Data processing method, device, electronic device and storage medium
By calculating the correlation intensity value between object accounts, the problem of inaccurate and non-universal quantification of social relationships in the prior art is solved, and relationship quantification and application in various scenarios are realized.
Patent Information
- Application Number
- CN202111446765.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-30
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-11-30
AI Technical Summary
The prior art cannot accurately quantify the social relationships between objects, and the quantification results are only applicable to specific scenarios and cannot be used in other scenarios.
By obtaining social behavior data of multiple object accounts, calculating the correlation coefficient and correlation intensity values of the correlation characteristics, generating the correlation intensity values between objects, using these values to characterize and quantify the objective relationship between objects, it is suitable for various social scenarios .
It improves the accurate quantification of social relationships between objects, can be applied in a variety of social scenarios, and enhances the efficiency and stickiness of relationship applications.
Smart Images

Figure CN114170035B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of big data technology, and in particular to a data processing method, device, electronic device and storage medium. Background Art
[0002] With the development of science and technology, online platforms based on the Internet have gradually become the main social scene. On the above online platforms, the social relationships between objects are quantified, and dynamic messages such as hot news, video works and friend dynamics are recommended to the objects based on the quantified social relationships, so as to increase the probability of dynamic messages being viewed.
[0003] In related technologies, in a specific scenario, the basic information of an object and the interactive behaviors between the object and other objects (such as clicking to view published works) are collected, and historical interactive behaviors are counted (click-through rate) to quantify the social relationships of the object. However, the statistical results cannot accurately reflect all social relationships between objects and are only valid for this specific scenario. Summary of the invention
[0004] The present disclosure provides a data processing method, device, electronic device, and storage medium to at least solve the problem in the related art that the social relationship between objects cannot be accurately quantified. The technical solution of the present disclosure is as follows:
[0005] According to a first aspect of an embodiment of the present disclosure, a data processing method is provided, comprising: obtaining social behavior data of multiple association features possessed by multiple object accounts in a preset object account set, wherein the association feature is used to represent the association information between two object accounts, and the social behavior data is used to represent the relationship data between the multiple object accounts corresponding to the association feature; determining an association coefficient of each association feature according to first mutual information between each association feature and other association features in the multiple association features; generating an association strength value between any two object accounts according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data.
[0006] Optionally, the multiple association features include: relationship establishment features, relationship interaction features, and relationship enhancement features.
[0007] Optionally, the above data processing method also includes: before determining the correlation coefficient of each correlation feature based on the first mutual information between each correlation feature and other correlation features in the multiple correlation features, extracting the interaction feature data corresponding to the relationship interaction feature in the social behavior data; determining the attenuation coefficient of each relationship interaction feature based on the feature occurrence time of each relationship interaction feature, the attenuation coefficient is negatively correlated with the time difference between the current time and the feature occurrence time; and updating the interaction feature data based on the attenuation coefficient of each relationship interaction feature.
[0008] Optionally, the above-mentioned "determining the correlation coefficient of each correlation feature among the multiple correlation features according to the first mutual information between each correlation feature and other correlation features" includes: counting the feature coverage rate of each correlation feature among the multiple correlation features according to the number of object pairs of each correlation feature among the multiple correlation features, the feature coverage rate being: the proportion of the number of object pairs of each correlation feature in the number of all object pairs of the multiple correlation features for multiple object accounts in the preset object accounts, where the object pair is two object accounts with the correlation feature; normalizing the feature coefficient corresponding to the feature coverage rate to generate an initial coefficient of each correlation feature among the multiple correlation features, the feature coefficient being the inverse of the feature coverage rate; determining the compensation coefficient of each correlation feature among the multiple correlation features according to the first mutual information between each correlation feature among the multiple correlation features and other correlation features; determining the correlation coefficient of each correlation feature among the multiple correlation features according to the initial coefficient and the compensation coefficient of each correlation feature among the multiple correlation features.
[0009] Optionally, the above-mentioned “determining the compensation coefficient of each of the multiple association features according to the first mutual information between each of the multiple association features and other association features” includes: determining the first mutual information corresponding to each of the multiple association features according to the information entropy of each of the multiple association features and the conditional entropy of the information entropy corresponding to other association features of each of the multiple association features, the first mutual information refers to the association information between each of the multiple association features and any other association feature; determining the second mutual information of each of the multiple association features according to the first mutual information between each of the multiple association features and other association features, the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple association features; determining the compensation coefficient of each of the at least one second association feature according to the size of the second mutual information of each of the multiple association features.
[0010] Optionally, the above-mentioned “determining the compensation coefficient of each of at least one second association feature according to the size of the second mutual information of each of the multiple association features” includes: determining the compensation coefficient of each of the multiple association features according to the numerical values in the compensation data set and the second mutual information, and the arrangement order of the numerical values in the compensation data set is the same as the arrangement order of the second mutual information.
[0011] Optionally, the above-mentioned “generating an association strength value between any two object accounts based on the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data” includes: multiplying the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data, to obtain at least one product result; adding at least one product result to generate an association strength value between any two object accounts.
[0012] Optionally, the above-mentioned data processing method also includes: after generating the association strength value between any two object accounts in the preset object account set based on the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data, obtaining a resource upload message, the resource upload message is used to identify the target object account in the preset object account set to upload multimedia resources; sending the resource upload message to the recommended object account corresponding to the target account, the recommended object account is: the object account whose association strength value between the target object account and other object accounts in the preset object account set is greater than the preset strength value.
[0013] According to a second aspect of an embodiment of the present disclosure, a data processing device is provided, including an acquisition unit, a first determination unit and a generation unit; the acquisition unit is used to acquire social behavior data of multiple association features possessed by multiple object accounts in a preset object account set, wherein the association feature is used to represent the association information between two object accounts, and the social behavior data is used to represent the relationship data between multiple object accounts corresponding to the association feature; the first determination unit is used to determine the association coefficient of each association feature among the multiple association features based on the first mutual information between each association feature and other association features; the generation unit is used to generate an association strength value between any two object accounts based on the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data.
[0014] Optionally, the multiple association features include: relationship establishment features, relationship interaction features, and relationship enhancement features.
[0015] Optionally, the above-mentioned data processing device also includes an extraction unit, a second determination unit and an updating unit; the extraction unit is used to extract interaction feature data corresponding to the relationship interaction feature in the social behavior data before determining the association coefficient of each association feature in the multiple association features based on the first mutual information between each association feature and other association features; the second determination unit is used to determine the attenuation coefficient of each relationship interaction feature based on the feature occurrence time of each relationship interaction feature, and the attenuation coefficient is negatively correlated with the time difference between the current time and the feature occurrence time; the updating unit is used to update the interaction feature data according to the attenuation coefficient of each relationship interaction feature.
[0016] Optionally, the first determination unit is used to: count the feature coverage rate of each of the multiple associated features according to the number of object pairs of each of the multiple associated features, where the feature coverage rate is: the proportion of the number of object pairs of each of the multiple associated features in the multiple object accounts in the preset object accounts, where the object pair is two object accounts with the associated features; normalize the feature coefficient corresponding to the feature coverage rate to generate an initial coefficient of each of the multiple associated features, where the feature coefficient is the inverse of the feature coverage rate; determine the compensation coefficient of each of the multiple associated features according to the first mutual information between each of the multiple associated features and other associated features; determine the association coefficient of each of the multiple associated features according to the initial coefficient and the compensation coefficient of each of the multiple associated features.
[0017] Optionally, the above-mentioned first determination unit is specifically used to: determine the first mutual information corresponding to each of the multiple association features according to the information entropy of each of the multiple association features and the conditional entropy of other association features in each of the multiple association features corresponding to the information entropy, where the first mutual information refers to the association information between each of the multiple association features and any other association feature; determine the second mutual information of each of the multiple association features according to the first mutual information between each of the multiple association features and other association features, where the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple association features; determine the compensation coefficient of each of the at least one second association feature according to the size of the second mutual information of each of the multiple association features.
[0018] Optionally, the above-mentioned first determination unit is specifically used to: determine the compensation coefficient of each of the multiple associated features based on the numerical values in the compensation data set and the second mutual information, and the arrangement order of the numerical values in the compensation data set is the same as the arrangement order of the second mutual information.
[0019] Optionally, the above-mentioned generation unit is specifically used to: multiply the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data to obtain at least one product result; add at least one product result to generate an association strength value between any two object accounts.
[0020] Optionally, the above-mentioned data processing device also includes a sending unit; the acquisition unit is also used to generate an association strength value between any two object accounts in the preset object account set based on the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data, and then obtain a resource upload message, the resource upload message is used to identify the target object account in the preset object account set to upload multimedia resources; the sending unit is used to send the resource upload message to the recommended object account corresponding to the target account, and the recommended object account is: the object account whose association strength value between the target object account and other object accounts in the preset object account set is greater than the preset strength value.
[0021] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein, when the program or instruction is executed by the processor, the data processing method provided in the first aspect and any possible design thereof is implemented.
[0022] According to a fourth aspect of an embodiment of the present disclosure, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, a data processing method provided in the first aspect and any possible design thereof is implemented.
[0023] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided. The computer program product is stored in a non-volatile storage medium. When the computer program product is executed by at least one processor, the computer program product implements the data processing method provided in the first aspect and any possible design thereof.
[0024] The technical solution provided by the present disclosure brings at least the following beneficial effects: first, social behavior data of multiple association features of multiple object accounts in the preset object account set are obtained, and then the association coefficient of each association feature is determined according to the first mutual information between each association feature and other association features in the multiple association features, and finally, the association strength value between any two object accounts is generated according to the social behavior data of each association feature of any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data. In this way, starting from the perspective of the association coefficient of the association feature between the object accounts, the objective relationship between the objects is characterized and the objective relationship between the objects is quantified, which can improve the accuracy of the quantified social relationship between the objects, so that the quantified association strength value can be directly applied to various social-related scenarios, and will not be limited to a specific scenario.
[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0027] Figure 1 is one of the flowchart diagrams of a data processing method according to an exemplary embodiment;
[0028] Figure 2 is a second flowchart diagram of a data processing method according to an exemplary embodiment;
[0029] Figure 3 is a third flowchart of a data processing method according to an exemplary embodiment;
[0030] Figure 4 is a fourth flowchart of a data processing method according to an exemplary embodiment;
[0031] Figure 5 is a fifth flowchart of a data processing method according to an exemplary embodiment;
[0032] Figure 6 is a structural schematic diagram of a data processing device according to an exemplary embodiment;
[0033] Figure 7 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0034] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0036] In addition, in the description of the embodiments of the present disclosure, unless otherwise specified, " / " means or, for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present disclosure, "multiple" means two or more than two.
[0037] Currently, more and more applications are developing social scenarios, and are committed to increasing the stickiness of objects by building social scenarios. In the process of building social scenarios, it is often necessary to quantify the social relationships between objects to improve the efficiency of social relationship applications. Existing technologies usually collect basic information of objects, or information about interactive behavior characteristics between objects, or object feedback information in a specific scenario, and quantify the relationship between objects. The quantification result can only be applied in this specific scenario, not in other scenarios, and cannot be used for all scenarios. It is not conducive to expanding new relationship applications, nor is it conducive to improving application efficiency.
[0038] In order to solve the above-mentioned problem that the social relationship of an object cannot be accurately quantified through the behavior of a single object, the embodiments of the present disclosure provide a universal relationship quantification system, which describes the relationship between objects based on objective descriptions so that the quantification results can be universal for all scenarios.
[0039] The data processing method provided by the embodiment of the present disclosure is described below in conjunction with the accompanying drawings. The method is exemplarily described below by taking the execution subject as a data processing device as an example. Figure 1 One of the flow charts of the data processing method provided by the embodiment of the present disclosure is shown. The data processing method provided by the embodiment of the present disclosure includes the following steps 101 to 103.
[0040] Step 101: The data processing device obtains social behavior data of multiple associated features possessed by multiple object accounts in a preset object account set.
[0041] In the disclosed embodiment, the association feature is used to represent the association information between two object accounts, and the social behavior data is used to represent the relationship data between multiple object accounts corresponding to the association feature.
[0042] In the embodiment of the present disclosure, the preset object account set includes multiple object accounts, and any two object accounts have multiple association characteristics. The social behavior data with multiple association characteristics includes: social behavior data with multiple association characteristics between any two object accounts.
[0043] Specifically, according to the process of relationship transfer between objects, we collect signals reflecting the strength of relationships and obtain social behavior data with multiple association features around the entire life cycle of the relationship between objects from establishment to maintenance to strengthening. It should be noted that based on the strength of relationships and using an unsupervised model, the association features obtained do not need to be limited to specific scenarios and are universal to all scenarios.
[0044] In the disclosed embodiments, a variety of association features include: relationship establishment features, relationship interaction features, and relationship strengthening features. The relationship establishment features are used to describe the association relationship between object accounts in the relationship establishment process, and the relationship establishment features specifically include: relationship type features and object closeness features (such as common friends); relationship interaction features are used to describe the association relationship between object accounts in the relationship maintenance process, and the relationship interaction features specifically include: multimedia resource consumption features and private message sending features; relationship strengthening features are used to describe the association relationship between object accounts in the relationship strengthening process, and the relationship strengthening features specifically include: whether to set special attention features, multimedia resource appreciation features, and multimedia resource reward features.
[0045] It should be noted that the multiple association features can be 15-dimensional features. The relationship establishment feature is used to describe the features that are only related to the object account itself and have nothing to do with the object behavior. The relationship interaction feature is used to describe the interactive behavior between the object accounts. The relationship strengthening feature is used to describe whether the object account has made additional time, money or emotional efforts.
[0046] In the embodiment of the present disclosure, the relationship type feature is used to express different relationship types, and the association feature between any two object accounts includes the relationship type feature corresponding to one of the relationship types.
[0047] The technical solution provided by the present disclosure brings at least the following beneficial effects: the relationship type feature is an important factor in identifying the intimacy between objects, and adding the relationship type feature to the association feature can enable the relationship establishment feature to reflect the object relationship of the object account during the relationship establishment process.
[0048] In the disclosed embodiment, the relationship types include offline friend type, online friend type and fan influencer type.
[0049] The technical solution provided by the present disclosure brings at least the following beneficial effects: the three relationship types of offline friend type, online friend type and fan influencer type are used to represent the strength of the relationship between object accounts, so as to accurately quantify the strength of association between objects according to the relationship type.
[0050] In the disclosed embodiment, the object closeness feature in the relationship type feature can be calculated by the number of common friends between the object accounts, and the object closeness feature can reflect the size of the intersection of the object circle.
[0051] Specifically, the data processing device obtains the object closeness characteristics, including: counting the number of friends of each object account in the preset object set; calculating the closeness between each object account and other object accounts according to a preset algorithm, and the preset algorithm is: taking the third number of friends as the divisor and the square root of the product of the first number of friends and the second number of friends as the dividend, performing a division operation, each object account corresponds to the first number of friends, the second number of friends of other object accounts, and the third number of friends of the common friends between each object account and other object accounts.
[0052] The technical solution provided by the present disclosure brings at least the following beneficial effects: starting from the entire flow process of establishing, maintaining and strengthening the relationship between objects, all signals that can reflect the closeness of the relationship are collected to facilitate comprehensive and objective quantification of the object relationship.
[0053] Step 102: The data processing device determines a correlation coefficient of each correlation feature according to first mutual information between each correlation feature and other correlation features among the multiple correlation features.
[0054] In the embodiment of the present disclosure, for each of the multiple association features of the multiple object accounts in the preset object account set, a relationship coefficient needs to be determined, that is, the association feature and the association coefficient are in a one-to-one relationship.
[0055] In the embodiment of the present disclosure, assuming that the number of the multiple association features possessed by the multiple object accounts in the preset object account set is 10, then each association feature has 9 first mutual information with other association features, and thus for the preset object account set, a total of 90 first mutual information are included.
[0056] In the disclosed embodiment, the data processing device adds the first mutual information between each correlation feature and other correlation features to obtain the correlation coefficient of each correlation feature.
[0057] In one design, in order to reduce the influence of the feature occurrence time of the second type of features, such as Figure 2 The second flowchart of the data processing method provided by the embodiment of the present disclosure is shown. Before step 102 provided by the embodiment of the present disclosure, the above data processing method also includes the following steps 201 to 203.
[0058] Step 201: The data processing device extracts interaction feature data corresponding to the relationship interaction feature in the social behavior data.
[0059] In the embodiment of the present disclosure, the relationship interaction feature is used to describe the association relationship between object accounts during the relationship maintenance process, and is specifically used to describe the interactive behavior between object accounts, including at least one of the following: multimedia resource consumption features and private message sending features.
[0060] Step 202: Determine the attenuation coefficient of each relationship interaction feature according to the feature occurrence time of each relationship interaction feature.
[0061] In the disclosed embodiment, the attenuation coefficient is negatively correlated with the time difference between the current time and the feature occurrence time.
[0062] Specifically, the calculation rule of the attenuation coefficient can be: Wherein, α is a first preset value, 0<α<1, β is a second preset value, β>1, t1 is the current time, and t2 is the time when the behavior occurs. For example, α=0.9, β=1.618.
[0063] Step 203: The data processing device updates the interaction feature data according to the attenuation coefficient of each relationship interaction feature.
[0064] In the embodiment of the present disclosure, if the time difference between the feature occurrence time and the current time is larger, the attenuation coefficient is smaller, and the product of the attenuation coefficient and the original feature data in the second category of features is smaller, that is, the feature data of the updated second category of features is smaller, thereby reducing the influence of associated features with earlier feature occurrence times on the association coefficient.
[0065] The technical solution provided by the present disclosure brings at least the following beneficial effects: since the relationship interaction characteristics are time-sensitive and gradually decay with offline actual situations such as graduation and resignation, the influence of the occurrence time of the relationship interaction characteristics on the correlation coefficient is reflected by the attenuation coefficient.
[0066] In one design, the data processing device can also normalize the social behavior data of each associated feature to reduce the situation where the social behavior data cannot accurately reflect the associated feature due to the single occasional feature information of the object. It is understandable that due to the great differences in the behavioral characteristics of different objects, a certain feature is very sparse. For example, object A never uses the search function, but one day he sees a message that B has posted a short video on an application, so he searches for A. This causes the search score between A and B to be abnormally high, thereby affecting the overall quantification and causing a breakdown phenomenon. Therefore, the above normalization method is used to prevent the occurrence of the breakdown phenomenon.
[0067] Step 103: The data processing device generates an association strength value between any two object accounts in the preset object account set based on the social behavior data of each association feature possessed by any two object accounts and the association coefficient of the association feature corresponding to the social behavior data.
[0068] In an embodiment of the present disclosure, the social behavior data of each association feature possessed by any two object accounts in a preset object account set and the association coefficient of the association feature corresponding to the social behavior data are multiplied to obtain at least one product result; the at least one product result is added to generate an association strength value between any two object accounts.
[0069] The technical solution provided by the present disclosure brings at least the following beneficial effects: the association strength value between any two object accounts is related to each association feature possessed by the above-mentioned any two object accounts, that is, the range of association features corresponding to the association strength value is relatively wide, so that the association strength value can accurately quantify the objective relationship between the object accounts.
[0070] For example, on the first application, object account A, object account B, object account C, and object account D all establish online relationships at the same time. If object account A and object account B frequently interact, the relationship between object account A and object account B becomes very close, and the association strength value thereof will also increase. If object account A and object account D basically have no interaction, the closeness of the online relationship between object account A and object account D will gradually disappear, and the association strength value thereof will also decrease.
[0071] In the disclosed embodiments, after the relationship quantification is completed, that is, after the association strength value is generated, the association strength value can be applied to any social scenario. For example, in a follow-up list, the people followed can be sorted from large to small according to the association strength value, so as to improve the experience of the object in searching for the people followed; for example, when sending a push notification of "a certain brand has officially uploaded a new work" to the object account, in order to reduce the disturbance to the object, the object account with a larger association strength value can be selected for push notification according to the association strength value; for another example, in video recommendation, the videos of the objects with higher association strength values can be given priority.
[0072] The technical solution provided by the present disclosure brings at least the following beneficial effects: first, social behavior data of multiple association features of multiple object accounts in the preset object account set are obtained, and then the association coefficient of each association feature is determined according to the first mutual information between each association feature and other association features in the multiple association features, and finally, the association strength value between any two object accounts is generated according to the social behavior data of each association feature of any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data. In this way, starting from the perspective of the association coefficient of the association feature between the object accounts, the objective relationship between the objects is characterized and the objective relationship between the objects is quantified, which can improve the accuracy of the quantified social relationship between the objects, so that the quantified association strength value can be directly applied to various social-related scenarios, and will not be limited to a specific scenario.
[0073] In one design, Figure 3 As shown in the third flowchart of the data processing method provided by the embodiment of the present disclosure, step 102 provided by the embodiment of the present disclosure may specifically include the following steps 301 to 304.
[0074] Step 301: The data processing device counts the feature coverage rate of each of the multiple association features according to the number of object pairs of each of the multiple association features.
[0075] In the embodiment of the present disclosure, the feature coverage rate is: for multiple object accounts in the preset object accounts, the number of object pairs of each associated feature accounts in the number of all object pairs of multiple associated features, where an object pair is two object accounts with an associated feature. An object pair refers to two object accounts involved in a certain associated feature.
[0076] For example, the preset object account set includes 1,000 object accounts, where the number of offline friend types of each object account is 10, and the preset object account set includes 10,000 object pairs. Assuming that the number of object pairs corresponding to all association features in the preset object account set is 100,000, the value of the association feature corresponding to the offline friend type should be the ratio of 10,000 to 100,000 (0.1).
[0077] Step 302: The data processing device normalizes the feature coefficients corresponding to the feature coverage to generate an initial coefficient for each of the multiple associated features.
[0078] In the disclosed embodiment, the feature coefficient is the inverse of the feature coverage.
[0079] In the disclosed embodiment, the characteristic coefficients are normalized, specifically mapping the characteristic coefficients to the same numerical range to facilitate subsequent calculation of the characteristic coefficients. After normalization, the initial systems corresponding to the characteristic coefficients are all distributed in the same numerical range, such as [0, 1], [0, 10], [0, 100], etc.
[0080] Step 303: The data processing device determines a compensation coefficient for each of the multiple association features according to the first mutual information between each of the multiple association features and other association features.
[0081] In the embodiment of the present disclosure, the first mutual information refers to the dependency relationship of the occurrence probability between each association feature and other association features. A first mutual information can be calculated between each association feature and any of the other association features. In other words, the number of first mutual information corresponding to each association feature is 1 less than the number of feature types of the multiple association features in the preset object account set.
[0082] In one design, Figure 4 As shown in the fourth flowchart of the data processing method provided by the embodiment of the present disclosure, step 303 provided by the embodiment of the present disclosure may further include the following steps 401 to 403.
[0083] Step 401: The data processing device determines first mutual information corresponding to each of the multiple correlation features according to the information entropy of each of the multiple correlation features and the conditional entropy of other correlation features in each of the multiple correlation features corresponding to the information entropy.
[0084] In the embodiment of the present disclosure, the first mutual information refers to association information between each of the multiple association features and any other association feature.
[0085] In the embodiment of the present disclosure, the information entropy of the correlation feature is used to identify the uncertainty of the correlation feature, and its calculation method is as follows: Among them, H(f t ) is information entropy, P(f t ) is the correlation feature with the value f t probability.
[0086] In the embodiment of the present disclosure, information entropy corresponds to the conditional entropy of other associated features in each associated feature, and is used to identify when the value of other associated features is f t ′, the uncertainty of the associated feature value corresponding to the information entropy is calculated as follows: Among them, H(f t |f t ′) is the conditional entropy, P(f t ′) is the value of other associated features f t The probability of ′, P(f t |f t ′) is the value of other associated features f t ′, the associated feature value is f t probability.
[0087] In the embodiment of the present disclosure, based on the above information entropy and conditional entropy, the first mutual information I(f t ;f t ′)=H(f t )-H(f t |f t ′)=I(f t ′; f t ).
[0088] In the embodiment of the present disclosure, according to the above calculation method, the first mutual information between each correlation feature and other correlation features is calculated respectively.
[0089] Step 402: The data processing device determines second mutual information of each of the multiple association features according to first mutual information between each of the multiple association features and other association features.
[0090] In the disclosed embodiment, the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple association features. All the first mutual information corresponding to each association feature is added together to generate a second mutual information corresponding to each association feature. The second mutual information is of the same type as the first mutual information, and is used to represent the association relationship between the association features.
[0091] Step 403: The data processing device determines a compensation coefficient for each of the at least one second association feature according to the size of the second mutual information of each of the multiple association features.
[0092] In the embodiment of the present disclosure, the compensation coefficient is used to indicate the importance of the associated feature. The process of determining the compensation coefficient in step 403 specifically includes: the data processing device determines the compensation coefficient of each associated feature in the plurality of associated features according to the values in the compensation data set and the second mutual information, and the arrangement order of the values in the compensation data set is the same as the arrangement order of the second mutual information.
[0093] Exemplarily, the data processing device sorts the second mutual information in ascending order; the data processing device sequentially determines the sum of the values in the compensation data set and the second mutual information as the compensation coefficient of each associated feature corresponding to the second mutual information in the sorting result, and the values in the compensation data set are arranged in ascending order.
[0094] In the disclosed embodiment, a compensation coefficient is configured for each second mutual information, and the larger the second mutual information, the larger the compensation coefficient, and vice versa. The settings in the compensation data set can be composed of an arithmetic progression with the third preset value as the first item, the fourth preset value as the tolerance, and the number of associated features in the multiple associated features as the number of items. Exemplarily, with 0.1 as the first item and 0.1 as the tolerance, assuming that the number of associated features in the associated features is 15, then the compensation data set includes 15 values, specifically {0.1, 0.2, 0.3, ..., 1.5}.
[0095] The technical solution provided by the present disclosure brings at least the following beneficial effects: according to the second mutual information order, different numerical values are selected to be added to the second mutual information to determine the compensation coefficient of the correlation feature corresponding to the second mutual information, so as to increase the weight corresponding to the larger second mutual information, so that the correlation coefficient calculated according to the compensation coefficient can more accurately quantify the correlation features between objects.
[0096] The technical solution provided by the present disclosure brings at least the following beneficial effects: the first mutual information is determined by information entropy and conditional entropy, and the compensation coefficient weighted by the initial coefficient is calculated based on the first mutual information, so that the importance of each associated feature can be reflected by the compensation coefficient, and the associated features between objects can be further accurately quantified.
[0097] Step 304: The data processing device determines the correlation coefficient of each of the multiple correlation features according to the initial coefficient and the compensation coefficient of each of the multiple correlation features.
[0098] In the embodiment of the present disclosure, the initial coefficient and the compensation coefficient are in one-to-one correspondence, and the result obtained by adding the two can be determined as the correlation coefficient of the corresponding correlation feature.
[0099] The technical solution provided by the present disclosure brings at least the following beneficial effects: Since the behaviors of objects corresponding to the associated features vary greatly, there may be situations where the features are very sparse. If the same measurement standard is used, it may affect the overall quantification result. Therefore, the feature coefficients are normalized to avoid breakdown. On this basis, combined with the compensation coefficient determined according to the first mutual information, the determined association coefficient is an objective quantification result of the associated features, so that the association coefficient is not limited to a specific scenario and is applicable to a variety of social-related scenarios.
[0100] In one design, Figure 5 As shown in the fifth flowchart of the data processing method provided by the embodiment of the present disclosure, after S103 provided by the embodiment of the present disclosure, the above data processing method may further include step 501 and step 502.
[0101] Step 501: The data processing device obtains a resource upload message.
[0102] In the embodiment of the present disclosure, the resource upload message is used to identify the target object account in the preset object account set uploading the multimedia resource. Exemplarily, the multimedia resource can be a dynamic message, a short video work or a product link.
[0103] Step 502: The data processing device sends the resource upload message to the recommended object account corresponding to the target account.
[0104] In the disclosed embodiment, the recommended target account is: a target account whose association strength value between the target target account and other target accounts in the preset target account set is greater than a preset strength value, so that the recommended target account can upload messages with basic resources, view friends' dynamics, reward friends' works, or purchase goods recommended by friends.
[0105] The technical solution provided by the present disclosure brings at least the following beneficial effects: recommending resource upload messages according to the association strength value can increase the probability of resource upload messages being viewed, that is, increase the interaction between objects, and thereby increase the object stickiness.
[0106] The above mainly introduces the scheme of the embodiment of the present disclosure from the perspective of the method. It is understandable that in order to realize the above functions, the data processing device includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.
[0107] The embodiments of the present disclosure may divide the data processing device into functional units according to the above method examples. For example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation.
[0108] Figure 6 FIG. 1 is a schematic diagram showing the structure of a data processing device according to an exemplary embodiment. Figure 6 As shown, the data processing device provided by the embodiment of the present disclosure includes an acquisition unit 61, a first determination unit 62 and a generation unit 63;
[0109] The acquisition unit 61 is used to acquire social behavior data of multiple association features of multiple object accounts in the preset object account set, wherein the association feature is used to represent the association information between two object accounts, and the social behavior data is used to represent the relationship data between multiple object accounts corresponding to the association feature; for example, Figure 1 As shown, the acquisition unit 61 can be used to execute step 101.
[0110] The first determining unit 62 is used to determine the correlation coefficient of each correlation feature according to the first mutual information between each correlation feature and other correlation features in the multiple correlation features; for example, Figure 1 As shown, the first determination unit 62 can be used to execute step 102 .
[0111] The generating unit 63 is used to generate the association strength value between any two object accounts according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data. Figure 1 As shown, the generating unit 63 can be used to execute step 103 .
[0112] Optionally, the multiple association features include: relationship establishment features, relationship interaction features, and relationship enhancement features.
[0113] Optional, such as Figure 6 As shown, the data processing device provided by the embodiment of the present disclosure further includes an extracting unit 64, a second determining unit 65 and an updating unit 66;
[0114] The extraction unit 64 is used to extract the interaction feature data corresponding to the relationship interaction feature in the social behavior data before determining the association coefficient of each association feature based on the first mutual information between each association feature and other association features in the multiple association features; for example, Figure 2 As shown, the extraction unit 64 can be used to perform step 201.
[0115] The second determining unit 65 is used to determine the attenuation coefficient of each relationship interaction feature according to the feature occurrence time of each relationship interaction feature, and the attenuation coefficient is negatively correlated with the time difference between the current time and the feature occurrence time; for example, Figure 2 As shown, the second determining unit 65 can be used to execute step 202 .
[0116] The updating unit 66 is used to update the interaction feature data according to the attenuation coefficient of each relationship interaction feature. Figure 2 As shown, the updating unit 66 can be used to perform step 203 .
[0117] Optional, such as Figure 6 As shown, the first determination unit 62 provided in the implementation example of the present disclosure is used to count the feature coverage rate of each of the multiple associated features according to the number of object pairs of each of the multiple associated features, and the feature coverage rate is: for multiple object accounts in the preset object accounts, the number of object pairs of each associated feature accounts for the proportion of all the object pairs of the multiple associated features, and the object pair is two object accounts with the associated feature; normalize the feature coefficient corresponding to the feature coverage rate to generate the initial coefficient of each of the multiple associated features, and the feature coefficient is the inverse of the feature coverage rate; determine the compensation coefficient of each of the multiple associated features according to the first mutual information between each of the multiple associated features and other associated features; determine the association coefficient of each of the multiple associated features according to the initial coefficient and the compensation coefficient of each of the multiple associated features. For example, Figure 3 As shown, the first determination unit 62 can be used to execute steps 301 to 304 .
[0118] Optional, such as Figure 6As shown, the first determination unit 62 provided in the embodiment of the present disclosure is specifically used to determine the first mutual information corresponding to each of the multiple correlation features according to the information entropy of each of the multiple correlation features and the conditional entropy of the information entropy corresponding to other correlation features in each of the multiple correlation features, the first mutual information refers to the correlation information between each of the multiple correlation features and any other correlation feature; determine the second mutual information of each of the multiple correlation features according to the first mutual information between each of the multiple correlation features and other correlation features, the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple correlation features; determine the compensation coefficient of each of the at least one second correlation feature according to the size of the second mutual information of each of the multiple correlation features. For example, Figure 4 As shown, the first determination unit 62 can be used to execute steps 401 to 403.
[0119] Optional, such as Figure 6 As shown, the first determination unit 62 provided in the implementation example of the present disclosure is specifically used to: determine the compensation coefficient of each associated feature among multiple associated features based on the numerical values in the compensation data set and the second mutual information, and the arrangement order of the numerical values in the compensation data set is the same as the arrangement order of the second mutual information.
[0120] Optional, such as Figure 6 As shown, the generating unit 63 is used for: multiplying the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data to obtain at least one product result; adding at least one product result to generate an association strength value between any two object accounts.
[0121] Optional, such as Figure 6 As shown, in the data processing device provided by the embodiment of the present disclosure, the device further includes: a sending unit 67;
[0122] The acquisition unit 61 is further used to generate the association strength value between any two object accounts according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set, and the association coefficient of the association feature corresponding to the social behavior data, and then acquire a resource upload message, the resource upload message being used to identify the target object account in the preset object account set uploading multimedia resources; for example, Figure 5 As shown, the acquisition unit 61 can be used to execute step 501.
[0123] The sending unit 67 is used to send the resource upload message to the recommended object account corresponding to the target account, and the recommended object account is: the object account whose association strength value between the target object account and other object accounts in the preset object account set is greater than the preset strength value. Figure 5 As shown, the sending unit 67 can be used to execute step 502.
[0124] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.
[0125] Figure 7 Schematic diagram of the structure of an electronic device provided by the present disclosure. Figure 7 The electronic device may include a processor 71, a memory 72, and a program or instruction stored in the memory 72 and executable on the processor 71; wherein the program or instruction, when executed by the processor 71, implements the data processing method in the above-mentioned embodiment.
[0126] In addition, the electronic device may further include a communication bus 73 and at least one communication interface 74 .
[0127] The processor 71 may be a central processing unit (CPU), a microprocessing unit, an application specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the disclosed solution.
[0128] The communication bus 73 is a signal path for transmitting information between the above components.
[0129] The communication interface 74 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0130] The memory 72 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 72 may exist independently and be connected to the processor 71 via a communication bus 74. The memory 72 may also be integrated with the processor 71.
[0131] The memory 72 is used to store instructions for executing the disclosed solution, and the execution is controlled by the processor 71. The processor 71 is used to execute the program or instructions stored in the memory 72, so as to realize the functions in the disclosed method.
[0132] As an example, combining Figure 6 The functions implemented by the acquisition unit 61, the first determination unit 62 and the generation unit 63 in the data processing device are similar to those Figure 7 The function of processor 71 in is the same.
[0133] In a specific implementation, as an embodiment, the processor 71 may include one or more CPUs, such as Figure 7 CPU0 and CPU1 in.
[0134] In a specific implementation, as an embodiment, the electronic device may include multiple processors 71. Each of these processors 71 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor 71 here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0135] In a specific implementation, as an embodiment, the electronic device may further include an output device 75 and an input device 76. The output device 75 communicates with the processor 71 and may display information in a variety of ways. For example, the output device 75 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 76 communicates with the processor 71 and may receive input from an object in a variety of ways. For example, the input device 76 may be a mouse, a keyboard, a touch screen device, or a sensor device.
[0136] Those skilled in the art will understand that Figure 7 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or adopt a different component arrangement. Figure 7 The electronic device in the system may be a server, a client or other device.
[0137] In addition, the present disclosure also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the electronic device can execute the data processing method provided in the above embodiment.
[0138] In addition, the present disclosure also provides a computer program product, including the computer program product being stored in a non-volatile storage medium, and when the computer program product is executed by at least one processor, the electronic device executes the data processing method provided in the above embodiment.
[0139] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.
Claims
1. A data processing method, characterized in that: include: Acquire social behavior data of multiple association features possessed by multiple object accounts in a preset object account set, wherein the association feature is used to represent association information between two object accounts, and the social behavior data is used to represent relationship data between multiple object accounts corresponding to the association feature; According to the number of object pairs of each of the multiple association features, a feature coverage rate of each of the multiple association features is counted, wherein the feature coverage rate is: for multiple object accounts in the preset object account set, the proportion of the number of object pairs of each of the association features in the number of all object pairs of the multiple association features, wherein the object pair is two object accounts having the association feature; Normalizing the feature coefficient corresponding to the feature coverage to generate an initial coefficient of each associated feature in the multiple associated features, wherein the feature coefficient is the inverse of the feature coverage; Determining a compensation coefficient for each of the multiple association features according to first mutual information between each of the multiple association features and other association features; Determining a correlation coefficient of each of the multiple correlation features according to the initial coefficient of each of the multiple correlation features and the compensation coefficient; The association strength value between any two object accounts is generated according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data.
2. The data processing method according to claim 1, characterized in that: The multiple association features include: relationship establishment features, relationship interaction features and relationship strengthening features.
3. The data processing method according to claim 2, characterized in that: Before determining the correlation coefficient of each correlation feature according to the first mutual information between each correlation feature and other correlation features in the multiple correlation features, the method further includes: Extracting interaction feature data corresponding to the relationship interaction feature in the social behavior data; Determine, according to the feature occurrence time of each of the relationship interaction features, an attenuation coefficient of each of the relationship interaction features, wherein the attenuation coefficient is negatively correlated with the time difference between the current time and the feature occurrence time; The interaction feature data is updated according to the attenuation coefficient of each of the relationship interaction features.
4. The data processing method according to claim 1, characterized in that: The determining, according to the first mutual information between each of the multiple association features and other association features, a compensation coefficient for each of the multiple association features, comprises: Determine, according to the information entropy of each of the multiple association features and the conditional entropy of other association features in each of the multiple association features corresponding to the information entropy, first mutual information corresponding to each of the multiple association features, wherein the first mutual information refers to association information between each of the multiple association features and any other association feature; Determine, according to the first mutual information between each of the multiple association features and other association features, the second mutual information of each of the multiple association features, where the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple association features; A compensation coefficient of each of the at least one second association feature is determined according to the size of the second mutual information of each of the multiple association features.
5. The data processing method according to claim 4, characterized in that: The determining, according to the size of the second mutual information of each of the multiple association features, a compensation coefficient of each of the at least one second association feature comprises: A compensation coefficient for each of the plurality of associated features is determined according to the values in the compensation data set and the second mutual information, and an arrangement order of the values in the compensation data set is the same as an arrangement order of the second mutual information.
6. The data processing method according to claim 1, characterized in that: The step of generating a correlation strength value between any two object accounts according to the social behavior data of each correlation feature possessed by any two object accounts in the preset object account set and the correlation coefficient of the correlation feature corresponding to the social behavior data comprises: Multiplying the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data to obtain at least one product result; The at least one multiplication result is added to generate an association strength value between the any two object accounts.
7. The data processing method according to claim 1, characterized in that: After generating the association strength value between any two object accounts according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data, the method further includes: Acquire a resource upload message, where the resource upload message is used to identify a target object account in the preset object account set to upload a multimedia resource; The resource upload message is sent to a recommended object account corresponding to the target account, wherein the recommended object account is an object account whose association strength value between the target object account and other object accounts in the preset object account set is greater than a preset strength value.
8. A data processing device, characterized in that: It includes an acquisition unit, a first determination unit and a generation unit; The acquisition unit is used to acquire social behavior data of multiple association features possessed by multiple object accounts in a preset object account set, wherein the association feature is used to represent association information between two object accounts, and the social behavior data is used to represent relationship data between multiple object accounts corresponding to the association feature; The first determining unit is used to count the feature coverage rate of each of the multiple association features according to the number of object pairs of each of the multiple association features, wherein the feature coverage rate is: for multiple object accounts in the preset object account set, the number of object pairs of each of the association features accounts for the proportion of all the object pairs of the multiple association features, wherein the object pair is two object accounts having the association feature; The first determining unit is used to normalize the feature coefficient corresponding to the feature coverage to generate an initial coefficient of each associated feature in the multiple associated features, wherein the feature coefficient is the inverse of the feature coverage; The first determining unit is used to determine a compensation coefficient for each of the multiple association features according to first mutual information between each of the multiple association features and other association features; The first determining unit is configured to determine a correlation coefficient of each of the multiple correlation features according to an initial coefficient of each of the multiple correlation features and the compensation coefficient; The generating unit is used to generate an association strength value between any two object accounts in the preset object account set according to the social behavior data of each association feature possessed by any two object accounts and the association coefficient of the association feature corresponding to the social behavior data.
9. The data processing device according to claim 8, characterized in that: The multiple association features include: relationship establishment features, relationship interaction features and relationship strengthening features.
10. The data processing device according to claim 9, characterized in that: The device further comprises: an extracting unit, a second determining unit and an updating unit; The extraction unit is configured to extract the interaction feature data corresponding to the relationship interaction feature in the social behavior data before determining the association coefficient of each association feature according to the first mutual information between each association feature and other association features in the multiple association features; The second determining unit is used to determine an attenuation coefficient of each of the relationship interaction features according to a feature occurrence time of each of the relationship interaction features, wherein the attenuation coefficient is negatively correlated with a time difference between a current time and the feature occurrence time; The updating unit is used to update the interaction feature data according to the attenuation coefficient of each of the relationship interaction features.
11. The data processing device according to claim 8, characterized in that: The first determining unit is specifically configured to: Determine, according to the information entropy of each of the multiple association features and the conditional entropy of other association features in each of the multiple association features corresponding to the information entropy, first mutual information corresponding to each of the multiple association features, wherein the first mutual information refers to association information between each of the multiple association features and any other association feature; Determine, according to the first mutual information between each of the multiple association features and other association features, the second mutual information of each of the multiple association features, where the second mutual information refers to the sum of the first mutual information corresponding to each of the multiple association features; A compensation coefficient of each of the at least one second association feature is determined according to the size of the second mutual information of each of the multiple association features.
12. The data processing device according to claim 11, characterized in that: The first determining unit is specifically configured to: A compensation coefficient for each of the plurality of associated features is determined according to the values in the compensation data set and the second mutual information, and an arrangement order of the values in the compensation data set is the same as an arrangement order of the second mutual information.
13. The data processing device according to claim 8, characterized in that: The generating unit is specifically used for: Multiplying the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data to obtain at least one product result; The at least one multiplication result is added to generate an association strength value between the any two object accounts.
14. The data processing device according to claim 8, characterized in that: The device further comprises: a sending unit; The acquisition unit is further configured to, after generating the association strength value between any two object accounts according to the social behavior data of each association feature possessed by any two object accounts in the preset object account set and the association coefficient of the association feature corresponding to the social behavior data, acquire a resource upload message, wherein the resource upload message is used to identify the target object account in the preset object account set to upload the multimedia resource; The sending unit is used to send the resource upload message to the recommended object account corresponding to the target account, and the recommended object account is: an object account whose association strength value between the target object account and other object accounts in the preset object account set is greater than a preset strength value.
15. An electronic device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein the program or instruction, when executed by the processor, implements the data processing method as described in any one of claims 1 to 7.
16. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the data processing method according to any one of claims 1 to 7 is implemented.
17. A computer program product comprising instructions, characterized in that The computer program product is stored in a non-volatile storage medium, and when the computer program product is executed by at least one processor, the data processing method according to any one of claims 1 to 7 is implemented.
