the aforementioned executing entity can obtain the target user's user data.

[0037] Large language models specifically refer to pre-trained large language models in artificial intelligence, possessing a large or even ultra-large number of parameters. The term "large language model" encompasses two meanings: "pre-training" and "large model." The combination of these two aspects creates a new paradigm in artificial intelligence: models pre-trained on large datasets can directly support various applications with little or no fine-tuning on large datasets. Large AI models exhibit excellent contextual understanding, language generation, learning capabilities, and transferability.

[0038] In this embodiment, user data is input into a large language model. Leveraging the powerful natural language understanding capabilities of the large language model, the user's points of interest (e.g., items, attractions, food, etc.) and the relationships between these points of interest are determined, generating an interest tree that represents the target user's interest information. The interest tree represents the user's interest preferences through a tree structure. Each node in the tree represents a point of interest, and the connections between nodes reflect the relationships or hierarchical relationships between these points of interest.

[0039] To improve the efficiency and effectiveness of data processing, the aforementioned execution body can preprocess user data before generating the interest tree, including but not limited to data cleaning, formatting, and normalization.

[0040] To ensure that the interest tree accurately reflects the user's current interests, a large language model can be used to generate an interest tree that represents the target user's current interests based on user data up to the current preset time period.

[0041] This embodiment does not limit the execution order of steps 201 and 202. That is, step 201 can be executed before step 202, step 201 can be executed after step 202, and step 201 can even be executed simultaneously with step 202.

[0042] In some optional implementations of this embodiment, the execution entity can perform step 202 as follows:

[0043] The first step is to identify the target user data corresponding to multiple time intervals from the user data, thus obtaining multiple user data groups that correspond one-to-one with the multiple time intervals.

[0044] The duration of each of the multiple time intervals varies. These time intervals can overlap or remain independent. The number of time intervals and their respective lengths can be set according to the specific circumstances. In some implementations, different time intervals can be set for different time units such as days, months, and years, with the length of the time interval increasing as the time unit increases.

[0045] As an example, the time interval includes a first time interval and a second time interval. The first time interval is the first period of time up to the present (e.g., 5 days), and the second time interval is the second period of time up to the present (e.g., one month).

[0046] For each of the multiple time intervals, a user data group is generated based on the target user data within that time interval, thus obtaining multiple user data groups that correspond one-to-one with the multiple time intervals.

[0047] The second step involves using a large language model to generate multiple interest trees that correspond one-to-one with each user data group.

[0048] As an example, for each user data group in multiple user data groups, the data in the user data group is input into the large language model to generate an interest tree corresponding to that user data group, thus obtaining multiple interest trees that correspond one-to-one with multiple user data groups.

[0049] In this implementation, a large language model is used to generate multiple interest trees representing the target user's interest information in different time intervals based on multiple user data groups. This provides rich interest-based data for the subsequent data recommendation process, which helps to improve the flexibility and accuracy of the data recommendation process.

[0050] In some optional implementations of this embodiment, the execution entity can perform the second step as follows: For each user data group in the plurality of user data groups, perform the following operation:

[0051] First, using a large language model, interest-based prompt text is generated based on preset prompt data and the user's data set.

[0052] The interest-based prompt text represents the target user's interest information within the time interval corresponding to the user data set. Preset prompt data guides the large model to determine the user's interest points from the user data set; for example, it might be "In *** format, output the target user's interest points."

[0053] Then, the interest-based text is expanded using a large language model to obtain the expanded text.

[0054] In this implementation, a series of interest-based prompt texts can be generated based on the first step described above. For example:

[0055] "Technology" → "Artificial Intelligence", "Machine Learning", "Programming Languages"

[0056] "Sports" -> "Football", "Basketball", "Tennis"

[0057] "Entertainment" → "Movies", "Music", "Games".

[0058] Each interest-based prompt text can be expanded using a large language model.

[0059] For the interest tag text "Technology" -> "Artificial Intelligence", "Machine Learning", "Programming Languages", the expanded text would be as follows:

[0060]

[0061]

[0062] For the interest prompt text "Entertainment" -> "Movies", "Music", "Games", the expanded text would be as follows:

[0063] Generate an interest tree corresponding to the user data group based on the expanded text.

[0064] The expanded text includes the user's points of interest and the relationships or hierarchical relationships between these points of interest; based on the points of interest, relationships or hierarchical relationships in the expanded text, an interest tree corresponding to the user's data group can be generated.

[0065] This implementation provides a specific method for generating interest trees based on a large language model, which improves the accuracy and generation efficiency of interest trees.

[0066] Step 203: Using a pre-trained data recommendation model, determine the data to be recommended that is related to the geographic location based on the interest tree.

[0067] In this embodiment, the aforementioned execution entity can determine the data to be recommended based on the interest tree using a pre-trained data recommendation model.

[0068] Using interest trees and geographic locations as input to a data recommendation model, data to be recommended to the target user is generated. As an example, within a preset area centered on geographic location, various types of data (e.g., shops, attractions) are identified to construct a dataset; then, based on the interest tree, data that the target user is interested in is selected and identified as the data to be recommended.

[0069] Data recommendation models can employ various models capable of implementing data recommendation functions, such as recurrent neural networks, convolutional neural networks, graph neural networks, and large language models.

[0070] In some optional implementations of this embodiment, the execution entity can perform step 203 as follows:

[0071] For each of the multiple interest trees, within the recommendation period corresponding to that interest tree, the data recommendation model determines the set of data to be recommended that is related to the geographic location.

[0072] Among them, the recommendation period for different interest trees is of different duration, and the recommendation period for an interest tree is positively correlated with the duration of the time interval corresponding to the interest tree. The data group to be recommended includes at least one data to be recommended.

[0073] Continuing with the first and second time intervals mentioned above, the recommendation period corresponding to the interest tree obtained based on user data within the first time interval is one day. This is the daily dimension. For example, during mealtimes, restaurants near the target user's location are recommended; during commuting hours, the most convenient mode of transportation is recommended. The recommendation period corresponding to the interest tree obtained based on user data within the second time interval is one month. This is the monthly dimension. For example, before holidays, reminders for booking travel tickets and hotels are pushed out; during holidays, popular tourist attractions with high visitor traffic or less crowded, less-visited attractions are recommended.

[0074] In this implementation, different interest trees are used to recommend data to be recommended to the target user within different recommendation periods, which further improves the accuracy of the recommendations and the richness of the data to be recommended.

[0075] In some optional implementations of this embodiment, the execution entity can perform the process of determining the data to be recommended in the following way: within the recommendation period corresponding to the interest tree, the data recommendation model determines the group of data to be recommended related to the geographical location based on the interest tree and the real-time operation data of the target user.

[0076] Real-time action data can be the real-time action data of a target user within their target application. This data can further reflect the target user's real-time interests. The interest tree, real-time action data, and geographic location are input into a data recommendation model to generate recommended data for the target user. Target applications include, for example, e-commerce applications, social media applications, video applications, and electronic map applications.

[0077] In this implementation, the accuracy of the data to be recommended is further improved by combining the interest tree and geographic location with the real-time operation data of the target user.

[0078] In some optional implementations of this embodiment, the execution entity can perform the process of determining the data to be recommended in the following manner:

[0079] First, the first feature vector representing the interest tree, the second feature vector representing the real-time operation data, and the third feature vector representing the geographical location are fused to obtain the fused vector.

[0080] As an example, the aforementioned execution entity can use an encoding network to encode the interest tree, real-time operation data, and geographic location separately to obtain a first feature vector, a second feature vector, and a third feature vector; then, the first feature vector, the second feature vector, and the third feature vector can be fused by methods such as vector concatenation and vector addition to obtain a fused vector.

[0081] Then, the fused vectors are input into the data recommendation model to determine the data group to be recommended.

[0082] As an example, the aforementioned execution entity can determine the similarity between the data vectors of each data in the data set corresponding to the fused vector and the geographic location, and sort the data in the data set in descending order of similarity, and then combine the data with the highest similarity ranking into a data group to be recommended.

[0083] In this implementation, the data recommendation model uses the fused vector of the first feature vector, the second feature vector, and the third feature vector as input to determine the data group to be recommended, which helps to further improve the accuracy and efficiency of data recommendation.

[0084] In some optional implementations of this embodiment, the execution entity may also perform the following operations:

[0085] First, using the target display device, the overview data corresponding to the data group to be recommended is displayed based on the overview display control in the initial display interface.

[0086] The initial display interface can be the interface that the target user enters when operating the target display device. An overview display control is added to the initial display interface to show an overview of the data group to be recommended.

[0087] Continue to refer to Figure 3 The diagram illustrates an overview of the display controls.

[0088] The initial display interface includes multiple controls, among which is an overview display control 301. For a food-related data group to be recommended, the overview display control may display, for example, "For lunch, we recommend 10 popular dishes." The overview data can be flexibly set; for example, the overview data in the overview display control can also be set to "Lunch Recommendations."

[0089] Then, in response to receiving a trigger operation for the overview display control via the target display device, at least one piece of data to be recommended from the group of data to be recommended is displayed based on at least one data display control in the details display interface.

[0090] In response to a target user's action such as clicking or touching to trigger an overview display control, a details display interface is shown to the target user. The details display interface includes at least one data display control for displaying at least one piece of data to be recommended from the data group to be recommended.

[0091] This implementation provides a data recommendation and display method, which improves the user experience for the target users.

[0092] In some optional implementations of this embodiment, the execution entity can perform the above data display process in the following manner: First, based on the type of at least one piece of data to be recommended, determine the display method of at least one piece of data to be recommended; then, in response to receiving a trigger operation for the overview display control, determine at least one data display control to be used for the display method; finally, in the details display interface, display at least one piece of data to be recommended through at least one data display control.

[0093] In this implementation, different display methods can be set for different types of data to be recommended.

[0094] For example, for data to be recommended in the categories of food and attractions, the display method is animation, specifically, it can be an animation of preset duration (e.g., 5 seconds) related to food or attractions. The animation can be generated based on multiple food images corresponding to a store, or based on multiple scenic images corresponding to an attraction.

[0095] Continue to refer to Figure 4 The diagram illustrates a details display interface using an animated presentation method. At least one data display control 401 in the details display interface can display at least one piece of data to be recommended using an animated method.

[0096] For example, for data to be recommended, such as transportation routes, a display method combining route information and route attribute information can be used.

[0097] Continue to refer to Figure 5 The diagram illustrates the detailed display interface for route recommendation data. The data display controls further include a route display control 501 and an attribute display control 502. For each recommended route, the route display control shows the specific trajectory of the route, while the attribute display control displays attribute information such as the route's travel time and length.

[0098] In this implementation, different display methods are used for different types of data to be recommended, which improves the data display effect and helps to improve the efficiency and experience of users in obtaining information.

[0099] See also Figure 6 , Figure 6This is a schematic diagram of an application scenario 600 of the data determination method according to this embodiment. Server 601 first obtains the geographic location and user data of the target user 602 from the target user's terminal device 603. After determining the geographic location and user data, firstly, using a large language model, an interest tree representing the target user's interest information is generated based on the target user's user data; then, using a pre-trained data recommendation model, the data to be recommended related to the geographic location is determined based on the interest tree, and the data to be recommended is fed back to the terminal device.

[0100] This embodiment provides a data determination method, which involves determining the geographical location of a target user; generating an interest tree representing the target user's interests based on the user data using a large language model; and determining the data to be recommended related to the geographical location using a pre-trained data recommendation model based on the interest tree. This provides a method for determining the data to be recommended, and the accuracy of the data to be recommended is improved by using the interest tree generated by the large language model and the geographical location of the target user.

[0101] Continue to refer to Figure 7 The illustration shows a schematic flow 700 of yet another embodiment of the data determination method according to this disclosure. Flow 700 includes the following steps:

[0102] Step 701: Determine the geographical location of the target user.

[0103] Step 702: From the user data, determine the target user data corresponding to each of the multiple time intervals, and obtain multiple user data groups that correspond one-to-one with the multiple time intervals.

[0104] The duration of several time intervals varies.

[0105] Step 703, for each user data group in the multiple user data groups, perform the following operation:

[0106] Step 7031: Generate interest prompt text based on the preset prompt data and the user data group using the large language model.

[0107] Among them, the interest-based text indicates the target user's interest information within the time interval corresponding to the user data group.

[0108] Step 7032: Expand the interest prompt text using a large language model to obtain the expanded text.

[0109] Step 7033: Generate the interest tree corresponding to the user data group based on the expanded text.

[0110] Step 704: For each of the multiple interest trees, within the recommendation period corresponding to that interest tree, the data recommendation model determines the data group to be recommended that is related to the geographical location.

[0111] The recommendation period for different interest trees varies in length, and the length of the recommendation period for an interest tree is positively correlated with the length of the time interval corresponding to that interest tree. Each data set to be recommended includes at least one piece of data to be recommended.

[0112] Step 705: Display the overview data corresponding to the data group to be recommended through the target display device, based on the overview display control in the initial display interface.

[0113] Step 706: In response to receiving a trigger operation for the overview display control via the target display device, at least one piece of data to be recommended from the group of data to be recommended is displayed based on at least one data display control in the details display interface.

[0114] The data determination method in this embodiment, in process 700, compared to process 200, specifically describes the generation process of the interest tree, the determination process of the data to be recommended, and the display process, further improving the accuracy of the data to be recommended and the user experience.

[0115] Continue to refer to Figure 8 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a data determination device, which is similar to... Figure 2 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0116] like Figure 8 As shown, the data determination device 800 includes: a location determination unit 801, configured to determine the geographical location corresponding to the target user; an interest tree generation unit 802, configured to generate an interest tree representing the target user's interest information based on the target user's user data using a large language model; and a data determination unit 803, configured to determine the data to be recommended related to the geographical location based on the interest tree using a pre-trained data recommendation model.

[0117] In some optional implementations of this embodiment, the interest tree generation unit 802 is further configured to: determine the target user data corresponding to each of the multiple time intervals from the user data, and obtain multiple user data groups that correspond one-to-one with the multiple time intervals, wherein the duration of the multiple time intervals is different; and generate multiple interest trees that correspond one-to-one with the multiple user data groups based on the multiple user data groups through a large language model.

[0118] In some optional implementations of this embodiment, the interest tree generation unit 802 is further configured to: for each user data group among multiple user data groups, perform the following operations: generate interest prompt text based on preset prompt data and the user data group using a large language model, wherein the interest prompt text represents the target user's interest information within the time interval corresponding to the user data group; expand the interest prompt text using a large language model to obtain expanded text; and generate an interest tree corresponding to the user data group based on the expanded text.

[0119] In some optional implementations of this embodiment, the data determination unit 803 is further configured to: for each of the multiple interest trees, within the recommendation period corresponding to the interest tree, determine a group of data to be recommended related to the geographical location based on the interest tree through a data recommendation model, wherein the duration of the recommendation period corresponding to different interest trees is different, the duration of the recommendation period corresponding to the interest tree is positively correlated with the duration of the time interval corresponding to the interest tree, and the group of data to be recommended includes at least one piece of data to be recommended.

[0120] In some optional implementations of this embodiment, the data determination unit 803 is further configured to: within the recommendation period corresponding to the interest tree, determine the data group to be recommended related to the geographical location through the data recommendation model, based on the interest tree and the real-time operation data of the target user.

[0121] In some optional implementations of this embodiment, the data determination unit 803 is further configured to: fuse the first feature vector representing the interest tree, the second feature vector representing real-time operation data, and the third feature vector representing geographical location to obtain a fused vector; input the fused vector into the data recommendation model to determine the data group to be recommended.

[0122] In some optional implementations of this embodiment, the above-mentioned apparatus further includes: a data display unit (not shown in the figure), configured to: display overview data corresponding to the data group to be recommended based on the overview display control in the initial display interface via the target display device; and, in response to receiving a trigger operation for the overview display control via the target display device, display at least one piece of data to be recommended in the data group to be recommended based on at least one data display control in the details display interface.

[0123] In some optional implementations of this embodiment, the data display unit is further configured to: determine the display method of at least one piece of data to be recommended based on the type of at least one piece of data to be recommended; in response to receiving a trigger operation for the overview display control, determine at least one data display control to be used in the display method; and display at least one piece of data to be recommended in the details display interface through at least one data display control.

[0124] This embodiment provides a data determination device that determines the geographical location of a target user; generates an interest tree representing the target user's interests based on the user data of the target user using a large language model; and determines the data to be recommended related to the geographical location based on the interest tree using a pre-trained data recommendation model. This provides a method for determining the data to be recommended, which improves the accuracy and determination efficiency of the data to be recommended by using the interest tree generated by the large language model and the geographical location of the target user.

[0125] According to embodiments of this disclosure, this disclosure also provides an electronic device, the electronic device 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 implement the data determination method described in any of the above embodiments when executed.

[0126] According to embodiments of this disclosure, this disclosure also provides a readable storage medium storing computer instructions that enable a computer to perform the data determination method described in any of the above embodiments when executed.

[0127] This disclosure provides a computer program product that, when executed by a processor, can implement the data determination method described in any of the above embodiments.

[0128] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may 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.

[0129] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0130] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0131] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 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 901 performs the various methods and processes described above, such as the data determination method. For example, in some embodiments, the data determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the data determination method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the data determination method by any other suitable means (e.g., by means of firmware).

[0132] 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), payload-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.

[0133] 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 determination device, 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.

[0134] 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.

[0135] 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).

[0136] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments 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., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0137] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are hosting products within the cloud computing service system to address the management difficulties and weak business scalability inherent in traditional physical hosts and Virtual Private Servers (VPS) services; they can also be servers for distributed systems or servers integrated with blockchain technology.

[0138] According to the technical solution of the embodiments of this disclosure, a data determination method and apparatus are provided. The method determines the geographical location corresponding to a target user; generates an interest tree representing the target user's interest information based on the user data of the target user using a large language model; and determines the data to be recommended related to the geographical location based on the interest tree using a pre-trained data recommendation model. This provides a method for determining the data to be recommended, improving the accuracy and efficiency of determining the data to be recommended based on the interest tree generated by the large language model and the geographical location corresponding to the target user.

[0139] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution provided in this disclosure can be achieved, and this is not limited herein.

[0140] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data determination method, comprising: Determine the geographical location of the target users; From the user data of the target user, target user data corresponding to multiple time intervals are determined, resulting in multiple user data groups that correspond one-to-one with the multiple time intervals, wherein the duration of the multiple time intervals is different; Using a large language model, multiple interest trees are generated that correspond one-to-one with the multiple user data groups. For each of the plurality of interest trees, within the recommendation period corresponding to that interest tree, a pre-trained data recommendation model determines a group of data to be recommended that is related to the geographic location based on that interest tree. The recommendation period corresponding to different interest trees has a different duration, and the duration of the recommendation period corresponding to the interest tree is positively correlated with the duration of the time interval corresponding to the interest tree. The group of data to be recommended includes at least one piece of data to be recommended.

2. The method according to claim 1, wherein, The step of generating multiple interest trees, each corresponding to one of the multiple user data groups, using the large language model includes: For each of the plurality of user data groups, perform the following operation: Using the large language model, interest prompt text is generated based on preset prompt data and the user data group, wherein the interest prompt text represents the target user's interest information within the time interval corresponding to the user data group; The interest-indicating text is expanded using the large language model to obtain the expanded text. Based on the expanded text, an interest tree corresponding to the user data group is generated.

3. The method according to claim 1, wherein, Within the recommendation period corresponding to the interest tree, the data recommendation model determines the data group to be recommended related to the geographical location based on the interest tree, including: Within the recommendation period corresponding to the interest tree, the data recommendation model determines the data group to be recommended that is related to the geographical location based on the interest tree and the real-time operation data of the target user.

4. The method according to claim 3, wherein, The step of determining a group of data to be recommended related to the geographic location using the data recommendation model, based on the interest tree and the target user's real-time operation data, includes: The first feature vector representing the interest tree, the second feature vector representing the real-time operation data, and the third feature vector representing the geographical location are fused to obtain the fused vector; The fused vector is input into the data recommendation model to determine the data group to be recommended.

5. The method according to any one of claims 1-4, wherein, Also includes: The summary data corresponding to the data group to be recommended is displayed on the target display device based on the summary display control in the initial display interface; In response to receiving a trigger operation for the overview display control via the target display device, at least one piece of data to be recommended from the group of data to be recommended is displayed based on at least one data display control in the details display interface.

6. The method according to claim 5, wherein, In response to receiving a trigger operation for the overview display control, displaying at least one piece of data to be recommended from the group of data to be recommended based on at least one data display control in the details display interface includes: Based on the type of the at least one piece of data to be recommended, determine the display method of the at least one piece of data to be recommended; In response to receiving a trigger operation for the overview display control, at least one data display control is determined to employ the display method; In the details display interface, the at least one piece of data to be recommended is displayed through the at least one data display control.

7. A data determination device, comprising: The location determination unit is configured to determine the geographical location of the target user. The interest tree generation unit is configured to: determine target user data corresponding to multiple time intervals from the user data of the target user, and obtain multiple user data groups that correspond one-to-one with the multiple time intervals, wherein the duration of the multiple time intervals is different; and generate multiple interest trees that correspond one-to-one with the multiple user data groups based on the multiple user data groups using a large language model. The data determination unit is configured to, for each of the plurality of interest trees, within the recommendation period corresponding to that interest tree, determine a group of data to be recommended related to the geographical location based on that interest tree using a pre-trained data recommendation model. The recommendation period corresponding to different interest trees has a different duration, and the duration of the recommendation period corresponding to the interest tree is positively correlated with the duration of the time interval corresponding to the interest tree. The group of data to be recommended includes at least one piece of data to be recommended.

8. The apparatus according to claim 7, wherein, The interest tree generation unit is further configured to: For each of the plurality of user data groups, perform the following operation: Using the large language model, interest-based prompt text is generated based on preset prompt data and the user data group, wherein the interest-based prompt text represents the target user's interest information within the time interval corresponding to the user data group; the interest-based prompt text is expanded using the large language model to obtain expanded text; and an interest tree corresponding to the user data group is generated based on the expanded text.

9. The apparatus according to claim 7, wherein, The data determination unit is further configured to: Within the recommendation period corresponding to the interest tree, the data recommendation model determines the data group to be recommended that is related to the geographical location based on the interest tree and the real-time operation data of the target user.

10. The apparatus according to claim 9, wherein, The data determination unit is further configured to: The first feature vector representing the interest tree, the second feature vector representing the real-time operation data, and the third feature vector representing the geographical location are fused to obtain a fused vector; the fused vector is then input into the data recommendation model to determine the data group to be recommended.

11. The apparatus according to any one of claims 7-10, wherein, Also includes: The data display unit is configured as follows: Through the target display device, based on the overview display control in the initial display interface, the overview data corresponding to the data group to be recommended is displayed; through the target display device, in response to receiving a trigger operation for the overview display control, based on at least one data display control in the details display interface, at least one piece of data to be recommended in the data group to be recommended is displayed.

12. The apparatus according to claim 11, wherein, The data display unit is further configured to: Based on the type of the at least one piece of data to be recommended, determine the display method of the at least one piece of data to be recommended; in response to receiving a trigger operation for the overview display control, determine at least one data display control to adopt the display method; in the details display interface, display the at least one piece of data to be recommended through the at least one data display control.

13. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, 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 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising: A computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images