Object recommendation method and apparatus, computer device, and readable storage medium

Abstract

The application relates to an object recommendation method and device, computer equipment and a readable storage medium. The method comprises the following steps: obtaining first physiological data and first attribute data of a first object using a target application, and second physiological data and second attribute data of a second object using the target application; determining an interest matching degree between the first object and the second object according to the first physiological data and the second physiological data; determining an attribute matching degree between the first object and the second object according to the first attribute data and the second attribute data; determining a target matching degree based on the attribute matching degree and the interest matching degree; and screening a target object from the second object according to the target matching degree, and recommending the target object to the first object. The method can effectively solve the defects that a traditional marriage platform depends on subjective information and lacks real-time data support, and more accurate and personalized marriage matching is realized.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an object recommendation method, apparatus, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] Existing platforms primarily match users based on subjective information such as their interests and hobbies, lacking objective data analysis of their physical and mental states. This results in incomplete and inappropriate matching results. They also fail to capture users' emotions and physical states (such as heart rate and HRV) in real time, making it difficult to dynamically adjust recommendation strategies. This results in inadequate timeliness and accuracy in matching results. These issues significantly impact the accuracy and user experience of existing dating platforms. Summary of the Invention

[0003] Based on this, it is necessary to provide an object recommendation method, apparatus, computer device, computer-readable storage medium and computer program product that can improve the timeliness and accuracy of matching in order to address the above technical problems.

[0004] In a first aspect, the present application provides an object recommendation method, comprising:

[0005] Acquiring first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0006] determining, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object;

[0007] determining an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0008] determining a target matching degree based on the attribute matching degree and the interest matching degree;

[0009] A target object is selected from the second object according to the target matching degree, and the target object is recommended to the first object.

[0010] In one embodiment, the target application includes a plurality of interactive items; determining the interest matching degree between the first object and the second object based on the first physiological data and the second physiological data includes:

[0011] For each interactive item, based on the first physiological data of the first object when operating the interactive item, the first interest score of the first object in the interactive item is determined; based on the second physiological data of the second object when operating the interactive item, the second interest score of the second object in the interactive item is determined; based on the first interest score and the second interest score, the interest matching degree between the first object and the second object is determined.

[0012] In one embodiment, determining the interest matching between the first object and the second object based on the first interestingness score and the second interestingness score includes:

[0013] Based on the first interest score of the first object in each interactive item, determine the average first interest score; based on the average first interest score and the first interest score of the first object in the interactive item, determine the deviation value of the first interest score of the first object in the interactive item; based on the second interest score of the second object in each interactive item, determine the average second interest score; based on the average second interest score and the second interest score of the second object in the interactive item, determine the deviation value of the second interest score of the second object in the interactive item; based on the first interest score deviation value and the second interest score deviation value, determine the interest matching degree between the first object and the second object.

[0014] In one embodiment, determining the attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data includes:

[0015] For each type of attribute data, determine the attribute weight parameter corresponding to the targeted type of attribute data; obtain the reference attribute matching degree between the first object and the second object; determine the first data belonging to the targeted type of attribute data in the first attribute data; determine the second data belonging to the targeted type of attribute data in the second attribute data; based on the first data, the second data, the attribute weight parameter and the reference attribute matching degree, determine the attribute matching degree between the first object and the second object.

[0016] In one embodiment, determining the attribute matching degree between the first object and the second object based on the first data, the second data, the attribute weight parameter, and the reference attribute matching degree includes:

[0017] Based on the first data and the second data, determine the deviation of the attribute data of the category; based on the sum of the squares of the deviations of the first object and the second object on each attribute data and the attribute weight parameter corresponding to each attribute data, determine the weighted Euclidean distance between the first object and the second object; and use the ratio between the weighted Euclidean distance and the reference attribute matching degree as the attribute matching degree between the first object and the second object.

[0018] In one embodiment, determining the target matching degree based on the attribute matching degree and the interest matching degree includes:

[0019] Obtain an attribute matching weight parameter, where the attribute matching weight parameter is used to characterize the importance of the attribute matching; obtain an interest matching weight parameter, where the interest matching weight parameter is used to characterize the importance of the interest matching; linearly combine the attribute matching weight parameter, the interest matching weight parameter, the attribute matching, and the interest matching to obtain a target matching between the first object and the second object.

[0020] In a second aspect, the present application further provides an object recommendation device, comprising:

[0021] an acquisition module, configured to acquire first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0022] a first determining module, configured to determine an interest matching degree between the first object and the second object based on the first physiological data and the second physiological data;

[0023] a second determining module, configured to determine an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0024] A third determining module, configured to determine a target matching degree based on the attribute matching degree and the interest matching degree;

[0025] A recommendation module is used to filter a target object from the second object according to the target matching degree, and recommend the target object to the first object.

[0026] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] Acquiring first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0028] determining, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object;

[0029] determining an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0030] determining a target matching degree based on the attribute matching degree and the interest matching degree;

[0031] A target object is selected from the second object according to the target matching degree, and the target object is recommended to the first object.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0033] Acquiring first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0034] determining, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object;

[0035] determining an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0036] determining a target matching degree based on the attribute matching degree and the interest matching degree;

[0037] A target object is selected from the second object according to the target matching degree, and the target object is recommended to the first object.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0039] Acquiring first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0040] determining, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object;

[0041] determining an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0042] determine a target matching degree based on the attribute matching degree and the interest matching degree;

[0043] screen a target object from the second object according to the target matching degree, and recommend the target object to the first object.

[0044] The object recommendation method, device, computer device, computer readable storage medium, and computer program product break through the limitation of traditional platforms that only rely on subjective information filling by introducing objective physiological indicators as matching basis. The interest matching degree between the first object and the second object is determined according to the first physiological data and the second physiological data. The user's interest (for example, interaction preference under stress) is indirectly inferred through physiological data, which supplements the deficiency of relying on subjective scoring alone. The attribute matching degree between the first object and the second object is determined according to the first attribute data and the second attribute data, which effectively improves the precision of attribute matching. The target matching degree is determined based on the attribute matching degree and the interest matching degree. The limitation of a single data source is broken through by introducing dynamic physiological data and static attribute data. Finally, the target object is screened from the second object according to the target matching degree, and the target object is recommended to the first object. The defects of traditional marriage platforms that rely on subjective information and lack of real-time data support are effectively solved, and more accurate and personalized marriage matching is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0046] Figure 1 An application environment diagram of an object recommendation method in an embodiment;

[0047] Figure 2 A flowchart of an object recommendation method in an embodiment;

[0048] Figure 3 A structural block diagram of an object recommendation device in an embodiment;

[0049] Figure 4 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0050] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0051] The object recommendation method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 is used to generate an object recommendation request and send the object recommendation request to the server 104, so that the server 104 screens a target object from the second object according to a target matching degree and recommends the target object to the first object. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0052] In an exemplary embodiment, as shown in Figure 2 , an object recommendation method is provided. The method is applied to the server 104 in Figure 1 for example, and includes the following steps 202 to 210. Wherein:

[0053] Step 202, obtaining first physiological data and first attribute data of a first object using a target application, and second physiological data and second attribute data of a second object using the target application.

[0054] The first object refers to a user who is using the target application. In the present application, this first object is an individual who hopes to find a matching object.

[0055] The target application refers to a marriage, love and friendship platform or application program, on which a user can fill in personal information, participate in psychological evaluation, wear a smart bracelet, etc., so that the platform can collect data and make matching recommendations.

[0056] The first physiological data refers to data about the physical and physiological state of the first subject, including but not limited to heart rate, heart rate variability (HRV), body temperature, sleep quality, and other data collected by devices such as smart bracelets.

[0057] The first attribute data refers to the psychological data and health data of the first subject. Optionally, the psychological data can be obtained through psychological assessments on dating platforms or applications. The health data can be obtained through physical examination reports.

[0058] Second objects refer to other users on the target application who participate in the matching process with the first object. The first object may be recommended to these second objects, or these second objects may be recommended to the first object.

[0059] The second physiological data refers to data about the physical and physiological state of the second subject, similar to the first physiological data, including but not limited to heart rate, HRV, body temperature, sleep quality, etc.

[0060] Secondary attribute data refers to the psychological and health data of the first subject. Similarly, psychological data can be obtained through psychological assessments on dating platforms or apps. Health data can be obtained through physical examination reports.

[0061] Specifically, wearable devices such as smart bracelets collect real-time physiological data such as the first person's heart rate, heart rate variability (HRV), body temperature, and sleep quality. Data is recorded and analyzed in different interaction scenarios (such as viewing the other person's profile, chatting with the other person, and meeting in person). Furthermore, psychological assessment questionnaires on dating platforms are used to obtain the first person's psychological characteristics, including personality, interests, and skills. Health data such as body fat percentage, BMI, blood pressure, and blood sugar are obtained through physical examination reports or other health monitoring tools.

[0062] Similarly, wearable devices such as smart bracelets collect real-time physiological data from the second person, including heart rate, heart rate variability (HRV), body temperature, and sleep quality. Data is recorded and analyzed in different interaction scenarios (such as viewing the other person's profile, chatting with the other person, and meeting in person). Furthermore, psychological assessment questionnaires on dating platforms are used to obtain the second person's psychological characteristics, including personality, interests, and skills. Health data such as body fat percentage, BMI, blood pressure, and blood sugar are collected through physical examination reports or other health monitoring tools.

[0063] Optionally, the psychological assessment data of the first and second subjects are preprocessed to extract characteristics such as personality, interests, and skills. Furthermore, the heart rate and HRV data of the first and second subjects are filtered and feature extracted, such as changes in heart rate variability.

[0064] Step 204 : Determine the interest matching degree between the first object and the second object based on the first physiological data and the second physiological data.

[0065] Interest matching refers to inferring and matching a user's interests and emotional state based on their physiological and behavioral data. It's understandable that this physiological data can reflect a user's emotional state. For example, changes in heart rate can be related to a user's level of excitement or nervousness. By analyzing this data, it's possible to infer a user's interests and emotional reactions in specific situations. Furthermore, in different interaction scenarios (such as viewing a person's profile, chatting with them, or meeting them in person), a user's physiological data can reveal their interests and reactions to different types of interactions. For example, an increased heart rate while viewing a person's profile may indicate interest in that person.

[0066] Specifically, by comparing the physiological data characteristics of the first and second subjects in the same or similar interaction scenarios, the emotional compatibility between the two is calculated. For example, if two people show an increased heart rate when viewing each other's profile, this may indicate that they have a high degree of emotional compatibility.

[0067] Optionally, the emotional match can be combined with other factors (such as long-term interests, behavioral habits, etc.) to form a comprehensive interest match. This comprehensive match can more comprehensively reflect the interest and emotional match between users.

[0068] Step 206: Determine the attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data.

[0069] Attribute matching refers to the evaluation of the degree of compatibility between two users based on their static attribute data (such as psychological characteristics and health data). This attribute data can help the system understand the user's personality, interests, and health status, and thus determine whether they are suitable for each other.

[0070] Specifically, the psychological compatibility between the first and second subjects is calculated by comparing their psychological characteristics. Optionally, a similarity calculation method (such as the Pearson correlation coefficient) is used to quantify the degree of psychological compatibility. Similarly, the health compatibility between the first and second subjects is calculated by comparing their health indicators. Optionally, methods such as weighted Euclidean distance are used to calculate the degree of health compatibility.

[0071] Optionally, the psychological feature matching degree and the health feature matching degree are combined to form a comprehensive attribute matching degree. For example, the matching degrees of different features are weighted and summed using a weighted model to obtain the final attribute matching degree.

[0072] Step 208: Determine the target matching degree based on the attribute matching degree and the interest matching degree.

[0073] Among them, target matching is a comprehensive indicator used to measure the compatibility of two users across multiple dimensions. It not only considers the user's interests and emotional responses (assessed through physiological data), but also the user's psychological characteristics and health status (assessed through attribute data).

[0074] Specifically, the interest matching degree and attribute matching degree are comprehensively calculated through a weighted model to obtain the target matching degree. The calculation formula of the target matching degree is as follows:

[0075] Target matching = A × interest matching + B × attribute matching.

[0076] Or goal matching = A × interest matching + B × psychological characteristic matching + C × health characteristic matching.

[0077] Step 210 : Filter target objects from the second object according to the target matching degree, and recommend the target objects to the first object.

[0078] The target user refers to another user (i.e., the second user) who is most suitable for the current user (i.e., the first user) as determined by the recommendation algorithm. The target user is selected based on a comprehensive analysis and matching of the multi-dimensional data (including physiological, psychological, and health data) of the first and second users.

[0079] Specifically, first, a target matching threshold is set based on the system's requirements and recommendation strategy. Only those secondary objects whose target matching exceeds this threshold are considered potential target objects. All secondary objects are sorted from high to low by target matching. The top N objects with the highest target matching are further selected as candidate target objects. The value of N can be adjusted based on the system's recommendation capacity and user needs. Recommendation information is then prepared, including the candidate target object's basic information, interests, hobbies, psychological characteristics, and health data. This ensures that the recommendation information is both comprehensive and protects user privacy. The list of selected target objects is then presented to the first subject. For example, these target objects are recommended to the first subject through the interface or notification of the dating platform.

[0080] Optionally, collect feedback from the first user on the recommended match, such as number of views and chat interactions. Analyze this user feedback to assess recommendation effectiveness and user satisfaction. Dynamically adjust the recommendation algorithm and matching strategy based on user feedback and matching results. Continuously optimize the system to improve matching success rates and user experience.

[0081] In one embodiment, for each interactive item, a first interest score of the first object in the interactive item is determined based on first physiological data of the first object when operating the interactive item; a second interest score of the second object in the interactive item is determined based on second physiological data of the second object when operating the interactive item; and a degree of interest matching between the first object and the second object is determined based on the first interest score and the second interest score.

[0082] Interactive activities refer to the different types of interactive activities users can engage in on dating platforms. These activities can include various platform features or scenarios where users can interact with potential matches. Optional interactive activities include viewing profiles, sending messages, making video calls, and participating in online or offline events.

[0083] The first interest score refers to the interest score of the first subject when participating in a certain interactive project. This score is determined based on the first subject's physiological data (such as heart rate, heart rate variability HRV, etc.) during the interactive project.

[0084] The second interest score refers to the interest score of the second subject when participating in a certain interactive project. This score is determined based on the physiological data of the second subject in the interactive project.

[0085] Specifically, we first identify all the interactive items included in the dating platform. These items can include viewing a person's profile, sending messages, making video calls, and participating in online or offline events. Each interactive item represents a specific type of interaction that users can perform on the platform.

[0086] Then, during each interactive activity, the first subject's physiological data, such as heart rate and heart rate variability (HRV), is collected in real time. The first subject's physiological responses are recorded as they operate each interactive activity. Similarly, during each interactive activity, the second subject's physiological data, such as heart rate and heart rate variability (HRV), is collected in real time. The second subject's physiological responses are recorded as they operate each interactive activity.

[0087] Next, based on the first subject's physiological data for each interactive item, an interest score is calculated. For example, if the first subject's heart rate increases when viewing a person's profile, they are considered interested in that person and given a higher interest score. Similarly, based on the second subject's physiological data for each interactive item, their interest score is calculated. For example, if the second subject's heart rate increases when receiving a message from someone, they are considered interested in that message and given a higher interest score.

[0088] Finally, for each interactive item, the interest scores of the first and second subjects are compared. If both have high and similar interest scores, they are considered to have a high degree of interest compatibility in this interactive item. The interest compatibility scores across all interactive items are comprehensively evaluated to arrive at an overall interest compatibility score. This overall interest compatibility score reflects the overall degree of interest compatibility between the first and second subjects across different interactive items.

[0089] By dynamically assessing users' interests and emotional responses to interactive projects based on physiological data, we can provide more accurate dating recommendations. This approach not only considers users' static interests but also incorporates real-time physiological responses, improving the timeliness and accuracy of matching.

[0090] In one embodiment, based on the first interest score of the first object in each interactive item, an average first interest score is determined; based on the average first interest score and the first interest score of the first object in the interactive item, a deviation value of the first interest score of the first object in the interactive item is determined; based on the second interest score of the second object in each interactive item, an average second interest score is determined; based on the average second interest score and the second interest score of the second object in the interactive item, a deviation value of the second interest score of the second object in the interactive item is determined; and based on the first interest score deviation value and the second interest score deviation value, the interest matching degree between the first object and the second object is determined.

[0091] The first interest score mean refers to the average of the first subject's interest scores across all interactive items. The first interest score deviation refers to the difference between the first subject's interest score in a specific interactive item and its mean interest score. The second interest score mean refers to the average of the second subject's interest scores across all interactive items. The second interest score deviation refers to the difference between the second subject's interest score in a specific interactive item and its mean interest score.

[0092] Specifically, first, the interest scores of the first subject in all interactive items are collected. The interest scores of the first subject in each interactive item are averaged to obtain a mean first interest score. For each interactive item, the deviation of the first subject's interest score in that item from its mean is calculated.

[0093] Similarly, collect the interest scores of the second subject in all interactive items. Average the interest scores of the second subject in each interactive item to obtain a mean second interest score. For each interactive item, calculate the deviation of the second subject's interest score in that item from its mean.

[0094] Then, for each interactive item, the deviation between the first and second subjects' interest scores is compared. If the deviations are similar and have the same sign (i.e., both subjects show high interest in a particular interactive item), they are considered to have a high degree of interest compatibility in that interactive item. The interest compatibility scores for all interactive items are comprehensively evaluated to produce an overall interest compatibility score. This overall interest compatibility score reflects the overall degree of interest compatibility between the first and second subjects across different interactive items.

[0095] Optional, S(u, v) = / (F1×F2)

[0096] F1=

[0097] F2=

[0098] Where S(u, v) is the interest match between the first and second objects. Ru,i is the first interest score of the first object in the interactive item. Rv,i is the first interest score of the second object in the interactive item. R^u is the mean of the first interest score. R^v is the mean of the second interest score. I represents all interactive items.

[0099] By calculating the mean and deviation of interest scores, we can more accurately capture changes in user interest in specific interactive items. This refined analysis helps identify users' true interests in specific contexts, thereby improving matching accuracy. Furthermore, interest matching calculated based on real-time physiological data allows for dynamic adjustment of matching strategies. As user interests change, recommendation results can be adjusted promptly to ensure that recommended items always align with the user's current interests.

[0100] In one embodiment, for each type of attribute data, an attribute weight parameter corresponding to the targeted type of attribute data is determined; a reference attribute matching degree between a first object and a second object is obtained; first data belonging to the targeted type of attribute data is determined in the first attribute data; second data belonging to the targeted type of attribute data is determined in the second attribute data; and the attribute matching degree between the first object and the second object is determined based on the first data, the second data, the attribute weight parameter and the reference attribute matching degree.

[0101] Each type of attribute data refers to different types of static attribute data used to assess user compatibility. This attribute data typically includes psychological characteristics and health data. For example, psychological characteristics include personality type and interests and hobbies; health data includes body fat percentage, BMI, blood pressure, blood sugar levels, etc.

[0102] Attribute weight parameters are numerical values ​​used to adjust the importance of different attribute data in the match calculation. These weights reflect the importance the system places on different attributes. By adjusting the weights, you can prioritize certain attributes based on actual needs and scenarios. For example, if health compatibility is considered very important, health data might be given a higher weight.

[0103] The reference attribute match is the initial match calculated based on the attribute data of the first and second objects in the absence of a specific interaction item. This match provides a benchmark for subsequent dynamic adjustments. Optionally, the reference attribute match is the maximum possible attribute match value, a predefined constant used to normalize the attribute match between the first and second objects to fall within a specific range (e.g., between 0 and 1).

[0104] First data refers to the specific values ​​or characteristics of the first subject within a specific attribute data category. This data is extracted from the first subject's attribute data set. For example, if the attribute data is health data, the first data may include specific values ​​such as the first subject's body fat percentage or BMI.

[0105] Secondary data refers to the specific values ​​or characteristics of the second subject within a specific attribute data category. This data is extracted from the attribute data set of the second subject. For example, if the attribute data is health data, the secondary data may include specific values ​​such as the second subject's body fat percentage or BMI.

[0106] Specifically, the system first identifies the different attribute data categories used to assess user matching. Weight parameters, known as attribute weight parameters, are assigned to the attribute data in each attribute category. These attribute weight parameters reflect the importance the system places on different attributes. The maximum possible attribute matching degree is then used as a predefined reference attribute matching degree, which is then used to normalize the matching degree to fall within a specific range (e.g., between 0 and 1).

[0107] Specific values ​​or features belonging to a specific attribute category are then extracted from the attribute dataset of the first object, and specific values ​​or features belonging to the same attribute category are extracted from the attribute dataset of the second object. Furthermore, based on the first data, the second data, the attribute weight parameters, and the reference attribute matching degree, the attribute matching degree between the first object and the second object is calculated. Optionally, a weighted Euclidean distance or other method can be used to calculate the matching degree to ensure that the matching degree comprehensively considers all relevant attributes.

[0108] Finally, the first and second data are combined with the weight parameters to calculate the matching degree for each attribute category. These matching degrees are then combined to obtain the final attribute matching degree. Through the above steps, a comprehensive and accurate attribute matching degree can be calculated by comprehensively considering the data of the first and second objects in different attribute categories, combining the weight parameters and the initial matching degree. This method ensures that the matching degree calculation is both comprehensive and flexible, adapting to the needs of different users and scenarios.

[0109] In one embodiment, based on the first data and the second data, the deviation of the attribute data of the target category is determined; based on the sum of the squares of the deviations of the first object and the second object on each attribute data and the attribute weight parameter corresponding to each attribute data, the weighted Euclidean distance between the first object and the second object is determined; and the ratio between the weighted Euclidean distance and the reference attribute matching degree is used as the attribute matching degree between the first object and the second object.

[0110] The deviation refers to the difference between the first object and the second object in a certain attribute data, which is expressed as the difference in the numerical values ​​of the two objects in the attribute data.

[0111] The sum of squared deviations is the sum of all squared deviations across multiple attribute data. It measures the overall difference between two objects across all attributes. As you can understand, for each attribute data, the squared deviation is calculated, and then the squared deviations of all attributes are summed to obtain the sum of squared deviations.

[0112] Weighted Euclidean distance refers to a distance measurement method that takes into account the importance (weight) of different attributes. The total distance is obtained by multiplying the square of the deviation of each attribute by its corresponding weight, summing the results, and then taking the square root.

[0113] Specifically, for each attribute data, the deviation between the first and second objects on that attribute is calculated. For example, if the attribute is body fat percentage, the deviation is the first object's body fat percentage minus the second object's body fat percentage. Then, for each attribute data, the square of the deviation is calculated, and the square of the deviation of each attribute data is multiplied by its corresponding attribute weight parameter. Finally, based on the weighted sum of the squared deviations, the weighted Euclidean distance between the first and second objects is calculated. This weighted Euclidean distance is then compared to the reference attribute matching degree to calculate a ratio. The calculated attribute matching degree is then output as an input parameter for the matching algorithm.

[0114] Optional, H(u, v) = 1- / max (H)

[0115] Where H(u, v) is the attribute matching degree between the first object and the second object (including health attribute matching degree and psychological attribute matching degree). hu,k is the first data (the specific data of the first object in the targeted category of psychological attribute data or the specific data of the first object in the targeted category of psychological attribute data). hv,k is the second data (the specific data of the second object in the targeted category of psychological attribute data or the specific data of the second object in the targeted category of psychological attribute data). Wk is the attribute weight parameter corresponding to the targeted category of attribute data (including health attribute weight parameter and psychological attribute weight parameter). max(H) is the reference attribute matching degree between the first object and the second object, that is, the maximum possible value of the predefined attribute matching degree (including reference health attribute matching degree and reference psychological attribute matching degree).

[0116] Because the consideration of attribute data differences encompasses multiple types of attributes, the match calculation is not limited to a single dimension of information, thus providing a more comprehensive reflection of the compatibility between two objects. Furthermore, the weighted Euclidean distance calculation integrates differences across multiple attributes, expressing the relative position of two objects in attribute space through the concept of distance. This facilitates comparison of the degree of compatibility between different pairs of objects. For example, the smaller the weighted Euclidean distance between two objects, the smaller the overall difference in their attributes, and the higher the potential compatibility.

[0117] In one embodiment, an attribute matching weight parameter is obtained, and the attribute matching weight parameter is used to characterize the importance of the attribute matching; an interest matching weight parameter is obtained, and the interest matching weight parameter is used to characterize the importance of the interest matching; the attribute matching weight parameter, the interest matching weight parameter, the attribute matching degree, and the interest matching degree are linearly combined to obtain a target matching degree between the first object and the second object.

[0118] The attribute matching weight parameter is a numerical value that represents the importance of attribute matching in the final target matching calculation. It reflects the importance the system places on the user's static attribute data (such as psychological characteristics and health data) in the matching evaluation.

[0119] The interest match weight parameter is a numerical value used to represent the importance of interest match in the final target match calculation. It reflects the importance the system places on users' dynamic interest data (such as interests and hobbies derived from interactive projects or behavioral data analysis) in the match assessment.

[0120] Specifically, the value of the attribute matching weight parameter is first obtained. This value can be a pre-set constant or a variable that is dynamically adjusted based on different user groups or scenarios. Similarly to the method for obtaining the attribute matching weight parameter, this value can also be fixed or dynamically adjusted based on the value of the interest matching weight parameter.

[0121] Then it is determined to use the linear combination method to calculate the target matching degree. The formula of the linear combination is: target matching degree = (attribute matching degree weight parameter × attribute matching degree) + (interest matching degree weight parameter × interest matching degree).

[0122] Finally, the obtained attribute matching weight parameter and interest matching weight parameter, as well as the specific values ​​of the calculated attribute matching and interest matching, are substituted into the above formula. This calculation results in a target matching degree between the first object and the second object. This target matching degree comprehensively considers both attribute matching and interest matching factors, and performs a reasonable weighted calculation based on their respective weight parameters, thereby more comprehensively and accurately reflecting the degree of match between the two objects.

[0123] Optional, M(u, v) = A × S(u, v) + B × H(u, v)

[0124] Or M(u,v)=A×S(u,v)+B1×H1(u,v)+B2×H2(u,v)

[0125] Where M(u, v) is the target matching degree. S(u, v) is the attribute matching degree. H(u, v) is the interest matching degree. A is the attribute matching degree weight parameter. B is the interest matching degree weight parameter. H1(u, v) is the health attribute matching degree. H2(u, v) is the psychological attribute matching degree. B1 is the health attribute weight parameter. B2 is the psychological attribute weight parameter.

[0126] Since different users may place different emphasis on attributes and interests in dating, setting attribute matching weight parameters and interest matching weight parameters separately can flexibly adapt to the needs of various users.

[0127] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0128] Based on the same inventive concept, embodiments of the present application also provide an object recommendation device for implementing the object recommendation method described above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more of the object recommendation device embodiments provided below can be found in the above-mentioned limitations on the object recommendation method and will not be repeated here.

[0129] In an exemplary embodiment, Figure 3 As shown, an object recommendation device 300 is provided, comprising: an acquisition module 302, a first determination module 304, a second determination module 306, a third determination module 308 and a recommendation module 310, wherein:

[0130] An acquisition module 302 is configured to acquire first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application;

[0131] A first determining module 304 is configured to determine an interest matching degree between the first object and the second object based on the first physiological data and the second physiological data;

[0132] A second determining module 306 is configured to determine an attribute matching degree between the first object and the second object based on the first attribute data and the second attribute data;

[0133] The third determination module 308 is used to determine the target matching degree based on the attribute matching degree and the interest matching degree;

[0134] The recommendation module 310 is configured to filter a target object from the second object according to the target matching degree, and recommend the target object to the first object.

[0135] In one embodiment, the first determination module 304 is used to determine, for each interactive item, a first interest score of the first object in the interactive item based on the first physiological data of the first object when operating the interactive item; determine a second interest score of the second object in the interactive item based on the second physiological data of the second object when operating the interactive item; and determine the interest matching degree between the first object and the second object based on the first interest score and the second interest score.

[0136] In one embodiment, the first determination module 304 is used to determine an average first interest score based on the first interest score of the first object in each interactive item; determine a deviation value of the first interest score of the first object in the interactive item based on the average first interest score and the first interest score of the first object in the interactive item; determine an average second interest score based on the second interest score of the second object in each interactive item; determine a deviation value of the second interest score of the second object in the interactive item based on the average second interest score and the second interest score of the second object in the interactive item; and determine the interest matching degree between the first object and the second object based on the first interest score deviation value and the second interest score deviation value.

[0137] In one embodiment, the second determination module 306 is used to determine, for each type of attribute data, an attribute weight parameter corresponding to the targeted type of attribute data; obtain a reference attribute matching degree between the first object and the second object; determine first data belonging to the targeted type of attribute data in the first attribute data; determine second data belonging to the targeted type of attribute data in the second attribute data; and determine the attribute matching degree between the first object and the second object based on the first data, the second data, the attribute weight parameter and the reference attribute matching degree.

[0138] In one embodiment, the second determination module 306 is used to determine the deviation of the attribute data of the category based on the first data and the second data; determine the weighted Euclidean distance between the first object and the second object based on the sum of the squares of the deviations of the first object and the second object on each attribute data and the attribute weight parameter corresponding to each attribute data; and use the ratio between the weighted Euclidean distance and the reference attribute matching degree as the attribute matching degree between the first object and the second object.

[0139] In one embodiment, the third determination module 308 is used to obtain an attribute matching weight parameter, which is used to characterize the importance of the attribute matching; obtain an interest matching weight parameter, which is used to characterize the importance of the interest matching; and linearly combine the attribute matching weight parameter, the interest matching weight parameter, the attribute matching degree, and the interest matching degree to obtain a target matching degree between the first object and the second object.

[0140] Each module in the object recommendation device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0141] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data related to object recommendation. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an object recommendation method is implemented.

[0142] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0143] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0144] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0145] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0146] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0147] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0148] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0149] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An object recommendation method, characterized in that: The method comprises: Obtaining first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application; the first attribute data and the second attribute data include psychological data obtained through a psychological assessment and health data obtained through a physical examination; the psychological data includes at least personality type and interests and hobbies; the health data includes at least body fat percentage, BMI, blood pressure, and blood sugar level; determining, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object; For each type of attribute data, determine the attribute weight parameter corresponding to the type of attribute data; determining first data belonging to the targeted category of attribute data in the first attribute data; determining second data belonging to the targeted category of attribute data in the second attribute data; Determining a deviation of the category attribute data based on the first data and the second data; Determining a weighted Euclidean distance between the first object and the second object based on a sum of squared deviations of the first object and the second object on each attribute data and an attribute weight parameter corresponding to each attribute data; The ratio between the weighted Euclidean distance and the reference attribute matching degree is used as the attribute matching degree between the first object and the second object; the reference attribute matching degree refers to an initial matching degree calculated based on the attribute data of the first object and the second object in the absence of a specific interactive item; determining a target matching degree based on the attribute matching degree and the interest matching degree; screening a target object from the second object according to the target matching degree, and recommending the target object to the first object; Collecting feedback data from the first subject on the recommended subject, analyzing the feedback data to evaluate the recommendation effect and user satisfaction, and dynamically adjusting the recommendation algorithm and matching strategy based on user feedback and matching results; The target application includes multiple interactive items; the multiple interactive items include at least one of viewing the other party's personal profile, sending messages, making video calls, and participating in online or offline activities; and determining the interest matching degree between the first object and the second object based on the first physiological data and the second physiological data includes: For each interactive item, determining a first interest score of the first object in the interactive item based on the first physiological data of the first object when operating the interactive item; determining a second interest score of the second object in the interactive item based on second physiological data of the second object when operating the interactive item; Based on the first interest score and the second interest score, and by the formula S(u, v)= / (F1×F2), determining the interest matching degree between the first object and the second object; Where F1= ; F2= ； Score the first interest level of the first subject in the interactive item i; Score the second interest level of the second object in the interactive item i; is the mean of the first interest rating; is the mean of the second interest rating; I is all interactive items; The method of determining a weighted Euclidean distance between the first object and the second object based on the sum of squared deviations of the first object and the second object on each attribute data and an attribute weight parameter corresponding to each attribute data, and using a ratio between the weighted Euclidean distance and a reference attribute matching degree as the attribute matching degree between the first object and the second object, includes: By the formula H(u, v) = 1- / max (H) determining a degree of attribute matching between the first object and the second object; Wherein, H(u, v) is the attribute matching degree between the first object and the second object, including the health attribute matching degree and the psychological attribute matching degree; is the first data; is the second data; Wk is the attribute weight parameter corresponding to the attribute data; max(H) is the reference attribute matching degree between the first object and the second object.

2. The method according to claim 1, characterized in that The first object refers to a user who is using the target application.

3. The method according to claim 2, characterized in that The first physiological data of the target application used by the first object refers to data about the physical and physiological state of the first object, including heart rate, heart rate variability, body temperature, and sleep quality.

4. The method according to claim 1, characterized in that The object recommendation method is applied to a dating platform or a dating application.

5. The method according to claim 1, wherein The attribute matching weight parameter is used to characterize the importance of the attribute matching in the target matching calculation.

6. The method according to claim 1, characterized in that The determining of the target matching degree based on the attribute matching degree and the interest matching degree includes: Obtaining an attribute matching weight parameter, wherein the attribute matching weight parameter is used to represent the importance of the attribute matching; Obtaining an interest matching weight parameter, where the interest matching weight parameter is used to represent the importance of the interest matching; The attribute matching weight parameter, the interest matching weight parameter, the attribute matching degree, and the interest matching degree are linearly combined to obtain a target matching degree between the first object and the second object.

7. An object recommendation device, characterized in that: The device comprises: an acquisition module, configured to acquire first physiological data and first attribute data of a first subject using a target application, and second physiological data and second attribute data of a second subject using the target application; the first attribute data and the second attribute data include psychological data obtained through a psychological assessment and health data obtained through a physical examination; the psychological data includes at least personality type and interests and hobbies; the health data includes at least body fat percentage, BMI, blood pressure, and blood sugar level; the target application includes multiple interactive items; the multiple interactive items include at least one of viewing the other party's profile, sending messages, making video calls, and participating in online or offline activities; a first determining module, configured to determine an interest matching degree between the first object and the second object based on the first physiological data and the second physiological data; a second determination module configured to determine, for each type of attribute data, an attribute weight parameter corresponding to the targeted type of attribute data; determine, in the first attribute data, first data belonging to the targeted type of attribute data; determine, in the second attribute data, second data belonging to the targeted type of attribute data; determine, based on the first data and the second data, a deviation of the targeted type of attribute data; determine, based on the sum of squares of the deviations of the first object and the second object on each type of attribute data and the attribute weight parameter corresponding to each type of attribute data; and use the ratio of the weighted Euclidean distance to a reference attribute matching degree as the attribute matching degree between the first object and the second object; the reference attribute matching degree being an initial matching degree calculated based on the attribute data of the first object and the second object in the absence of a specific interactive item; A third determining module, configured to determine a target matching degree based on the attribute matching degree and the interest matching degree; a recommendation module, configured to select a target object from the second object based on the target matching degree and recommend the target object to the first object; collect feedback data from the first object on the recommended object, analyze the feedback data to evaluate the recommendation effect and user satisfaction, and dynamically adjust the recommendation algorithm and matching strategy based on user feedback and matching results; The first determination module is further configured to determine, for each interactive item, a first interest score of the first object in the interactive item based on the first physiological data of the first object when operating the interactive item; determine a second interest score of the second object in the interactive item based on the second physiological data of the second object when operating the interactive item; and determine a second interest score of the second object in the interactive item based on the first interest score and the second interest score, and calculate the interest score of the second object in the interactive item according to the formula S(u, v)= / (F1×F2), determine the interest matching degree between the first object and the second object; where F1= ;F2= ; Score the first interest level of the first subject in the interactive item i; Score the second interest level of the second object in the interactive item i; is the mean of the first interest rating; is the mean of the second interest rating; I is all interactive items; The second determining module is further configured to use the formula H(u, v)=1- / max(H) determines the attribute matching degree between the first object and the second object; wherein H(u, v) is the attribute matching degree between the first object and the second object, including the health attribute matching degree and the psychological attribute matching degree; is the first data; is the second data; Wk is the attribute weight parameter corresponding to the attribute data; max(H) is the reference attribute matching degree between the first object and the second object.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images