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

Abstract

The invention relates to an object recommendation method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring first physiological data and first attribute data of a target application used by a first object, and second physiological data and second attribute data of the target application used by a second object; 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. By adopting the method, the defects that a traditional love and marriage platform depends on subjective information and lacks real-time data support can be effectively overcome, and more accurate and personalized love and 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 mainly match users based on subjective information such as interests and hobbies filled in by users, lacking objective data analysis support for users' physiological and psychological states, resulting in incomplete and individuated matching results. They are also unable to capture users' emotions and physiological states (such as heart rate, HRV, etc.) in real time, making it difficult to dynamically adjust recommendation strategies, resulting in insufficient timeliness and accuracy of matching results. These problems have caused significant defects in 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 response to the above technical problems.

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

[0005] Acquire 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;

[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 a degree of attribute matching between the first object and the second object according to 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 according to 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, determine the first object's first interest score in the interactive item; based on the second physiological data of the second object when operating the interactive item, determine the second object's second interest score in the interactive item; based on the first interest score and the second interest score, determine the interest matching degree between the first object and the second object.

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

[0013] Based on the first interest score of the first object in each interactive project, determine the mean first interest score; based on the first interest score mean and the first interest score of the first object in the interactive project, determine the deviation value of the first interest score of the first object in the interactive project; based on the second interest score of the second object in each interactive project, determine the mean second interest score; based on the second interest score mean and the second interest score of the second object in the interactive project, determine the deviation value of the second interest score of the second object in the interactive project; based on the first interest score deviation value and the second interest score of the second object in the interactive project, 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 according to 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 type attribute data; based on the sum of squares of the deviations between 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, wherein the attribute matching weight parameter is used to characterize the importance of the attribute matching; obtain an interest matching weight parameter, wherein 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 degree, and the interest matching degree to obtain a target matching degree between the first object and the second object.

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

[0021] An acquisition module, configured to acquire 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;

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

[0023] A second determination module, configured to determine a degree of attribute matching between the first object and the second object according to the first attribute data and the second attribute data;

[0024] A third determination 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 select 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, including 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] Acquire 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;

[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 a degree of attribute matching between the first object and the second object according to 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] Acquire 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;

[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 a degree of attribute matching between the first object and the second object according to 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, including a computer program, which implements the following steps when executed by a processor:

[0039] Acquire 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;

[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 a degree of attribute matching between the first object and the second object according to the first attribute data and the second attribute data;

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

[0043] 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.

[0044] The object recommendation method, device, computer equipment, computer-readable storage medium and computer program product obtain the first physiological data and first attribute data of the first object using the target application, and the second physiological data and second attribute data of the second object using the target application. It breaks through the limitation of the traditional platform relying only on subjective information filling, and introduces objective physiological indicators as the basis for matching. According to the first physiological data and the second physiological data, the interest matching degree between the first object and the second object is determined. The user's interest (such as interaction preference under stress state) is indirectly inferred by physiological data, which supplements the deficiency of relying solely on subjective scoring. According to the first attribute data and the second attribute data, the attribute matching degree between the first object and the second object is determined. The accuracy of attribute matching is effectively improved. The target matching degree is determined based on the attribute matching degree and the interest matching degree. By introducing dynamic physiological data and static attribute data, the limitation of a single data source is broken. Finally, the target object is selected from the second object according to the target matching degree, and the target object is recommended to the first object. It effectively solves the defects of the traditional love and marriage platform relying on subjective information and lacking real-time data support, and realizes more accurate and personalized love and marriage matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

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

[0047] Figure 2 A schematic diagram of a flow chart of an object recommendation method in one embodiment;

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

[0049] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The object recommendation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. 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 selects the target object from the second object according to the target matching degree and recommends the target object to the first object. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0052] In an exemplary embodiment, Figure 2 As shown, an object recommendation method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 202 to 210. Among them:

[0053] Step 202: Acquire first physiological data and first attribute data of a first object using a target application, and acquire 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 this application, the first object is an individual who hopes to find a matching object.

[0055] The target application refers to a dating platform or application where users can fill in personal information, participate in psychological assessments, wear smart bracelets, 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 through devices such as smart bracelets.

[0057] The first attribute data refers to the psychological data and health data about the first object. 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] The second objects refer to other users on the target application who participate in the matching process together 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] The second attribute data refers to the psychological data and health data about the first object. Similarly, psychological data can be obtained through psychological assessments on dating platforms or applications. Health data can be obtained through physical examination reports.

[0061] Specifically, wearable devices such as smart bracelets are used to collect the first subject's heart rate, heart rate variability (HRV), body temperature, sleep quality and other physiological data in real time. Data is recorded and analyzed in different interaction scenarios (such as viewing the other party's information, chatting with the other party, and meeting offline). And through the psychological assessment questionnaire of the marriage and dating platform, the psychological characteristic data of the first subject, including personality, interests, and skills, is obtained. Through physical examination reports or other health monitoring tools, the first subject's body fat rate, BMI, blood pressure, blood sugar and other health data are obtained.

[0062] Similarly, wearable devices such as smart bracelets can be used to collect the second subject's heart rate, heart rate variability (HRV), body temperature, sleep quality and other physiological data in real time. Data is recorded and analyzed in different interaction scenarios (such as viewing the other party's information, chatting with the other party, and meeting offline). And through the psychological assessment questionnaire of the marriage and dating platform, the psychological characteristic data of the second subject, including personality, interests, and skills, is obtained. Through physical examination reports or other health monitoring tools, the second subject's body fat rate, BMI, blood pressure, blood sugar and other health data are obtained.

[0063] Optionally, the psychological assessment data of the first subject and the second subject are preprocessed to extract characteristics such as personality, interests, and skills, and the heart rate and HRV data of the first subject and the second subject 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 according to the first physiological data and the second physiological data.

[0065] Among them, interest matching refers to inferring and matching the user's interests and emotional state based on the user's physiological data and behavioral data. It can be understood that these physiological data can reflect the user's emotional state. For example, changes in heart rate may be related to the user's excitement or nervousness. By analyzing these data, the user's interests and emotional reactions in specific situations can be inferred. And in different interaction scenarios (such as viewing the other party's information, chatting with the other party, and meeting offline), the user's physiological data can reveal his interest and reaction to different types of interactions. For example, a faster heart rate when the user views the other party's information may indicate interest in the object.

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

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

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

[0069] Among them, attribute matching refers to the evaluation of the matching degree between two users based on the users’ static attribute data (such as psychological characteristics, health data, etc.). These attribute data can help the system understand the users’ personalities, interests, and health conditions, and thus determine whether they are suitable for each other.

[0070] Specifically, by comparing the psychological characteristics of the first object and the second object, the matching degree of the two at the psychological level is calculated. Optionally, a similarity calculation method (such as the Pearson correlation coefficient) is used to quantify the matching degree of the psychological characteristics. Similarly, by comparing the health indicators of the first object and the second object, the matching degree of the two at the health level is calculated. Optionally, a method such as weighted Euclidean distance is used to calculate the matching degree of health characteristics.

[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 through 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 in 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 the 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 , screening a target object from the second object according to the target matching degree, and recommending the target object to the first object.

[0078] The target object refers to other users (i.e., the second object) that are calculated based on the recommendation algorithm and are most suitable for the current user (i.e., the first object). It can be understood that the selection of the target object is based on a comprehensive analysis and matching of the multi-dimensional data (including physiological data, psychological data, and health data) of the first object and the second object.

[0079] Specifically, first, a target matching threshold is set according to the system's requirements and recommendation strategies. Only those second objects whose target matching exceeds the threshold will be considered as potential target objects. All second objects are sorted from high to low according to the target matching. And further select the top N objects with the highest target matching as candidate target objects. The value of N can be adjusted according to the system's recommendation capacity and the user's needs. Then prepare the recommendation information, including the basic information, interests, psychological characteristics and health data of the candidate target objects. Ensure that the recommendation information is comprehensive and protects user privacy. And further show the first object a list of the screened target objects. For example, recommend these target objects to the first object through the interface or notification method of the marriage and dating platform.

[0080] Optionally, collect feedback from the first subject on the recommended subject, such as the number of views, chat interactions, etc. Analyze user 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. Continuously optimize the system to improve the matching success rate 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 projects refer to different types of interactive activities that users can conduct on the dating platform. These activities can be various functions or scenarios provided by the platform, in which users can interact with potential matches. Optional interactive projects include viewing the other party's profile, sending messages, making video calls, participating in online or offline activities, etc.

[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 physiological data (such as heart rate, heart rate variability HRV, etc.) of the first subject in 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, first identify all interactive items included in the dating platform. These items can be viewing the other party's profile, sending messages, video calls, participating in online or offline activities, etc. Each interactive item represents a specific type of interaction that users can perform on the platform.

[0086] Then, in each interactive item, the physiological data of the first subject, such as heart rate, heart rate variability (HRV), etc., are collected in real time. And the physiological response of the first subject when operating each interactive item is recorded. Similarly, in each interactive item, the physiological data of the second subject, such as heart rate, heart rate variability (HRV), etc., are collected in real time. And the physiological response of the second subject when operating each interactive item is recorded.

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

[0088] Finally, for each interactive project, the interest scores of the first object and the second object are compared. If the interest scores of both are high and similar, they are considered to have a high interest match in this interactive project. The interest matches of all interactive projects are comprehensively evaluated to obtain an overall interest match. It can be understood that this overall interest match reflects the overall interest match degree of the first object and the second object in different interactive projects.

[0089] Since it can dynamically evaluate the user's interests and emotional responses in interactive projects based on physiological data, it can provide more accurate dating recommendations. This method not only takes into account the user's static interests, but also combines real-time physiological responses to improve the timeliness and accuracy of matching.

[0090] In one embodiment, based on the first interest score of the first object in each interactive project, 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 project, a deviation value of the first interest score of the first object in the interactive project is determined; based on the second interest score of the second object in each interactive project, 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 project, a deviation value of the second interest score of the second object in the interactive project 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 interest scores of the first object in all interactive projects. The first interest score deviation refers to the difference between the interest score of the first object in a specific interactive project and its interest score mean. The second interest score mean refers to the average of the interest scores of the second object in all interactive projects. The second interest score deviation refers to the difference between the interest score of the second object in a specific interactive project and its interest score mean.

[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 the first interest score mean. For each interactive item, the deviation of the interest score of the first subject in the item from the mean is calculated.

[0093] Similarly, the interest scores of the second object in all interactive items are collected. The interest scores of the second object in each interactive item are averaged to obtain the second interest score mean. For each interactive item, the deviation of the interest score of the second object in the item and its mean is calculated.

[0094] Then, for each interactive item, the interest score deviation values ​​of the first object and the second object are compared. If the deviation values ​​of the two are close and have the same sign (i.e., both show a high interest in a certain interactive item), it is considered that they have a high interest match in the interactive item. The interest match of all interactive items is comprehensively evaluated to obtain an overall interest match. It can be understood that this overall interest match reflects the overall interest match degree of the first object and the second object in different interactive items.

[0095] Optional, S(u,v)= / (F1×F2)

[0096] F1=

[0097] F2=

[0098] Wherein, S(u, v) is the interest matching degree between the first object and the second object. Ru,i is the first interest score of the first object in the interactive project. Rv,i is the first interest score of the second object in the interactive project. R^u is the mean of the first interest score. R^v is the mean of the second interest score. I is all interactive projects.

[0099] By calculating the mean and deviation of the interest score, it is possible to more accurately capture the changes in user interests in specific interactive items. This refined analysis helps to identify the user's true interests in certain specific situations, thereby improving the accuracy of matching. And the interest matching calculated based on real-time physiological data allows for dynamic adjustment of matching strategies. When the user's interests change, the recommendation results can be adjusted in a timely manner to ensure that the recommended objects always meet the user's current interests.

[0100] In one of the embodiments, 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 evaluate user matching. These attribute data usually include psychological characteristics and health data. For example, psychological characteristics include personality type, interests and hobbies, etc.; health data includes body fat percentage, BMI, blood pressure, blood sugar level, etc.

[0102] Attribute weight parameters refer to the numerical values ​​used to adjust the importance of different attribute data in the matching calculation. These weights reflect the importance the system attaches to different attributes. By adjusting the weights, the importance of certain attributes can be highlighted according to actual needs and scenarios. For example, if health compatibility is considered very important, the weight of health data may be set higher.

[0103] The reference attribute matching degree refers to the 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. This matching degree provides a benchmark for subsequent dynamic adjustments. Optionally, this reference attribute matching degree is the maximum possible value of the attribute matching degree, which is a predefined constant used to normalize the attribute matching degree between the first object and the second object so that it falls within a specific range (e.g., between 0 and 1).

[0104] The first data refers to the specific values ​​or features of the first object under a specific attribute data category. These data are extracted from the attribute data set of the first object. For example, if the attribute data is health data, the first data may include specific values ​​such as body fat percentage and BMI of the first object.

[0105] The second data refers to the specific values ​​or features of the second object under a specific attribute data category. These data are extracted from the attribute data set of the second object. For example, if the attribute data is health data, the second data may include specific values ​​such as body fat percentage and BMI of the second object.

[0106] Specifically, different attribute data categories used to evaluate user matching are first identified. Weight parameters, i.e., attribute weight parameters, are set for the attribute data of each attribute category. These attribute weight parameters reflect the importance the system places on different attributes. The maximum value that the attribute matching can reach is used as a predefined reference attribute matching degree, which is used to normalize the matching degree so that it falls within a specific range (e.g., between 0 and 1).

[0107] Then, a specific value or feature belonging to a specific attribute category is extracted from the attribute data set of the first object, and a specific value or feature belonging to the same attribute category is extracted from the attribute data set of the second object. And further based on the first data, the second data, the attribute weight parameter 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 data and the second data are combined with the weight parameter to calculate the matching degree of each attribute category. And these matching degrees are combined to obtain the final attribute matching degree. Through the above steps, the data of the first object and the second object in different attribute categories can be comprehensively considered, and a comprehensive and accurate attribute matching degree can be calculated by combining the weight parameter and the initial matching degree. This method ensures that the matching degree calculation is both comprehensive and flexible, and can meet the needs of different users and scenarios.

[0109] In one of the embodiments, based on the first data and the second data, the deviation of the attribute data of the targeted category is determined; based on the sum of the squares of the deviations between the first object and the second object in 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 certain attribute data, which is expressed as the difference in the values ​​of the two objects in the attribute data.

[0111] The sum of squared deviations refers to the sum of the squares of all deviations on multiple attribute data. It is an indicator to measure the overall difference between two objects on all attributes. As can be understood, for each attribute data, the square of its deviation is calculated, and then the squares of the deviations of all attributes are added together to obtain the sum of squared deviations. As can be understood, for each attribute data, the square of its deviation is calculated, and then the squares of the deviations of all attributes are added together 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, then summing them up and taking the square root.

[0113] Specifically, first, for each attribute data, the deviation between the first object and the second object on the attribute is calculated. For example, if the attribute is body fat percentage, the deviation is the body fat percentage of the first object minus the body fat percentage of the second object. 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 squared deviations, the weighted Euclidean distance between the first object and the second object is calculated. The weighted Euclidean distance is further compared with the reference attribute matching degree to calculate the ratio. The calculated attribute matching degree is output as an input parameter of the matching algorithm.

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

[0115] Among them, 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 type of psychological attribute data or the specific data of the first object in the targeted type of psychological attribute data). hv,k is the second data (the specific data of the second object in the targeted type of psychological attribute data or the specific data of the second object in the targeted type of psychological attribute data). Wk is the attribute weight parameter corresponding to the targeted type 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] Since the consideration of attribute data differences covers multiple types of attributes, the calculation of the matching degree is not limited to a single dimension of information, thus reflecting the matching between two objects more comprehensively. In addition, the calculation method of weighted Euclidean distance combines the differences of multiple attributes and expresses the relative position relationship of two objects in the attribute space through the concept of distance. It is convenient to compare the matching degree between different object pairs. For example, the smaller the weighted Euclidean distance between two objects, the smaller the overall difference in their attributes, and the higher the potential matching degree may be.

[0117] In one of the embodiments, 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 used to characterize the importance of the 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 matching weight parameter is a value that represents the importance of interest matching in the final target matching calculation. It reflects the importance the system places on the user's dynamic interest data (such as interests and hobbies obtained through interactive projects or behavior data analysis) in the matching evaluation.

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

[0121] Then determine to use linear combination method to calculate target matching, the linear combination formula is: target matching = (attribute matching weight parameter × attribute matching) + (interest matching weight parameter × interest matching).

[0122] Finally, the obtained attribute matching weight parameter, interest matching weight parameter, and the specific values ​​of the calculated attribute matching and interest matching are substituted into the above formula. The target matching between the first object and the second object is obtained by calculation. This target matching takes into account both the attribute matching and interest matching factors, and performs a reasonable weighted calculation according to their respective weight parameters, thereby more comprehensively and accurately reflecting the matching degree 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)+B 1 ×H 1 (u, v) + B 2 ×H 2 (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. H 1 (u, v) is the health attribute matching degree. 2 (u, v) is the psychological attribute matching degree. 1 is the health attribute weight parameter. 2 is the psychological attribute weight parameter.

[0126] Since different users may attach different importance to attributes and interests in dating, by setting attribute matching weight parameters and interest matching weight parameters respectively, it is possible to flexibly adapt to the needs of various users.

[0127] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0128] Based on the same inventive concept, the embodiment of the present application also provides an object recommendation device for implementing the object recommendation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more object recommendation device embodiments provided below can refer to the limitations on the object recommendation method above, 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, 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 determination module 304, configured to determine the interest matching degree between the first object and the second object according to the first physiological data and the second physiological data;

[0132] A second determination module 306, configured to determine the attribute matching degree between the first object and the second object according to the first attribute data and the second attribute data;

[0133] A 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 used to filter the 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 a mean first interest score based on the first interest score of the first object in each interactive project; determine a deviation value of the first interest score of the first object in the interactive project based on the mean first interest score and the first interest score of the first object in the interactive project; determine a mean second interest score based on the second interest score of the second object in each interactive project; determine a deviation value of the second interest score of the second object in the interactive project based on the mean second interest score and the second interest score of the second object in the interactive project; 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 squares of the deviations between the first object and the second object in 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; 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 above-mentioned object recommendation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to 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, referred to as I / O) and a communication interface. The processor, the memory and the 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 the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, 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 can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and 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 the memory, database or other medium 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0148] The technical features of the above embodiments may be combined arbitrarily. 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 only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An object recommendation method, characterized in that: The method comprises: Acquire 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, based on the first physiological data and the second physiological data, a degree of interest matching between the first object and the second object; Determining a degree of attribute matching 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; 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.

2. The method according to claim 1, characterized in that The target application includes a plurality of interactive items; The 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 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 interestingness score and the second interestingness score, an interest matching degree between the first object and the second object is determined.

3. The method according to claim 2, characterized in that The determining, based on the first interest score and the second interest score, the interest matching degree between the first object and the second object comprises: Determine a first interest score mean based on the first interest score of each interactive item by the first object; Determining a deviation value of a first interest score of the first object in the interactive item based on the first interest score mean value and the first interest score of the first object in the interactive item; Determining a second interest score mean based on the second interest score of the second object in each interactive item; Determine a deviation value of a second interest score of the second object in the interactive item based on the second interest score mean value and 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, an interest matching degree between the first object and the second object is determined.

4. The method according to claim 1, characterized in that: The determining, according to the first attribute data and the second attribute data, the attribute matching degree between the first object and the second object includes: For each type of attribute data, determine the attribute weight parameter corresponding to the type of attribute data; Obtaining a reference attribute matching degree between the first object and the second object; 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; Based on the first data, the second data, the attribute weight parameter, and the reference attribute matching degree, an attribute matching degree between the first object and the second object is determined.

5. The method according to claim 4, characterized in that The 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: Determining a deviation of the attribute data of the category based on the first data and the second data; Determine 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.

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 characterize the importance of the attribute matching; Obtaining an interest matching weight parameter, wherein 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.

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 object using a target application, and second physiological data and second attribute data of a second object using the target application; A first determining module, configured to determine an interest matching degree between the first object and the second object according to the first physiological data and the second physiological data; A second determination module, configured to determine a degree of attribute matching between the first object and the second object according to the first attribute data and the second attribute data; A third determination module, configured to determine a target matching degree based on the attribute matching degree and the interest matching degree; A recommendation module is used to select a target object from the second object according to the target matching degree, and recommend the target object to the first 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