Point of interest determination method and device, computer readable storage medium and electronic equipment

Abstract

The invention provides an interest point determination method, an interest point determination device, a computer readable storage medium and electronic equipment, and relates to the technical field of big data. The interest point determination method comprises the following steps: acquiring a current context, wherein the current context comprises current time information and current interest point information; determining a target historical point-of-interest behavior corresponding to the current context; generating a prompt text by using the current context, the target historical point-of-interest behavior and the user portrait; and inputting the prompt text into the large language model to determine a point-of-interest prediction result. The interest point determination accuracy can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of big data technology, and in particular to a method for determining a point of interest, a device for determining a point of interest, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the development of terminals and big data technology, technologies related to Point of Interest (POI) are deployed in various scenarios, for example, analyzing user behavior to predict the points of interest that users may visit in the future.

[0003] Currently, solutions for determining user points of interest generally have the problem of low accuracy, which makes it impossible to better meet user needs. Summary of the invention

[0004] The present disclosure provides a method for determining points of interest, a device for determining points of interest, a computer-readable storage medium, and an electronic device, thereby overcoming the problem of low accuracy of solutions for determining points of interest at least to a certain extent.

[0005] According to a first aspect of the present disclosure, a method for determining points of interest is provided, including: obtaining a current context, the current context including current time information and current points of interest information; determining a target historical point of interest behavior corresponding to the current context; generating a prompt text using the current context, the target historical point of interest behavior and a user portrait; and inputting the prompt text into a large language model to determine a point of interest prediction result.

[0006] According to a second aspect of the present disclosure, a device for determining points of interest is provided, including: a context acquisition module, used to acquire a current context, the current context including current time information and current points of interest information; a historical behavior determination module, used to determine a target historical point of interest behavior corresponding to the current context; a prompt text generation module, used to generate a prompt text using the current context, the target historical point of interest behavior and a user portrait; and a result determination module, used to input the prompt text into a large language model to determine a point of interest prediction result.

[0007] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for determining points of interest is implemented.

[0008] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising a processor; and a memory for storing one or more programs, wherein when the one or more programs are executed by the processor, the processor implements the above-mentioned method for determining points of interest.

[0009] In the technical solutions provided by some embodiments of the present disclosure, the corresponding target historical point of interest behavior is determined based on the current context, and a prompt text is generated using the current context, the target historical point of interest behavior, and the user portrait, and the prompt text is input into a large language model to determine the point of interest prediction result. On the one hand, the disclosed solution uses a large language model to analyze points of interest, which combines user portraits, historical point of interest behaviors, and the current context, thereby improving the accuracy of point of interest determination, helping to match user needs, and cooperating with other tasks (such as product recommendation tasks) to enhance the user's application experience; on the other hand, the target historical point of interest behavior used in the present disclosure is the historical point of interest behavior corresponding to the current context, rather than all historical point of interest behaviors, thereby reducing the length of the prompt text generated thereby, and focusing the historical point of interest behaviors in the prompt text, thereby improving the quality of the prompt text.

[0010] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0012] Figure 1 The figure shows an input and output diagram of the interest point determination process according to an embodiment of the present disclosure.

[0013] Figure 2 A schematic diagram of pre-maintaining a historical point of interest behavior set according to an embodiment of the present disclosure is shown.

[0014] Figure 3 A schematic diagram showing a list corresponding to a historical point of interest behavior set according to an embodiment of the present disclosure.

[0015] Figure 4 The flowchart of the method for determining points of interest according to an exemplary embodiment of the present disclosure is schematically shown.

[0016] Figure 5 A schematic diagram of factors used in the process of recalling historical interest point behaviors according to an embodiment of the present disclosure is shown.

[0017] Figure 6 A schematic diagram showing the style of the prompt text of an embodiment of the present disclosure is shown.

[0018] Figure 7 A schematic diagram showing the results of interest point prediction according to an embodiment of the present disclosure is shown.

[0019] Figure 8 A block diagram of a device for determining points of interest according to an exemplary embodiment of the present disclosure is schematically shown.

[0020] Fig. 9 A block diagram of a device for determining points of interest according to another exemplary embodiment of the present disclosure is schematically shown.

[0021] Fig.10 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0022] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps may be decomposed, while some steps may be combined or partially combined, so the actual execution order may change according to the actual situation.

[0025] The interest point determination scheme of the embodiment of the present disclosure can be implemented by a terminal device, that is, each step of the interest point determination method described below can be performed by the terminal device, and the interest point determination device described below can be configured in the terminal device. The present disclosure does not limit the device type of the terminal device, for example, including but not limited to smart phones, tablet computers, smart wearable devices, personal computers, etc.

[0026] Figure 1 FIG. 1 is a schematic diagram showing the input and output of the interest point determination process of an embodiment of the present disclosure. Figure 1 The input of the interest point determination process of the embodiment of the present disclosure may include user portrait, current context and target historical interest point behavior, and the output is the interest point prediction result.

[0027] User portraits can describe the user's personal characteristics and behavioral preferences, which can be divided into static attributes and dynamic attributes. Static attributes may include but are not limited to the user's age, gender, home address, work address, occupation, etc., and dynamic attributes may include but are not limited to whether the user has a car, whether the user has children, recent traffic habits, etc. These attributes can, for example, affect the user's travel destination and method, thereby affecting the accuracy and efficiency of determining points of interest.

[0028] Based on user portraits, more accurate POI recommendation services can be provided based on different user characteristics and preferences. For example, the travel differences between office workers and students, and the travel differences between car users and non-car users. These differences can help the large language model (LLM) of the disclosed embodiment filter out irrelevant or unreasonable POIs and improve the accuracy and recall of predictions. For example, what types of restaurants, shopping malls, parks, etc. you like, these interests and preferences can help the large language model select POIs that are suitable for users.

[0029] The current context may include current time information and current point of interest information. The current time information may be expressed, for example, in the form of the following timestamp: {2023-05-07 10:00:00}. The current point of interest information may include one or more of the point of interest name, point of interest category, and point of interest description. The point of interest name indicates the geographical location name of the point of interest, such as hospital a, school b, etc. The point of interest category may include at least one layer of categories, indicating the type classification of the point of interest. Taking the three-layer category as an example, for the park point of interest, its point of interest categories may include tourist attractions, scenic spots, and royal gardens. The point of interest description is an introduction to the point of interest, usually shown in a short text.

[0030] The target historical point of interest behavior is one or more historical point of interest behaviors recalled from the historical point of interest behavior set. Specifically, the recall can be performed based on the current context. The specific factors considered include a combination of one or more of the time factor, importance factor, and relevance factor of the historical point of interest behavior relative to the current context.

[0031] The point of interest determination process of the disclosed embodiment is performed based on the user portrait, the current context and the target's historical point of interest behavior. Specifically, the user portrait, the current context and the target's historical point of interest behavior can be used to generate a prompt text (Prompt), and the prompt text is input into a large language model. The output of the large language model is the point of interest prediction result.

[0032] Among them, large language models can also be called large language models, which refer to language models containing hundreds of billions (or more) parameters, which are trained on a large amount of text data, such as models ChatGPT, GPT-3, PaLM, Galactica, LlaMA, etc. Specifically, large language models can be built on top of the Transformer architecture, in which multi-head attention layers are stacked in a very deep neural network.

[0033] Prompt text in a large language model is an input used to guide the model to complete a specific task, usually containing empty slots or masks for the model to fill or predict.

[0034] For the historical interest point behavior set in the embodiment of the present disclosure, Figure 2 A pre-built schematic diagram is shown as an example.

[0035] On the basis of privacy compliance, the terminal device can obtain the user's location coordinates and the corresponding timestamp. It is understandable that in the data analysis process, the user's location coordinates and timestamps are often obtained in pairs, such as Figure 2 The user location coordinates 1 and timestamp 1 in .

[0036] Subsequently, the terminal device may convert the user location coordinates into the point of interest information. Specifically, the terminal device may use the geographic service interface of a built-in or third-party navigation application to convert the user location coordinates into the point of interest information. As described above, the point of interest information may include a point of interest name (POI), a point of interest category (POI category), and a point of interest description (POI description), such as Figure 2 The user location coordinate 1 is converted into the point of interest information 1.

[0037] Next, a historical POI behavior can be generated from the timestamp and POI information, such as Figure 2 The historical point of interest behavior 1 is constructed by timestamp 1 and point of interest information 1.

[0038] Similarly, historical interest point behavior 2, historical interest point behavior 3, etc. can be formed. A historical interest point behavior set is obtained from these historical interest point behaviors.

[0039] The historical point of interest behavior set can also be called a point of interest memory stream. It can be understood that the historical point of interest behavior set maintains a record of the user's historical visits to points of interest, which is a list that can be stored in a terminal device.

[0040] Figure 3 A schematic diagram showing a list corresponding to a historical point of interest behavior set according to an embodiment of the present disclosure is shown. Figure 3 As shown, each historical POI behavior may include a visit timestamp, POI, POI category, and POI description. Figure 3 This is only an exemplary description and does not limit the form and content of the historical point of interest behavior of the present disclosure.

[0041] The following is an explanation of the method for determining points of interest according to an embodiment of the present disclosure.

[0042] Figure 4 The flowchart of the method for determining points of interest according to an exemplary embodiment of the present disclosure is schematically shown. Figure 4 , the method for determining points of interest may include the following steps:

[0043] S42. Obtain the current context, which includes current time information and current point of interest information.

[0044] In an exemplary embodiment of the present disclosure, the current context may include current time information and current point of interest information. Among them, the current time information may be expressed in the form of, for example, the following timestamp: {2023-05-07 10:00:00}. The current point of interest information may include one or more of the point of interest name, point of interest category, and point of interest description. The point of interest name indicates the geographical location name of the point of interest, such as a hospital, b school, etc. The point of interest category may include at least one layer of categories, indicating the type division of the point of interest. Taking the three-layer category as an example, for the point of interest A Park, its point of interest category may include tourist attractions, scenic spots, and royal gardens. It can be understood that the more layers of point of interest categories, the more information disclosed, and the higher the accuracy of subsequent point of interest prediction. The point of interest description is an introduction to the point of interest, which is a natural language description, usually shown in a short text, such as: A Park is a royal garden, built in the Qing Dynasty, which concentrates the essence of classical gardens and is known as the "treasure of gardens."

[0045] Specifically, the terminal device may obtain the current timestamp and the current user location coordinates, and may use the geographic service interface of a built-in or third-party navigation application to convert the current user location coordinates into the current point of interest information.

[0046] S44. Determine the target historical point of interest behavior corresponding to the current context.

[0047] Given that the prompt text used in subsequent large language model processing has a length limit, too long text cannot allow the large language model to understand the intention. In addition, a large number of irrelevant historical interest point behaviors may interfere with the reasoning of the large language model and affect the accuracy of interest point determination. Therefore, the implementation method of the present disclosure needs to determine the historical interest point behaviors corresponding to the current context. For the sake of ease of description, the present disclosure records the historical interest point behaviors corresponding to the current context as target historical interest point behaviors.

[0048] In an exemplary embodiment of the present disclosure, the terminal device may determine the target historical interest point behavior corresponding to the current context from the historical interest point behavior set, and the number of the target historical interest point behavior determined by the embodiment of the present disclosure is one or more.

[0049] The historical point of interest behavior set may be pre-stored in the terminal device. The following is an explanation of the pre-construction process of the historical point of interest behavior set according to the embodiment of the present disclosure.

[0050] First, for the historical user location coordinates, the terminal device can determine the time information corresponding to the user coordinate position. The terminal device can convert the user location coordinates into the point of interest information. Specifically, the terminal device can use the geographic service interface of the built-in or third-party navigation application to convert the user location coordinates into the point of interest information.

[0051] Next, the terminal device can use the point of interest information and the corresponding event information to construct historical point of interest behaviors.

[0052] It can be understood that the above process is only a process of generating a historical point of interest behavior, and the terminal device can determine the set of all historical point of interest behaviors in history as the historical point of interest behavior set.

[0053] The process of determining the target historical POI behavior corresponding to the current context from the historical POI behavior set can be called historical POI behavior recall. Figure 5 The factors considered in the process include a combination of one or more of the time factor, importance factor, and relevance factor of the historical interest point behavior relative to the current context.

[0054] The following describes the embodiments of the present disclosure for determining the target historical point of interest behavior.

[0055] The first embodiment of determining the target historical point of interest behavior according to the present disclosure:

[0056] First, the terminal device may obtain time information of historical interest point behaviors in the historical interest point behavior set.

[0057] Next, the terminal device can determine the time difference between the current time information in the current context and the time information of the historical point of interest behavior, and determine the time factor corresponding to the historical point of interest behavior based on the time difference. The time factor is negatively correlated with the time difference, that is, the larger the time difference, the smaller the time factor; the smaller the time difference, the larger the time factor.

[0058] If the time factor corresponding to the historical point of interest behavior m is recorded as T(m), the time factor can be expressed as formula 1:

[0059] T(m)=exp(-λ(tt m )) (Formula 1)

[0060] Among them, T(m) ranges from [0,1], t is the current time, t m is the time when the historical interest point behavior m occurs, and λ is a decay coefficient.

[0061] It can be seen that when λ increases, T(m) decreases, indicating that the decay rate of memory is accelerated. Therefore, only recent historical interest point behaviors can be recalled. In other words, when the historical interest point behavior is closer to the current one, the larger T(m) is, the more likely it is to be recalled; when the historical interest point behavior is farther away from the current one, the smaller T(m) is, the less likely it is to be recalled.

[0062] by Figure 3 Taking the three historical points of interest as an example, if the current time is 2023-05-04 10:00:00, assuming that the attenuation coefficient λ is 0.01, the time factor T(m1) corresponding to Park A is: T(m1) = exp(-0.01*2)≈0.980; the time factor T(m2) corresponding to Stadium B is: T(m2) = exp(-0.01*13)≈0.878; the time factor T(m3) corresponding to Shopping Street C is: T(m3) = exp(-0.01*166)≈0.190.

[0063] It can be seen that the time factor T(m1) corresponding to Park A is the largest, because the time corresponding to the point of interest A Park is closest to the current moment. The time factor T(m3) corresponding to Shopping Street C is the smallest, because the time corresponding to the point of interest C Shopping Street is the farthest from the current moment. The time factor T(m2) corresponding to Stadium B is the largest and is between the two.

[0064] After determining the time factor corresponding to the historical point of interest behavior, the terminal device may determine the target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set according to the time factor corresponding to the historical point of interest behavior.

[0065] Specifically, the POI score may be determined based on the time factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0066] In this embodiment, since only the time factor is considered, the time factor can be directly used as the score of the interest point. In addition, the present disclosure does not limit the specific value of the score threshold.

[0067] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0068] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0069] A second embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0070] On the one hand, the terminal device can determine the time factor corresponding to the historical point of interest behavior. This process is the same as the process in the first embodiment above and will not be repeated here.

[0071] On the other hand, the terminal device may determine the importance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information.

[0072] The importance factor is an indicator to measure whether a historical point of interest behavior is important. Specifically, the probability and prior probability of the point of interest information of the historical point of interest behavior appearing in the current point of interest information can be determined, and the information volume of the historical point of interest behavior can be determined using the probability and prior probability. When the initial importance factor corresponding to the historical point of interest behavior is determined, the terminal device can update the initial importance factor using the information volume to determine the importance factor corresponding to the historical point of interest behavior.

[0073] When a user visits a new point of interest and saves it in the historical point of interest behavior set, the terminal device can assign an importance value, such as 0.5. There are two initialization methods, one is random initialization, and the other is to use a content-based importance evaluation method, such as TF-IDF (term frequency-inverse text frequency index), which can enhance the accuracy of the importance factor during initialization.

[0074] The above determination process adopts the TF-IDF method. Specifically, the interest point description of the historical interest point behavior m is expressed as a vector M using TF-IDF. Then, the initial importance factor I(m) of the historical interest point behavior m can be expressed as Formula 2:

[0075]

[0076] Among them, l is the length of the vector, which is generally a fixed value.

[0077] Then, based on the current POI information, the language model is used to calculate the probability P(m|C) and the prior probability P(m) of the historical POI behavior m appearing in the current context C, and the logarithmic difference between the two is determined as the information amount Info(m), which is expressed as Formula 3:

[0078] Info(m)=|logP(m|C)-logP(m)| (Formula 3)

[0079] Next, the importance factor is updated using Formula 4 to obtain the importance factor corresponding to the historical interest point behavior.

[0080] I(m)=I(m)*exp (-Info(m)) (Formula 4)

[0081] After determining the time factor and importance factor corresponding to the historical interest point behavior, the terminal device may determine the target historical interest point behavior corresponding to the current context from the historical interest point behavior set according to the time factor and importance factor corresponding to the historical interest point behavior.

[0082] Specifically, the POI score may be determined based on the time factor and importance factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0083] The interest point score can be determined, for example, in a weighted manner. The interest point score Score can be expressed as Formula 5:

[0084] Score=α*T(m)+β*I(m) (Formula 5)

[0085] Among them, α and β are weight coefficients of the time factor and the importance factor respectively, and the present disclosure does not limit their values.

[0086] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0087] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0088] A third embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0089] On the one hand, the terminal device can determine the time factor and importance factor corresponding to the historical point of interest behavior. This process is the same as the process in the above-mentioned second embodiment and will not be repeated.

[0090] On the other hand, the terminal device may determine the relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information.

[0091] The relevance factor is an indicator that measures the relevance of the historical point of interest behavior to the current context. It can be determined by calculating the similarity. In other words, the terminal device can determine the similarity between the point of interest information of the historical point of interest behavior and the current point of interest information as the relevance factor corresponding to the historical point of interest behavior.

[0092] Specifically, the embedding similarity can be used to determine the relevance factor R(m), refer to Formula 6:

[0093] R(m)=Sim(3mb(m),3mb(C)) (Formula 6)

[0094] For this process, the terminal device may use a language model such as BERT to perform feature encoding on the POI information, and then calculate the similarity (such as cosine similarity).

[0095] In addition, the relevance factor can also be an indicator to measure the relevance between the historical interest point behavior and the user's personal attributes. The user's personal attributes include but are not limited to gender, age, occupation, etc. In some embodiments, the user's personal attributes can be embodied as the user portrait mentioned in the present disclosure.

[0096] After determining the time factor, importance factor and relevance factor corresponding to the historical interest point behavior, the terminal device can determine the target historical interest point behavior corresponding to the current context from the historical interest point behavior set based on the time factor, importance factor and relevance factor corresponding to the historical interest point behavior.

[0097] Specifically, the point of interest score can be determined based on the time factor, importance factor and relevance factor corresponding to the historical point of interest behavior. If the point of interest score is greater than the score threshold, the terminal device determines the historical point of interest behavior as the target historical point of interest behavior corresponding to the current context.

[0098] The interest point score can be determined, for example, in a weighted manner. The interest point score Score can be expressed as Formula 7:

[0099] Score=α*T(m)+β*I(m)+γ*R(m) (Formula 7)

[0100] Among them, α, β and γ are weight coefficients of time factor, importance factor and relevance factor respectively, and the present disclosure does not limit their values.

[0101] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0102] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0103] A fourth embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0104] The terminal device may determine the time factor and the relevance factor corresponding to the historical point of interest behavior. The process of determining the time factor and the relevance factor is the same as that in the above embodiment and will not be repeated herein.

[0105] Next, the terminal device may determine a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set according to the time factor and the relevance factor corresponding to the historical point of interest behavior.

[0106] Specifically, the POI score may be determined based on the time factor and relevance factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0107] The interest point score can be determined, for example, in a weighted manner. The interest point score Score can be expressed as Formula 8:

[0108] Score=α*T(m)+γ*R(m) (Formula 8)

[0109] Among them, α and γ are weight coefficients of the time factor and the relevance factor respectively, and the present disclosure does not impose any limitation on their values.

[0110] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0111] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0112] A fifth embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0113] The terminal device may determine the importance factor corresponding to the historical point of interest behavior. The process of determining the importance factor is the same as that in the above embodiment and will not be described in detail.

[0114] Next, the terminal device may determine a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set according to the importance factor corresponding to the historical point of interest behavior.

[0115] Specifically, the POI score may be determined based on the importance factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0116] In this embodiment, because only the importance factor is considered, the importance factor can be directly used as the score of the point of interest. In addition, the present disclosure does not limit the specific value of the score threshold.

[0117] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0118] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0119] A sixth embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0120] The terminal device may determine the importance factor and the relevance factor corresponding to the historical point of interest behavior. The process of determining the importance factor and the relevance factor is the same as that in the above embodiment and will not be repeated herein.

[0121] Next, the terminal device may determine a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set according to the importance factor and the relevance factor corresponding to the historical point of interest behavior.

[0122] Specifically, the POI score may be determined based on the importance factor and relevance factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0123] The interest point score can be determined, for example, in a weighted manner. The interest point score Score can be expressed as Formula 9:

[0124] Score=β*I(m)+γ*R(m) (Formula 9)

[0125] Among them, β and γ are weight coefficients of the importance factor and the relevance factor respectively, and the present disclosure does not limit their values.

[0126] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0127] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0128] A seventh embodiment of determining a target historical point of interest behavior according to the present disclosure:

[0129] The terminal device may determine the relevance factor corresponding to the historical point of interest behavior. The process of determining the relevance factor is the same as that in the above embodiment and will not be described in detail.

[0130] Next, the terminal device may determine a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set according to the relevance factor corresponding to the historical point of interest behavior.

[0131] Specifically, the POI score may be determined based on the relevance factor corresponding to the historical POI behavior. If the POI score is greater than a score threshold, the terminal device determines the historical POI behavior as the target historical POI behavior corresponding to the current context.

[0132] In this embodiment, since only the relevance factor is considered, the relevance factor can be directly used as the score of the interest point. In addition, the present disclosure does not limit the specific value of the score threshold.

[0133] It is understandable that the above process is only a judgment process for one historical point of interest behavior, and by traversing all historical point of interest behaviors in the historical point of interest behavior set, all target historical point of interest behaviors used in the embodiment of the present disclosure can be determined.

[0134] In addition, if the number of determined target historical interest point behaviors is less than the quantity threshold, the terminal device can determine the number threshold number of historical interest point behaviors from the historical interest point behavior set in descending order of interest point scores as the target historical interest point behaviors. The quantity threshold is the minimum number of target historical interest point behaviors used to execute the subsequent algorithm, and the present disclosure does not limit its specific value.

[0135] S46. Generate prompt text using the current context, target historical POI behavior and user portrait.

[0136] After determining the current context, the target's historical POI behavior and the user's portrait, the terminal device can use this information to automatically generate prompt text.

[0137] Figure 6 The schematic diagram of the style of the prompt text of the embodiment of the present disclosure is shown. Figure 6 ,The prompt text can include the user portrait, the behavior sequence of the target historical POI behaviors, and the prediction task. Among them, the prediction task includes the current context, specifically including the current time information {2023-05-07 8:00:00} and the current POI information {D library}.

[0138] In addition, the prediction task can also include prediction targets, such as Figure 6As shown, the prediction target is, for example, “Please give three POIs that I may visit at {2023-05-07 10:00:00}, sort them by preference, and give the reason for the prediction.”

[0139] The prediction target involved in the present disclosure can be determined by the prediction task, that is, different prediction tasks may have different prediction targets. In addition, once the prediction target is set, it can be configured as fixed data. For example Figure 6 As shown, it includes three POIs that may be visited 2 hours from now. The time element and the POI quantity element can be pre-configured by the terminal device or configured by the user, and the present disclosure does not limit this.

[0140] S48. Input the prompt text into the large language model to determine the POI prediction result.

[0141] After determining the prompt text, the terminal device can input the prompt text into the large language model, and the output of the large language model is the prediction result of the point of interest. Among them, the present disclosure does not limit the type, scale, training, etc. of the large language model used.

[0142] Figure 7 The present disclosure embodiment and Figure 6 Schematic diagram of the corresponding interest point prediction results. Figure 7 , the content output by the large language model is similar to Figure 6 The prediction tasks are consistent across the prompt texts shown.

[0143] Based on the current context, the target's historical POI behavior, and the user's profile, the large language model predicts that the three POIs that the user may visit at {2023-05-07 10:00:00} are E attraction, F park, and G stadium, and they are sorted according to the user's preferences. The output is diverse and personalized because it takes into account the user's age, gender, permanent residence, whether there is a car, and other characteristics, as well as the user's travel history and POIs. The output is also flexible and explainable because it can be customized according to different tasks or fields, such as increasing or decreasing the number of prediction results, or giving reasons or suggestions for the prediction results.

[0144] It should be noted that although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0145] Furthermore, this example implementation also provides a device for determining points of interest.

[0146] Figure 8 FIG. 1 schematically shows a block diagram of an apparatus for determining points of interest according to an exemplary embodiment of the present disclosure. Figure 8 According to an exemplary embodiment of the present disclosure, the point of interest determination device 8 may include a context acquisition module 81 , a historical behavior determination module 83 , a prompt text generation module 85 and a result determination module 87 .

[0147] Specifically, the context acquisition module 81 can be used to obtain the current context, which includes the current time information and the current point of interest information; the historical behavior determination module 83 can be used to determine the target historical point of interest behavior corresponding to the current context; the prompt text generation module 85 can be used to generate prompt text using the current context, target historical point of interest behavior and user portrait; the result determination module 87 can be used to input the prompt text into the large language model to determine the point of interest prediction result.

[0148] According to an exemplary embodiment of the present disclosure, the historical behavior determination module 83 may be configured to execute: determining a target historical interest point behavior corresponding to the current context from a historical interest point behavior set.

[0149] According to an exemplary embodiment of the present disclosure, referring to Fig. 9 Compared with the interest point determination device 8 , the interest point determination device 9 may further include a set determination module 91 .

[0150] Specifically, the set determination module 91 can be configured to perform: for historical user location coordinates, determine the time information corresponding to the user location coordinates; convert the user location coordinates into point of interest information; construct historical point of interest behaviors using the point of interest information and the corresponding time information; and determine the set of all historical point of interest behaviors as a historical point of interest behavior set.

[0151] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can be configured to execute: obtaining the time information of the historical interest point behavior in the historical interest point behavior set; determining the time difference between the current time information and the time information of the historical interest point behavior, and determining the time factor corresponding to the historical interest point behavior based on the time difference, the time factor is negatively correlated with the time difference; determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set in combination with the time factor corresponding to the historical interest point behavior.

[0152] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set in combination with the time factor corresponding to the historical interest point behavior can be configured to perform: determining the interest point score in combination with the time factor corresponding to the historical interest point behavior; if the interest point score is greater than the score threshold, determining the historical interest point as the target historical interest point behavior corresponding to the current context.

[0153] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the interest point score in combination with the time factor corresponding to the historical interest point behavior can be configured to perform: determining the importance factor corresponding to the historical interest point behavior based on the interest point information of the historical interest point behavior and the current interest point information; determining the interest point score based on the time factor and importance factor corresponding to the historical interest point behavior.

[0154] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the interest point score in combination with the time factor and importance factor corresponding to the historical interest point behavior can be configured to perform: determining the relevance factor corresponding to the historical interest point behavior based on the interest point information of the historical interest point behavior and the current interest point information; determining the interest point score based on the time factor, importance factor and relevance factor corresponding to the historical interest point behavior.

[0155] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the interest point score in combination with the time factor corresponding to the historical interest point behavior can also be configured to perform: determining the relevance factor corresponding to the historical interest point behavior based on the interest point information of the historical interest point behavior and the current interest point information; determining the interest point score based on the time factor and relevance factor corresponding to the historical interest point behavior.

[0156] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can also be configured to execute: if the number of determined target historical interest point behaviors is less than a quantity threshold, then determining a number threshold of historical interest point behaviors from the historical interest point behavior set in order of interest point scores from high to low as the target historical interest point behaviors.

[0157] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can also be configured to execute: obtaining the point of interest information of the historical interest point behavior in the historical interest point behavior set; determining the importance factor corresponding to the historical interest point behavior based on the point of interest information of the historical interest point behavior and the current interest point information; and determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set in combination with the importance factor corresponding to the historical interest point behavior.

[0158] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set in combination with the importance factor corresponding to the historical interest point behavior can be configured to perform: determining the interest point score in combination with the importance factor corresponding to the historical interest point behavior; if the interest point score is greater than the score threshold, determining the historical interest point as the target historical interest point behavior corresponding to the current context.

[0159] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the interest point score in combination with the importance factor corresponding to the historical interest point behavior can be configured to perform: determining the relevance factor corresponding to the historical interest point behavior based on the interest point information of the historical interest point behavior and the current interest point information; and determining the interest point score in combination with the importance factor and the relevance factor corresponding to the historical interest point behavior.

[0160] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can be configured to execute: if the number of determined target historical interest point behaviors is less than a quantity threshold, then determining a number threshold of historical interest point behaviors from the historical interest point behavior set in order of interest point scores from high to low as the target historical interest point behaviors.

[0161] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can be configured to execute: obtaining the point of interest information of the historical interest point behavior in the historical interest point behavior set; determining the relevance factor corresponding to the historical interest point behavior based on the point of interest information of the historical interest point behavior and the current interest point information; determining the point of interest score based on the relevance factor corresponding to the historical interest point behavior; if the point of interest score is greater than the score threshold, determining the historical interest point as the target historical interest point behavior corresponding to the current context.

[0162] According to an exemplary embodiment of the present disclosure, the process of the historical behavior determination module 83 determining the target historical interest point behavior corresponding to the current context from the historical interest point behavior set can also be configured to execute: if the number of determined target historical interest point behaviors is less than a quantity threshold, then determining a number threshold of historical interest point behaviors from the historical interest point behavior set in order of interest point scores from high to low as the target historical interest point behaviors.

[0163] According to an exemplary embodiment of the present disclosure, the process of determining the importance factor by the historical behavior determination module 83 can be configured to perform: determining the probability and prior probability of the point of interest information of the historical point of interest behavior appearing in the current point of interest information; determining the amount of information corresponding to the historical point of interest behavior using the probability and prior probability; determining the initial importance factor corresponding to the historical point of interest behavior, and updating the initial importance factor using the information amount to determine the importance factor corresponding to the historical point of interest behavior.

[0164] According to an exemplary embodiment of the present disclosure, the process of determining the relevance factor by the historical behavior determination module 83 may be configured to execute: determining the similarity between the interest point information of the historical interest point behavior and the current interest point information as the relevance factor corresponding to the historical interest point behavior.

[0165] Since the functional modules of the device for determining points of interest in the embodiment of the present disclosure are the same as those in the above method implementation, they will not be described in detail here.

[0166] Fig.10 Schematic diagram of an electronic device suitable for implementing the exemplary embodiment of the present disclosure is shown. The terminal device of the exemplary embodiment of the present disclosure may be configured as follows Fig.10 It should be noted that Fig.10 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0167] The electronic device of the present disclosure includes at least a processor and a memory, wherein the memory is used to store one or more programs. When the one or more programs are executed by the processor, the processor can implement the method for determining points of interest of the exemplary embodiment of the present disclosure.

[0168] Specifically, Fig.10As shown, the electronic device 100 may include: a processor 1010, an internal memory 1021, an external memory interface 1022, a Universal Serial Bus (USB) interface 1030, a charging management module 1040, a power management module 1041, a battery 1042, an antenna 1, an antenna 2, a mobile communication module 1050, a wireless communication module 1060, an audio module 1070, a sensor module 1080, a display screen 1090, a camera module 1091, an indicator 1092, a motor 1093, a button 1094, and a Subscriber Identification Module (SIM) card interface 1095, etc. The sensor module 1080 may include a depth sensor, a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor, etc.

[0169] It is to be understood that the structure illustrated in the embodiment of the present disclosure does not constitute a specific limitation on the electronic device 100. In other embodiments of the present disclosure, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0170] The processor 1010 may include one or more processing units, for example, the processor 1010 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor and / or a neural network processor (NPU). Different processing units may be independent devices or integrated into one or more processors. In addition, a memory may be provided in the processor 1010 for storing instructions and data.

[0171] The electronic device 100 can realize the shooting function through the ISP, the camera module 1091, the video codec, the GPU, the display screen 1090 and the application processor. In some embodiments, the electronic device 100 may include 1 or N camera modules 1091, where N is a positive integer greater than 1. If the electronic device 100 includes N cameras, one of the N cameras is a main camera.

[0172] The internal memory 1021 can be used to store computer executable program codes, which include instructions. The internal memory 1021 can include a program storage area and a data storage area. The external memory interface 1022 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100.

[0173] The present disclosure also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or may exist independently without being assembled into the electronic device.

[0174] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0175] Computer-readable storage media can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0176] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device implements the method described in the embodiments of the present disclosure.

[0177] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0178] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0179] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0180] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0181] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0182] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing what is disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be considered merely as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

[0183] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining points of interest, characterized in that: include: Acquire a current context, wherein the current context includes current time information and current point of interest information; Determining a target historical point of interest behavior corresponding to the current context; Generate prompt text using the current context, the target historical point of interest behavior and the user portrait; The prompt text is input into a large language model to determine a point of interest prediction result.

2. The method for determining points of interest according to claim 1, characterized in that: Determining a target historical point of interest behavior corresponding to the current context includes: A target historical point of interest behavior corresponding to the current context is determined from the historical point of interest behavior set.

3. The method for determining points of interest according to claim 2, characterized in that: The method for determining points of interest further includes: For historical user location coordinates, determining time information corresponding to the user location coordinates; Converting the user location coordinates into point of interest information; Constructing historical point-of-interest behaviors using the point-of-interest information and the corresponding time information; A set of all the historical interest point behaviors in history is determined as the historical interest point behavior set.

4. The method for determining points of interest according to claim 2, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set includes: Acquire time information of historical interest point behaviors in the historical interest point behavior set; Determine a time difference between the current time information and the time information of the historical point of interest behavior, and determine a time factor corresponding to the historical point of interest behavior according to the time difference, wherein the time factor is negatively correlated with the time difference; A target historical point of interest behavior corresponding to the current context is determined from the historical point of interest behavior set in combination with a time factor corresponding to the historical point of interest behavior.

5. The method for determining points of interest according to claim 4, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set in combination with a time factor corresponding to the historical point of interest behavior includes: Determine the interest point score in combination with the time factor corresponding to the historical interest point behavior; If the interest point score is greater than a score threshold, the historical interest point is determined as a target historical interest point behavior corresponding to the current context.

6. The method for determining points of interest according to claim 5, characterized in that: Determining the interest point score in combination with the time factor corresponding to the historical interest point behavior includes: Determining an importance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; The interest point score is determined based on the time factor and the importance factor corresponding to the historical interest point behavior.

7. The method for determining points of interest according to claim 6, characterized in that: Determining the score of the point of interest by combining the time factor and the importance factor corresponding to the historical point of interest behavior includes: Determining a relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; The interest point score is determined based on the time factor, importance factor and relevance factor corresponding to the historical interest point behavior.

8. The method for determining points of interest according to claim 5, characterized in that: Determining the interest point score in combination with the time factor corresponding to the historical interest point behavior includes: Determining a relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; The interest point score is determined based on the time factor and the relevance factor corresponding to the historical interest point behavior.

9. The method for determining points of interest according to any one of claims 5 to 8, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set further includes: If the determined number of the target historical interest point behaviors is less than a quantity threshold, the threshold number of historical interest point behaviors are determined from the historical interest point behavior set in descending order of the interest point scores as the target historical interest point behaviors.

10. The method for determining points of interest according to claim 2, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set includes: Obtaining point of interest information of historical point of interest behaviors in the historical point of interest behavior set; Determining an importance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; The target historical point of interest behavior corresponding to the current context is determined from the historical point of interest behavior set in combination with the importance factor corresponding to the historical point of interest behavior.

11. The method for determining points of interest according to claim 10, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set in combination with the importance factor corresponding to the historical point of interest behavior includes: Determine the interest point score based on the importance factor corresponding to the historical interest point behavior; If the interest point score is greater than a score threshold, the historical interest point is determined as a target historical interest point behavior corresponding to the current context.

12. The method for determining points of interest according to claim 11, characterized in that: Determining the score of the point of interest in combination with the importance factor corresponding to the historical point of interest behavior includes: Determining a relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; The interest point score is determined by combining the importance factor and the relevance factor corresponding to the historical interest point behavior.

13. The method for determining points of interest according to any one of claims 10 to 12, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set further includes: If the determined number of the target historical interest point behaviors is less than a quantity threshold, the threshold number of historical interest point behaviors are determined from the historical interest point behavior set in descending order of the interest point scores as the target historical interest point behaviors.

14. The method for determining points of interest according to claim 2, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set includes: Obtaining point of interest information of historical point of interest behaviors in the historical point of interest behavior set; Determining a relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information; Determining a point of interest score according to a relevance factor corresponding to the historical point of interest behavior; If the interest point score is greater than a score threshold, the historical interest point is determined as a target historical interest point behavior corresponding to the current context.

15. The method for determining points of interest according to claim 14, characterized in that: Determining a target historical point of interest behavior corresponding to the current context from the historical point of interest behavior set further includes: If the determined number of the target historical interest point behaviors is less than a quantity threshold, the threshold number of historical interest point behaviors are determined from the historical interest point behavior set in descending order of the interest point scores as the target historical interest point behaviors.

16. The method for determining points of interest according to claim 6 or 10, characterized in that: Determining the importance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information includes: Determine the probability and prior probability that the point of interest information of the historical point of interest behavior appears in the current point of interest information; Determine the amount of information corresponding to the historical point of interest behavior using the probability and the prior probability; An initial importance factor corresponding to the historical point of interest behavior is determined, and the initial importance factor is updated using the amount of information to determine the importance factor corresponding to the historical point of interest behavior.

17. The method for determining points of interest according to claim 7, 8, 12 or 14, characterized in that: Determining the relevance factor corresponding to the historical point of interest behavior according to the point of interest information of the historical point of interest behavior and the current point of interest information includes: The similarity between the point of interest information of the historical point of interest behavior and the current point of interest information is determined as a relevance factor corresponding to the historical point of interest behavior.

18. A device for determining points of interest, characterized in that: include: A context acquisition module, used to acquire a current context, wherein the current context includes current time information and current point of interest information; A historical behavior determination module, used to determine a target historical point of interest behavior corresponding to the current context; A prompt text generation module, used to generate prompt text using the current context, the target historical point of interest behavior and the user portrait; The result determination module is used to input the prompt text into a large language model to determine the interest point prediction result.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining points of interest according to any one of claims 1 to 17 is implemented.

20. An electronic device, characterized in that: include: processor; A memory for storing one or more programs, wherein when the one or more programs are executed by the processor, the processor implements the method for determining a point of interest according to any one of claims 1 to 17.

Images