CN109816187B - Information processing method, information processing device, computer equipment and storage medium - Google Patents

Information processing method, information processing device, computer equipment and storage medium Download PDF

Info

Publication number
CN109816187B
CN109816187B CN201711164561.5A CN201711164561A CN109816187B CN 109816187 B CN109816187 B CN 109816187B CN 201711164561 A CN201711164561 A CN 201711164561A CN 109816187 B CN109816187 B CN 109816187B
Authority
CN
China
Prior art keywords
resource
current
rating information
information set
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711164561.5A
Other languages
Chinese (zh)
Other versions
CN109816187A (en
Inventor
刘健
李弓瑟
郭锐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tenpay Payment Technology Co Ltd
Original Assignee
Tenpay Payment Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tenpay Payment Technology Co Ltd filed Critical Tenpay Payment Technology Co Ltd
Priority to CN201711164561.5A priority Critical patent/CN109816187B/en
Publication of CN109816187A publication Critical patent/CN109816187A/en
Application granted granted Critical
Publication of CN109816187B publication Critical patent/CN109816187B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an information processing method, an information processing device, a computer device and a storage medium, wherein the method comprises the following steps: acquiring each resource rating information set obtained by rating the resources according to different algorithms; acquiring a current resource from the resource rating information set; acquiring a rating information set of each target resource where the current resource is located; acquiring the level difference between the current resource and other resources in a current target resource rating information set to obtain the level deviation of the current resource in the current target resource rating information set; and determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set. The method can improve the accuracy of the comprehensive level corresponding to the computing resource.

Description

Information processing method, information processing device, computer equipment and storage medium
Technical Field
The present invention relates to the field of internet technologies, and in particular, to an information processing method, an information processing apparatus, a computer device, and a storage medium.
Background
With the development of internet technology, people use the internet more and more frequently, and more users acquire resources through the internet, for example, purchase financial products such as funds, buy clothes and the like.
There is a need to obtain the level of resources in many scenarios, such as pushing funds to users based on the level of funds, pushing online stores to users based on the level of stores on the platform, or showing the level of each fund on a stock buying and selling system. In the conventional technology, when calculating the resource level, a computer device needs to collect a large amount of information related to the resource, such as comments related to the resource, performance data of the resource in the past period, such as sales volume of the resource, growth rate information of the resource, etc., and then grade the resource according to the collected resource information and by using a selected resource rating calculation method, however, each rating calculation method has certain defects or sidedness, and therefore the accuracy of the resource rating information obtained by using the existing calculation method is low.
Disclosure of Invention
Therefore, it is necessary to provide an information processing method, apparatus, computer device, and storage medium for solving the above-mentioned problems, in which a plurality of resource rating information sets obtained by rating resources according to different algorithms are obtained, a level deviation is obtained according to a level difference between a current resource and other resources in the resource rating information sets, and a comprehensive level is determined according to the level deviation.
An information processing method, the method comprising:
acquiring each resource rating information set obtained by rating resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource;
acquiring current resources from the resource rating information sets, wherein the current resources at least exist in two different resource rating information sets;
acquiring a rating information set of each target resource where the current resource is located;
calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources;
and determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set.
In one embodiment, the method further comprises: and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
An information processing apparatus, the apparatus comprising:
the resource grading information collection comprises resource identification and corresponding resource grade information, and each resource grading information collection has at least one same resource;
a current resource obtaining module, configured to obtain a current resource from the resource rating information set, where the current resource exists in at least two different resource rating information sets;
the second set acquisition module is used for acquiring the rating information sets of all target resources where the current resources are located;
the deviation obtaining module is used for calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources;
and the level determining module is used for determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set.
In one embodiment, the apparatus further comprises a push information getting module: and the push information corresponding to the current resource is obtained according to the comprehensive level of the current resource.
A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to carry out the steps of the above-mentioned information processing method.
A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when executed by a processor, causes the processor to execute the steps of the above-mentioned information processing method.
According to the information processing method, the device, the computer equipment and the storage medium, the resource rating information sets obtained by rating the resources according to different algorithms are obtained, then the current resources and the target resource rating information sets where the current resources are located are obtained from the resource rating information sets, the level deviation of the current resources in the current target resource rating information sets is obtained through calculation according to the levels of the current resources in the current target resource rating information sets and the levels of other resources, then the comprehensive level corresponding to the current resources is determined according to the level deviation corresponding to the current resources in each target resource rating information set, and due to the fact that the comprehensive levels of the resources are obtained by comprehensively considering a plurality of resource rating information obtained by using different algorithms, the resource rating can be more comprehensive, and the accuracy of the comprehensive levels corresponding to the calculated resources is improved.
Drawings
FIG. 1 is a diagram of an application environment of a method of processing information provided in one embodiment;
FIG. 2A is a flow diagram of a method for information processing in one embodiment;
FIG. 2B is a flow diagram of a method for information processing in one embodiment;
FIG. 3 is a flowchart illustrating determining a comprehensive level corresponding to a current resource according to a level deviation corresponding to each target resource rating information set of the current resource in one embodiment;
FIG. 4 is a flowchart illustrating an embodiment of determining a composite score corresponding to a current resource based on level scores corresponding to the current resource in each target resource rating information set;
FIG. 5 is a flowchart illustrating obtaining target weights corresponding to respective sets of target resource rating information in one embodiment;
FIG. 6 is a flowchart illustrating how to obtain a target weight corresponding to a current target resource rating information set according to a current correlation coefficient corresponding to a current reference resource rating information set and an initial weight corresponding to a current target resource rating information set in one embodiment;
FIG. 7 is a flow diagram of a method of information processing in one embodiment;
FIG. 8A is a diagram illustrating a reference to level information for a current resource in a set of resource rating information in one embodiment;
FIG. 8B is a diagram that illustrates a reference to a level score that corresponds to a current resource in the set of resource rating information, in one embodiment;
FIG. 9A is a block diagram showing a configuration of an information processing apparatus according to an embodiment;
FIG. 9B is a block diagram showing a configuration of an information processing apparatus according to an embodiment;
FIG. 10 is a block diagram that illustrates the structure of the level determination module in one embodiment;
FIG. 11 is a block diagram showing the structure of a composite score determining unit in one embodiment;
FIG. 12 is a block diagram showing a configuration of an object weight obtaining unit in one embodiment;
FIG. 13 is a block diagram showing the structure of a target weight calculating unit in one embodiment;
FIG. 14 is a block diagram showing the construction of an information processing apparatus according to an embodiment;
FIG. 15 is a block diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another. For example, the first preset threshold may be referred to as a second preset threshold, and similarly, the second preset threshold may be referred to as a first preset threshold, without departing from the scope of the present application.
Fig. 1 is a diagram of an application environment of an information processing method provided in an embodiment, as shown in fig. 1, in the application environment, including a terminal 110 and a computer device 120. When it is required to obtain the push information corresponding to the current resource, for example, when the computer device 120 receives a resource push information obtaining request sent by the terminal 110, the computer device 120 obtains the resource push information corresponding to the current resource according to the resource push information obtaining request, and returns the resource push information corresponding to the current resource to the terminal 110. In an embodiment, the computer device 120 may also automatically trigger the step of obtaining the push information corresponding to the current resource, for example, when the user logs in the financial platform, or the computer device 120 may automatically execute the information processing method provided in the embodiment of the present invention at preset time intervals, and send the push information of the current resource to the terminal 110. In an embodiment, after obtaining the push information corresponding to the current resource, the computer device 120 may send the push information corresponding to the current resource to the terminal 110 in real time, or store the push information corresponding to the current resource in association with the current resource, and send the push information to the terminal 110 when receiving a push information acquisition request sent by the terminal 110 or at a preset time.
The computer device 120 may be an independent physical server or terminal, may also be a server cluster formed by a plurality of physical servers, and may be a cloud server providing basic cloud computing services such as a cloud server, a cloud database, a cloud storage, and a CDN. The terminal 110 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like. The computer device 120 and the terminal 110 may be connected in a communication connection manner such as a network, and the invention is not limited thereto.
As shown in fig. 2A, in one embodiment, an information processing method is proposed, and this embodiment is mainly illustrated by applying the method to the computer device 120 in fig. 1. The method specifically comprises the following steps:
step S202, acquiring each resource rating information set obtained by rating the resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource.
Specifically, an algorithm refers to a method of obtaining an output from an input and a calculation method. The different algorithms may be at least one of different inputs and different calculation methods. For example, the fund rating method may be to obtain fund level information according to the calculated sharp index or obtain fund level information according to the calculated reynolds index. The rating means that a level is determined according to a certain evaluation index. The level of the resource is determined, for example, based on information about the resource such as reviews of the resource, quality of the resource, and the like. The level of the resource can be represented by numbers, images, letters, etc., for example, level 1, level 2, or one star, two stars, etc., and can be specifically set according to the actual needs as long as the level of the resource can be identified. The resource refers to data, services, or goods available to the user, or carriers of the data, services, or goods, such as an online store selling clothes. Resources may include virtual resources such as video resources, financial products such as funds and stocks, etc., and physical resources such as clothing, television, etc. The resource identification is used to identify the resource, which may be, for example, the name of the resource. In one embodiment, the resources are virtual resources and the growth rate may change over time, such as stocks and funds. There are a plurality of resource rating information sets. An algorithm corresponds to a set of resource rating information.
In one embodiment, the resources in each resource rating information set are consistent or partially consistent, for example, if there are A, B, C resources in the first resource rating information set, A, B, C three resources are also included in the other resource rating information sets. Or A, B, C three resources exist in the first resource rating information set, and A, D two resources are included in the second resource rating information set.
In one embodiment, the rating information of funds from different fund rating agencies may be obtained, and then the rating information of funds from the same fund rating agency may be combined into a resource rating information set. For example, the rating information of the Chenxing fund rating mechanism on each fund is formed into one resource rating information set, and the rating information of the China fund rating mechanism on each fund is formed into another resource rating information set.
In an embodiment, after the plurality of resource rating information sets are obtained, the level information of the resources in the resource rating information sets may be further screened to remove abnormal rating information in the resource rating information sets. For example, the rating float range Delta may be set in advance. And calculating the difference D between the highest level and the lowest level of the same resource in a plurality of resource rating information sets, if D > Delta, deleting the highest level and the lowest level of the resource, and repeating the process for each resource. In an embodiment, the highest level information of the same resource in multiple resource rating information sets may also be acquired, if only one resource rating information set is rated as the highest level, the highest level information is removed, and then the lowest level of the resource rating information set is acquired, and if only one resource rating information set is rated as the lowest level, the lowest level information is removed.
Step S204, current resources are obtained from the resource rating information sets, and the current resources exist in at least two different resource rating information sets.
In particular, a current resource refers to a resource that exists in at least two different sets of resource rating information. There may be more than one current resource. For example, if the first set of resource rating information includes A, B, C three resources and the second set of resource rating information includes A, B, D three resources, then a and B are current resources.
And step S206, acquiring each target resource rating information set of the current resource.
Specifically, the target resource rating information set refers to a resource rating information set including the current resource. And after the current resources are obtained, respectively obtaining a target resource rating information set of each current resource.
And step S208, calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources.
Specifically, the level deviation refers to a level-to-level difference. The current target resource rating information set refers to a target resource rating information set where the current resource is located when the level difference is calculated. Assume that the target resource rating information set in which the current resource is located includes a first set and a second set. Then the first set is the current target resource rating information set when calculating the level difference between the current resource and other resources in the first set, and the second set is the current target resource rating information set when calculating the level difference between the current resource and other resources in the second set. Other resources refer to resources in the current target resource rating information set other than the current resource. For example, if the current target resource rating information set includes current resources a and B, when the level difference between a and other resources is obtained, B also belongs to other resources. The level deviation may be represented by a magnitude relationship, such as greater than, less than, or equal to. The specific level difference may be used to indicate that, for example, the level deviation is 2 if the current resource is 2 levels higher than other resources, the level deviation is-2 if the current resource is 2 levels lower than other resources, and the level deviation is 0 if the current resource is several times the same as other resources.
Step S210, determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set.
Specifically, the level deviation of the current resource corresponding to each target resource rating information set is integrated to determine the integrated level corresponding to the current resource. In one embodiment, the comprehensive level may be obtained according to the distribution of the level deviation of the current resource, for example, when the ratio of the current resource level greater than the other resource levels exceeds a preset ratio, the comprehensive level of the current resource is the highest level. In an embodiment, the comprehensive level of each current resource may be obtained according to the level deviation of all the current resources, for example, a corresponding score is obtained according to the level deviation of the current resource, and then a corresponding relationship between the score and the comprehensive level is set, and specifically, the comprehensive level of the current resource whose score is sorted in a preset sort may be set as the highest level. In one embodiment, other factors may also be combined to determine the integration level corresponding to the current resource. For example, the influence weight is set in combination with the fund size, then a comprehensive grade is obtained according to the influence weight and the score obtained according to the grade deviation, and then a comprehensive grade corresponding to the current resource is obtained according to the comprehensive grade.
According to the information processing method, each resource rating information set obtained by rating the resources according to different algorithms is obtained, then the current resource and each target resource rating information set where the current resource is located are obtained from the resource rating information sets, the level deviation of the current resource in the current target resource rating information set is obtained through calculation according to the level of the current resource in the current target resource rating information set and the level deviation of other resources, then the comprehensive level corresponding to the current resource is determined according to the level deviation of the current resource in each target resource rating information set, and the comprehensive level of the resource is obtained by comprehensively considering a plurality of resource rating information obtained by using different algorithms, so that the resource rating can be more comprehensive, and the accuracy of calculating the comprehensive level corresponding to the resource is improved.
As shown in fig. 2B, in an embodiment, the information processing method may further include a step S212 of obtaining push information corresponding to the current resource according to the comprehensive level of the current resource.
Specifically, the push information may be the current resource and the comprehensive level of the current resource, or may be a resource transfer value of the current resource obtained according to the comprehensive level of the current resource, for example, a corresponding relationship between the comprehensive level and the amount of the fund recommended to be purchased may be set, and after the comprehensive level is obtained, the corresponding recommended purchase amount is obtained. Or screening out the current resources with high comprehensive level as recommended resources according to the comprehensive level of each current resource, and specifically setting according to actual requirements. The push information corresponding to the current resource can be pushed in real time, and can also be pushed to the terminal periodically after the push information is obtained or after a push information acquisition request is received, and the push information can be specifically set according to actual requirements.
The information processing method comprises the steps of obtaining resource rating information sets obtained by rating resources according to different algorithms, obtaining current resources and target resource rating information sets where the current resources are located from the resource rating information sets, obtaining level differences of the current resources and other resources in the current target resource rating information sets, calculating level deviations of the current resources in the current target resource rating information sets according to the level differences, determining comprehensive levels corresponding to the current resources according to the level deviations of the current resources in the target resource rating information sets, and obtaining pushing information of the current resources according to the comprehensive levels of the current resources. The comprehensive level of the resource is obtained by comprehensively considering the resource rating information obtained by a plurality of different algorithms, so that the accuracy of the comprehensive level corresponding to the resource is improved, the reliability of the resource pushing information obtained according to the resource level is enhanced, the invalid pushing and the interaction times between the terminal equipment and the server can be reduced, and the computer network resource is saved.
In one embodiment, as shown in fig. 3, the step S210 of determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set includes:
step S302, obtaining the grade value of the current resource corresponding to each target resource rating information set according to the grade deviation of the current resource corresponding to each target resource rating information set.
Specifically, the corresponding relationship between the level deviation and the level score may be preset, for example, when the level deviation is greater than the predetermined threshold, the corresponding level score is 1, when the level deviation is less than the predetermined threshold, the corresponding level score is-1, and when the level deviation is equal to the predetermined threshold, the corresponding level score is-1. The specific score may be set according to actual needs, in one embodiment, if the level deviation is opposite, the corresponding level score is an opposite number, and if there is no level deviation, that is, the level score when the current resource is equal to the level of the other resource is 0. In this way, the obtained level score can intuitively represent the level of the current resource in the resource rating information set. For example, if the level deviation is N, the corresponding level score is M, and if the level deviation is-N, the corresponding level score is-M.
Step S304, determining a comprehensive score corresponding to the current resource according to the grade scores of the current resource corresponding to the target resource grading information sets.
Specifically, after obtaining the level scores of the current resource corresponding to each target resource rating information set, the level scores corresponding to the current resource may be added to obtain a comprehensive score of the current resource. For example, if there are two target resource rating information sets, and the level scores of the current resource are 1, 2, and 3 respectively corresponding to the first target resource rating information set, and the level scores of the current resource are 2, -2, and 3 respectively corresponding to the second target resource rating information set, the total score obtained by adding is 1+2+3+2-2+ 3-9.
And step S306, determining the comprehensive grade of the current resource according to the comprehensive grade of the current resource.
Specifically, the corresponding relationship between the composite score and the composite level may be preset, and after the composite score is obtained, the composite level of the current resource is obtained according to the corresponding relationship between the composite score and the composite level. In one embodiment, the composite score of the current resource may be set to a first level in the composite score of all current resources sorted within a preset first sorting, the composite score may be set to a second level between the first preset sorting and a second preset sorting, and so on. Or the composite score is in a first grade when the composite score is larger than the first preset score, and the composite score is in a second grade when the composite score is between a second preset score and the first preset score. By analogy, the setting can be specifically carried out according to actual needs. For example, the highest 10% of the composite scores are 5 stars, the next 22.5% are 4 stars, the next 35% are 3 stars, the next 22.5% are 2 stars, and the last 10% are 1 star.
In an embodiment, as shown in fig. 4, the step S304 of determining the composite score corresponding to the current resource according to the level scores corresponding to the current resource in each target resource rating information set may specifically include the following steps:
step S402, acquiring target weights corresponding to the target resource rating information sets.
Specifically, a target weight corresponding to each target resource rating information set may be preset. And calculating to obtain the target weight corresponding to the target resource rating information set. For example, the target weight is obtained according to the number of the target resource rating information sets, and if there are n target resource rating information sets, the target weight is 1/n. Of course the target weights may also be set empirically. For example, a greater weight may be placed on the set of fund rating information given by a large-scale or highly trustworthy fund rating agency.
Step S404, obtaining the comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set.
Specifically, after the target weight is obtained, the target weight corresponding to the target resource rating information set may be multiplied by the level score of the current resource in the target resource rating information set to obtain products, and then the products corresponding to the current resource are added to obtain a comprehensive score of the current resource. Is formulated as follows:
Figure BDA0001475998410000101
wherein j represents the current resource, M represents the number of the target resource rating information set, k represents the number of other resources in the target resource rating information set, S (j) represents the comprehensive score of the current resource j, and w i And M (i, j, k) represents a grade score obtained according to the grade deviation of the current resource j and the kth other resource in the ith target resource rating information set.
In one embodiment, as shown in fig. 5, the step S402 of obtaining the target weight corresponding to each target resource rating information set includes:
step S502, obtaining the initial weight corresponding to each target resource rating information set.
Specifically, the initial weight may be preset, and the initial weight corresponding to each target resource rating information set may be the same or different. The target weight may be obtained according to the number of the target resource rating information sets, for example, if there are n target resource rating information sets, the initial weight is 1/n. The specific setting can be carried out according to actual needs.
Step S504, obtaining the initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set.
Specifically, after the initial weight is obtained, the initial weight corresponding to the target resource rating information set may be multiplied by the level score of the current resource in the target resource rating information set to obtain products, and then the products corresponding to the current resource are added to obtain the initial score of the current resource.
Step S506, an initial resource rating set is formed by the initial rating corresponding to each current resource, and resource rating information of each current resource is obtained from the current target resource rating information set to form a current reference resource rating information set.
Specifically, the current target resource rating information set refers to a target resource rating information set where a current resource is located when resource rating information of the current resource is obtained. Each target resource rating information set can be used as a current target resource rating information set to obtain a corresponding current reference resource rating information set. And for each target resource rating information, extracting the resource rating information of the current resource to form a corresponding current reference resource rating information set. For example, if the current resource is a and B, and there are two target resource rating sets, the resource rating information of the current resource a and B is extracted from the first target resource rating information set to form a corresponding first current reference resource rating information set, and the resource rating information of the current resource a and B is extracted from the second target resource rating information set to form a corresponding second current reference resource rating information set. And the initial scores of A and B are combined into an initial resource score set.
Step S508, calculating the correlation between the current reference resource rating information set and the initial resource scoring set, and obtaining a current correlation coefficient corresponding to the current reference resource rating information set.
Specifically, the correlation coefficient is used to represent the degree of correlation between the current reference resource rating information set and the initial resource rating set, and if the correlation coefficient is large, the degree of correlation is high. The method of the correlation coefficient can be set according to actual needs. For example, at least one of a pearson correlation coefficient, a kender correlation coefficient, and a spearman correlation coefficient of the current reference resource rating information set and the initial resource score set may be calculated to yield a current correlation coefficient.
Taking the pearson correlation coefficient as an example, the pearson coefficient is a quotient of a covariance and a standard deviation between the two sets, so that the covariance between the initial resource rating set and the current reference resource rating information set can be calculated, the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set are calculated, a product operation is performed according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result, and finally, a quotient operation is performed according to the covariance and the standard deviation calculation result to obtain the current correlation coefficient corresponding to the current reference resource rating information set. The covariance is used for measuring the total error of two variables in probability theory and statistics, and can obtain products according to the difference between the value of each variable in the first set and the mean value of the first set and the difference between the value of each variable in the second set and the mean value of the second set, then calculate the mean value after summing each product, obtain the covariance, and judge whether the variation of the variables of the two sets is consistent according to the covariance. If the trend of the two sets is consistent, then the covariance between the two sets is positive. If the two variables have opposite trends, then the covariance between the two sets is negative.
Step S510, obtaining a target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
Specifically, after a current correlation coefficient corresponding to the current reference resource rating information set is obtained, the initial weight is updated by using the current correlation coefficient to obtain a target weight corresponding to the current target resource rating information set. The specific calculation method may be set according to actual needs, for example, the target weight corresponding to the current target resource rating information set may be equal to the sum of the initial weight corresponding to the current target resource rating information set and the current correlation coefficient. Is formulated as follows: w is a i Initial weight + correlation coefficient preset value. Wherein, w i And representing the target weight corresponding to the ith target resource rating information set. The preset value can be based onIt is actually necessary to set it to 0.1, for example.
In one embodiment, as shown in fig. 6, the step S510 of obtaining a target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set includes:
step S602, obtaining an updated weight according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
Specifically, after a current correlation coefficient corresponding to the current reference resource rating information set is obtained, an update weight corresponding to the current target resource rating information set is obtained by using the current correlation coefficient and the corresponding initial weight. The specific calculation method may be set according to actual needs, for example, the update weight corresponding to the current target resource rating information set may be equal to the initial weight corresponding to the current target resource rating information set plus the product of the current correlation coefficient and the preset value. The update weight may be equal to the product of the current correlation coefficient and the initial weight.
Step S604, obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight, and entering the step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, obtaining a target weight corresponding to the current target resource rating information set according to the updated weight.
Specifically, after obtaining the updated initial weight corresponding to the current target resource rating information set according to the update weight, re-entering the step of obtaining the initial weight corresponding to each target resource rating information set until a preset condition is met, stopping circulation, and obtaining the target weight corresponding to the current target resource rating information set according to the finally obtained update weight. For example, the resulting update weight may be used as the target weight. Of course, other factors may be combined to obtain the target weight. If the updated weight is obtained, the updated weight is sent to the user terminal and then receivedAnd adjusting the updating weight through an adjusting instruction sent by the terminal by the user. The magnitude of the adjustment can be set as desired. The preset stop condition includes at least one of the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is greater than a first preset threshold, a deviation value obtained according to the initial weight before updating and the initial weight after updating is less than a second preset threshold, and a deviation value obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is less than a third preset threshold. Before updating refers to before the updated initial weight is obtained according to the updated weight in each circulation, and after the updated initial weight is obtained according to the updated weight in each circulation of the updated finger. The first preset threshold, the second preset threshold and the third preset threshold can be set according to actual needs. The calculation method of the deviation value can be set according to the actual situation. For example, the deviation value may be calculated as a square of the difference between the initial score before updating and the initial score after updating of each current resource and a value obtained by summing the squares. Is formulated as follows:
Figure BDA0001475998410000131
wherein D represents a deviation value, b represents the number of current resources, S L Indicating the initial score obtained for this cycle, S L-1 The initial score obtained from the last cycle is indicated.
In one embodiment, the update weight corresponding to the current target resource rating information set may be equal to the initial weight corresponding to the current target resource rating information set plus the product of the current correlation coefficient and the step value, formulated as w Furthermore, the utility model ＝w Beginning of the design + p step, where w Furthermore, the utility model Update weight, w, representing a current set of reference resource rating information Beginning of the design The initial weight is represented, p represents the current correlation coefficient, step represents the step value, because the step value needs to be set for better convergence because of the multiple-cycle calculation in the embodiment, if the step value is too small, the cycle number is large, the convergence speed is slow, the value range of step can be obtained according to experience,in practice, 0.001 may be desirable.
In one embodiment, the step of obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight includes: and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set. Specifically, normalization is a dimensionless processing means capable of changing the absolute value of a plurality of numerical values into a relative value relationship between the numerical values. The normalization method may be specifically set according to actual needs. In one embodiment, the corresponding update weights of each target resource rating information set in the current cycle may be obtained, a total weight is obtained after summing, and then an updated initial weight is obtained according to the ratio of the update weight to the total weight. Is formulated as follows:
Figure BDA0001475998410000141
w beginning of the design ＝w h Where M represents the number of sets of target resource rating information, w h And representing the updating weight corresponding to the h-th target resource rating information set obtained by the current round of circulation. H represents the total weight, w Beginning of the design Representing the updated initial weights.
In one embodiment, as shown in fig. 7, the information processing method may further include the steps of:
step S702, obtaining corresponding growth information of each resource in a preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource.
Specifically, the preset time may be set according to actual needs. For example, it may be one month. The growth rate refers to the ratio of the increment of the end value of the resource at the end of the preset time period relative to the initial value of the resource at the beginning of the preset time period to the initial value. For example, a stock has risen by 10% in a month, and then the growth rate for that month is 10%. It is understood that the increment value can be either a positive or negative value. For example, if the stock purchased falls, the growth rate is negative. The fluctuation rate refers to the fluctuation amplitude of the value of the resource in the past preset time, and is reflected by the value sequence of the resource in the preset time. The standard deviation of the mean value of the asset value in each short time in the preset time can be calculated according to the value sequence, and the fluctuation rate is obtained. The fluctuation rate may be obtained from a resource management entity, such as a financial management entity. The number of resources can be obtained as required.
Step S704, an algorithm set is obtained, and the algorithm set comprises a plurality of different resource rating algorithms.
Specifically, the resource rating algorithm refers to a method for obtaining a resource rating according to an input and a calculation method. The different resource ranking algorithms may be at least one of different inputs and different calculation methods, and may be specifically set according to actual needs. For example, the sharp ratio of the resource is calculated according to the sharp ratio calculation method and the growth information, or the reynolds index of the resource is calculated according to the reynolds index calculation method and the growth information. The corresponding relation between the sharp ratio and the resource level and the corresponding relation between the reynolds index and the resource level can be preset, so that the resource rating information of the current resource can be respectively obtained according to the sharp ratio and the reynolds index obtained through calculation.
Step S706, calculating the resource rating information of each corresponding resource according to the current resource rating algorithm and the growth information corresponding to each resource, and forming a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
Specifically, the current resource rating algorithm refers to a corresponding resource rating algorithm when calculating the resource rating. After the rating information of the corresponding resource is obtained according to the current resource rating algorithm, the corresponding resource rating information sets can be combined into a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set. For example, if the current resource is a or B. The resource rating information of a and the resource rating information of B determined by the sharp ratio algorithm constitute a first set of resource rating information, and the resource rating information of a and the resource rating information of B determined by the reynolds index algorithm constitute a second set of resource rating information.
Specifically, the information processing method provided by the present invention is described below by taking resources as funds.
1. The method includes the steps of acquiring the rating information of different fund rating mechanisms on the fund, wherein the fund rating information of each rating mechanism is used as a resource rating information set, and in the embodiment, acquiring 3 resource rating information sets, I1, I2 and I3 respectively.
2. And extracting the current resource from the three financial resource rating information, and assuming that the 3 financial resource rating information sets all comprise three funds A1, A2 and A3, so that the current resources are A1, A2 and A3, and the target resource rating information sets are I1, I2 and I3. The rating information of the respective current resources in the resource rating information sets I1, I2, and I3 is shown in fig. 8A.
3. And calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources to obtain a grade score. Comparing each current resource in each target resource rating information set with other resources in the same target resource rating information set to obtain the size relationship of the current resource and other resources, wherein if the level of the current resource is higher than the levels of the other resources, the corresponding level score is 1, if the level of the current resource is lower than the levels of the other resources, the corresponding level score is-1, and if the level of the current resource is equal to the levels of the other resources, the corresponding level score is 0. In the embodiments of the present invention. The corresponding level scores obtained by comparing each current resource with other resources are shown in fig. 8B.
4. And acquiring an initial weight corresponding to each target resource rating set I1, I2 and I3. At the time of the first acquisition, the initial weight corresponding to each of the target resource rating sets I1, I2, and I3 is the reciprocal of the number of the target resource rating sets, and since there are 3 target resource rating information sets in this embodiment, the initial weight corresponding to each of the target resource rating sets I1, I2, and I3 is 1/3.
4. And obtaining initial scores corresponding to the current resources according to the initial weight of the target resource rating information set and the grade scores of the current resources in the target resource rating information set, forming an initial resource rating set by the initial scores corresponding to the current resources, and obtaining resource rating information of the current resources from the current target resource rating information set to form a current reference resource rating information set. For example, for current asset a, the initial score is 1/3 x (1+1) +1/3 x (-1+1) +1/3 x (-1+0) ═ 1/3. For current resource B, the initial score was 1/3 (-1+1) +1/3 (1+1) +1/3 (1+1) ═ 4/3. For current asset C, the initial score was 1/3 (-1+ -1) +1/3 (-1+ -1) +1/3 (0+ -1) — 5/3. The initial resource scores are all (1/3, 4/3, -5/3). According to fig. 8A, the reference resource rating information sets corresponding to the target resource rating information sets are I1(5, 4, 3), I2(4, 5, 3), and I3(4, 5, 4).
5. And calculating the correlation between the current reference resource rating information set and the initial resource scoring set to obtain a current correlation coefficient corresponding to the current reference resource rating information set. In this embodiment, the covariance between the initial resource rating information set and the current reference resource rating information set, the standard deviation corresponding to the initial resource rating set, and the standard deviation corresponding to the current reference resource rating information set may be calculated. The current correlation coefficient is a ratio of the covariance and a standard deviation calculation result, and the standard deviation calculation result is equal to a product of a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set. Therefore, in this embodiment, the covariance between the initial resource score set (1/3, 4/3, -5/3) and the reference resource rating information set is 0.67, 1, and 0.44, and the standard deviation between the initial resource score set (1/3, 4/3, 5/3) and the reference resource rating information set is respectively: 1.53, 1, 0.58. Therefore, the current correlation coefficient corresponding to the reference resource rating information set I1(5, 4, 3) is: 0.67/(1.53 × 1) ═ 0.44, the current correlation coefficient corresponding to the reference resource rating information set I2(4, 5, 3) is: 1/(1.53 × 1) ═ 0.65, so the current correlation coefficient for the reference resource rating information set I3(4, 5, 4) is: 0.44/(1.53 × 0.58) ═ 0.50.
6. And obtaining an updating weight according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set. Wherein the update weight is equal to the initial weight plus the product of the step value and the current correlation coefficient, the step value taking 0.001. In this embodiment, the update weight corresponding to the reference resource rating information set I1(5, 4, and 3) is calculated as: 1/3+0.44 × 0.001 ═ 0.33377, the update weight corresponding to the reference resource rating information set I2(4, 5, 3) is: 1/3+0.65 × 0.001 ═ 0.33398, the update weights corresponding to the reference resource rating information set I3(4, 5, 4) are: 1/3+0.5 × 0.001 ═ 0.33383.
7. And normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set. The obtained updated weights can be added to obtain a total weight, and then the updated weight of the current resource is divided by the total weight to obtain a normalized value which is used as an updated initial weight. Since the total weight is 0.33377+0.33398+0.33383 is 1.00158, the updated initial weights corresponding to I1(5, 4, 3), I2(4, 5, 3), and I3(4, 5, 4) are: 0.33377/1.00158 ═ 0.33324, 0.333398/1.00158 ═ 0.33345, and 0.33383/1.00158 ═ 0.33330.
8. And 4, re-entering the step 4, and repeating the steps 4-8. And stopping until the preset stop condition is met, for example, if the preset stop condition is met when the steps are repeated for 50 times, taking the finally obtained update weight as the target weight corresponding to the target resource rating information set.
9. And obtaining the comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set. Assume that I1, I2, I3 correspond to target weights of 0.3, 0.5, and 0.2. Then the overall score for current asset a is 0.3 x (1+1) +0.5 x (-1+1) +0.2 x (-1+0) ═ 0.4, based on the rank scores obtained in fig. 8B. For current resource B, the overall score was 0.3 x (-1+1) +0.5 x (1+1) +0.2 x (1+1) ═ 0.9. For current resource C, the overall score was 0.3 x (-1+ -1) +0.5 x (-1+ -1) +0.2 x (0+ -1) — 1.8.
10. And determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set. The scores of the current resource A, B, C are compared, and assuming that the comprehensive score is that the comprehensive grade corresponding to the first 1/3 is three stars, the second 1/3 is 2 stars, and the remaining 1/3 is one star, the comprehensive grades corresponding to the current resource A, B, C are two stars, three stars, and one star, respectively.
11. And pushing the comprehensive level information of the current resources to the terminal. With the higher level resources in the page rank first.
As shown in fig. 9A, in an embodiment, an information processing apparatus is provided, which may be integrated in the computer device 120, and specifically may include:
a first set obtaining module 902, configured to obtain each resource rating information set obtained by rating resources according to different algorithms, where the resource rating information set includes a resource identifier and corresponding resource level information, and each resource rating information set has at least one same resource.
A current resource obtaining module 904, configured to obtain a current resource from the resource rating information sets, where the current resource exists in at least two different resource rating information sets.
A second set obtaining module 906, configured to obtain each target resource rating information set where the current resource is located.
A deviation obtaining module 908, configured to calculate, according to the level of the current resource in the current target resource rating information set and the level of the other resource, a level deviation of the current resource in the current target resource rating information set.
A level determining module 910, configured to determine, according to a level deviation of the current resource corresponding to each target resource rating information set, a comprehensive level corresponding to the current resource.
As shown in fig. 9B, in an embodiment, the information processing apparatus further includes a push information obtaining module 912, configured to obtain push information corresponding to the current resource according to the comprehensive level of the current resource.
As shown in FIG. 10, in one embodiment, the level determination module 910 includes:
the score obtaining unit 1002 is configured to obtain, according to the level deviation of the current resource in each target resource rating information set, a level score corresponding to the current resource in each target resource rating information set.
And a comprehensive score determining unit 1004, configured to determine a comprehensive score corresponding to the current resource according to the level scores of the current resource corresponding to the target resource rating information sets.
A level determining unit 1006, configured to determine a comprehensive level of the current resource according to the comprehensive score of the current resource.
As shown in fig. 11, in one embodiment, the composite score determining unit 1004 includes:
and an object weight obtaining unit 1102, configured to obtain an object weight corresponding to each target resource rating information set.
And the comprehensive score calculating unit 1104 is configured to obtain a comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the level score of the current resource corresponding to the target resource rating information set.
As shown in fig. 12, in one embodiment, the target weight obtaining unit 1102 includes:
an initial weight obtaining unit 1202, configured to obtain an initial weight corresponding to each target resource rating information set.
An initial score obtaining unit 1204, configured to obtain an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the level score corresponding to the current resource in the target resource rating information set.
A set composing unit 1206, configured to compose the initial scores corresponding to each current resource into an initial resource score set, and obtain resource rating information of each current resource from the current target resource rating information set to compose a current reference resource rating information set.
A coefficient calculating unit 1208, configured to calculate a correlation between the current reference resource rating information set and the initial resource scoring set, so as to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
And the target weight calculation unit 1210 is configured to obtain a target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
As shown in fig. 13, in one embodiment, the target weight calculation unit 1210 includes:
an update weight obtaining unit 1302, configured to obtain an update weight according to a current correlation coefficient corresponding to the current reference resource rating information set and an initial weight corresponding to the current target resource rating information set.
And an updating unit 1304, configured to obtain an updated initial weight corresponding to the current target resource rating information set according to the update weight, and perform the step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, and obtain a target weight corresponding to the current target resource rating information set according to the update weight.
The preset stopping condition comprises at least one of the steps that the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is larger than a first preset threshold value, the deviation value of the initial weight before updating and the initial weight after updating is smaller than a second preset threshold value, and the deviation value of the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is smaller than a third preset threshold value.
In one embodiment, the update unit 1304 is configured to: and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
In one embodiment, the coefficient calculation unit 1208 is configured to: a covariance between the initial resource score set and the current reference resource rating information set is calculated. And calculating the standard deviation corresponding to the initial resource grading set and the standard deviation corresponding to the current reference resource grading information set. And performing product operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result. And performing quotient operation according to the covariance and the standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
As shown in fig. 14, in one embodiment, the apparatus further comprises:
the growth information obtaining module 1402 is configured to obtain growth information corresponding to each resource within a preset time, where the growth information includes a growth rate and a fluctuation rate of the current resource.
An algorithm set obtaining module 1406 is configured to obtain an algorithm set, where the algorithm set includes a plurality of different resource rating algorithms.
The set composition module 1408 is configured to calculate resource rating information of each corresponding resource according to the current resource rating algorithm and the growth information corresponding to each resource and compose a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
FIG. 15 is a diagram showing an internal structure of a computer device in one embodiment. The computer device may specifically be the computer device 120 in fig. 1. As shown in fig. 15, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the information processing method. The internal memory may also have a computer program stored therein, which, when executed by the processor, causes the processor to perform the information processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 15 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the information processing apparatus provided in the present application may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 15. The memory of the computer device may store therein various program modules constituting the information processing apparatus, such as a first set acquisition module 902, a current resource acquisition module 904, a second set acquisition module 906, a deviation obtaining module 908, and a level determination module 910 shown in fig. 9A. The computer program constituted by the respective program modules causes the processor to execute the steps in the information processing method of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 15 may obtain, by the first set obtaining module 902 in the information processing apparatus shown in fig. 9A, each resource rating information set obtained by rating the resource according to different algorithms, where the resource rating information set includes a resource identifier and corresponding resource level information, and each resource rating information set has at least one same resource. The current resource is obtained from the resource rating information sets by the current resource obtaining module 904, and the current resource exists in at least two different resource rating information sets. And acquiring each target resource rating information set of the current resource through a second set acquisition module 906. The deviation obtaining module 908 obtains the level deviation of the current resource in the current target resource rating information set by calculating according to the level of the current resource in the current target resource rating information set and the level of other resources. And determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set by the level determining module 910.
In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring each resource rating information set obtained by rating the resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource; acquiring current resources from the resource rating information sets, wherein the current resources exist in at least two different resource rating information sets; acquiring a rating information set of each target resource where the current resource is located; calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources; and determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set.
In one embodiment, the step performed by the processor for determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set includes: obtaining grade scores of the current resources corresponding to the target resource rating information sets according to the grade deviation of the current resources corresponding to the target resource rating information sets; determining a comprehensive score corresponding to the current resource according to the grade scores of the current resource corresponding to the target resource grading information sets; and determining the comprehensive level of the current resource according to the comprehensive score of the current resource.
In one embodiment, the step, executed by the processor, of determining a composite score corresponding to the current resource according to the level scores corresponding to the current resource in each target resource rating information set includes: acquiring target weights corresponding to the target resource rating information sets; and obtaining the comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set.
In one embodiment, the step of obtaining the target weight corresponding to each target resource rating information set executed by the processor includes: acquiring initial weights corresponding to the target resource rating information sets; obtaining an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set; the initial scores corresponding to all the current resources form an initial resource score set, and the resource rating information of all the current resources is acquired from a current target resource rating information set to form a current reference resource rating information set; calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set; and obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
In one embodiment, the step, executed by the processor, of obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set includes: obtaining an updating weight according to a current correlation coefficient corresponding to a current reference resource rating information set and an initial weight corresponding to a current target resource rating information set; obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight, and entering a step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, obtaining a target weight corresponding to the current target resource rating information set according to the updated weight; the preset stopping condition comprises at least one of the steps that the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is larger than a first preset threshold value, the deviation value of the initial weight before updating and the initial weight after updating is smaller than a second preset threshold value, and the deviation value of the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is smaller than a third preset threshold value.
In one embodiment, the step performed by the processor of obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight includes: and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
In one embodiment, the step of calculating the correlation between the current reference resource rating information set and the initial resource score set, and obtaining the current correlation coefficient corresponding to the current reference resource rating information set, performed by the processor, includes: calculating the covariance between the initial resource grading set and the current reference resource grading information set; calculating a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set; performing product operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result; and performing quotient operation according to the covariance and the standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
In one embodiment, the steps performed when the computer program is executed by the processor further comprise: acquiring corresponding growth information of each resource in preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource; acquiring an algorithm set, wherein the algorithm set comprises a plurality of different resource rating algorithms; and calculating the corresponding resource rating information of each resource according to the current resource rating algorithm and the corresponding growth information of each resource, and forming a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
In one embodiment, the steps performed when the computer program is executed by the processor further comprise: and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of: acquiring each resource rating information set obtained by rating the resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource; acquiring current resources from the resource rating information sets, wherein the current resources exist in at least two different resource rating information sets; acquiring a rating information set of each target resource where the current resource is located; calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources; and determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set.
In one embodiment, the step performed by the processor for determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set includes: obtaining grade scores of the current resources corresponding to the target resource rating information sets according to the grade deviation of the current resources corresponding to the target resource rating information sets; determining a comprehensive score corresponding to the current resource according to the grade score corresponding to the current resource in each target resource rating information set; and determining the comprehensive grade of the current resource according to the comprehensive score of the current resource.
In one embodiment, the step performed by the processor of determining a composite score corresponding to the current resource according to the level scores corresponding to the current resource in the target resource rating information sets includes: acquiring target weights corresponding to the target resource rating information sets; and obtaining the comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set.
In one embodiment, the step of obtaining the target weight corresponding to each target resource rating information set executed by the processor includes: acquiring initial weights corresponding to the target resource rating information sets; obtaining an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set; the initial scores corresponding to all the current resources form an initial resource score set, and the resource rating information of all the current resources is acquired from a current target resource rating information set to form a current reference resource rating information set; calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set; and obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
In one embodiment, the step, executed by the processor, of obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set includes: obtaining an updating weight according to a current correlation coefficient corresponding to a current reference resource rating information set and an initial weight corresponding to a current target resource rating information set; obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight, and entering a step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, obtaining a target weight corresponding to the current target resource rating information set according to the updated weight; the preset stopping condition comprises at least one of the steps that the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is larger than a first preset threshold value, the deviation value of the initial weight before updating and the initial weight after updating is smaller than a second preset threshold value, and the deviation value of the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is smaller than a third preset threshold value.
In one embodiment, the step performed by the processor of obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight includes: and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
In one embodiment, the step of calculating the correlation between the current reference resource rating information set and the initial resource score set, and obtaining the current correlation coefficient corresponding to the current reference resource rating information set, performed by the processor, includes: calculating the covariance between the initial resource grading set and the current reference resource grading information set; calculating a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set; performing product operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result; and carrying out quotient operation according to the covariance and standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
In one embodiment, the method performed by the processor further comprises: acquiring growth information of the current resource within preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource; calculating the growth information corresponding to the current resource by using different algorithms to obtain the resource rating information of the corresponding current resource; and forming a resource rating information set by using the resource rating information of each current resource obtained by adopting the same algorithm. Acquiring each resource rating information set obtained by rating the resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource; acquiring current resources from the resource rating information sets, wherein the current resources exist in at least two different resource rating information sets; acquiring a rating information set of each target resource where the current resource is located; acquiring the grade difference between the current resource and other resources in the current target resource rating information set to obtain the grade deviation of the current resource in the current target resource rating information set; determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set; and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
In one embodiment, the step performed by the processor for determining the comprehensive level corresponding to the current resource according to the level deviation of the current resource corresponding to each target resource rating information set includes: obtaining grade scores of the current resources corresponding to the target resource rating information sets according to the grade deviation of the current resources corresponding to the target resource rating information sets; determining a comprehensive score corresponding to the current resource according to the grade scores of the current resource corresponding to the target resource grading information sets; and determining the comprehensive level of the current resource according to the comprehensive score of the current resource.
In one embodiment, the step performed by the processor of determining a composite score corresponding to the current resource according to the level scores corresponding to the current resource in the target resource rating information sets includes: acquiring target weights corresponding to the target resource rating information sets; and obtaining the comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set.
In one embodiment, the step of obtaining the target weight corresponding to each target resource rating information set executed by the processor includes: acquiring initial weights corresponding to the target resource rating information sets; obtaining an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set; the initial scores corresponding to all the current resources form an initial resource score set, and the resource rating information of all the current resources is acquired from a current target resource rating information set to form a current reference resource rating information set; calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set; and obtaining a target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set.
In one embodiment, the step of obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set, which is executed by the processor, includes: obtaining an updating weight according to a current correlation coefficient corresponding to a current reference resource rating information set and an initial weight corresponding to a current target resource rating information set; obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight, and entering a step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, obtaining a target weight corresponding to the current target resource rating information set according to the updated weight; the preset stopping condition comprises at least one of the steps that the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is larger than a first preset threshold value, the deviation value of the initial weight before updating and the initial weight after updating is smaller than a second preset threshold value, and the deviation value of the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is smaller than a third preset threshold value.
In one embodiment, the step performed by the processor of obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight includes: and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
In one embodiment, the step performed by the processor of calculating the correlation between the current reference resource rating information set and the initial resource score set to obtain a current correlation coefficient corresponding to the current reference resource rating information set includes: calculating the covariance between the initial resource grading set and the current reference resource grading information set; calculating a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set; performing product operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result; and carrying out quotient operation according to the covariance and standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
In one embodiment, the steps performed when the computer program is executed by the processor further comprise: acquiring corresponding growth information of each resource in preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource; acquiring an algorithm set, wherein the algorithm set comprises a plurality of different resource rating algorithms; and calculating the corresponding resource rating information of each resource according to the current resource rating algorithm and the corresponding growth information of each resource, and forming a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
In one embodiment, the steps performed when the computer program is executed by the processor further comprise: and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (14)

1. An information processing method, the method comprising:
acquiring each resource rating information set obtained by rating resources according to different algorithms, wherein the resource rating information set comprises resource identifications and corresponding resource level information, and each resource rating information set has at least one same resource;
acquiring current resources from the resource rating information sets, wherein the current resources at least exist in two different resource rating information sets;
acquiring a rating information set of each target resource where the current resource is located;
calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources;
obtaining grade scores of the current resources corresponding to the target resource rating information sets according to grade deviations of the current resources corresponding to the target resource rating information sets;
acquiring initial weights corresponding to the target resource rating information sets;
obtaining an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set;
forming an initial resource rating set by the initial rating corresponding to each current resource, and obtaining resource rating information of each current resource from the current target resource rating information set to form a current reference resource rating information set;
calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set;
obtaining a target weight corresponding to the current target resource rating information set according to a current correlation coefficient corresponding to the current reference resource rating information set and an initial weight corresponding to the current target resource rating information set;
obtaining a comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set;
and determining the comprehensive level of the current resource according to the comprehensive score of the current resource.
2. The method according to claim 1, wherein the step of obtaining the target weight corresponding to the current target resource rating information set according to the current correlation coefficient corresponding to the current reference resource rating information set and the initial weight corresponding to the current target resource rating information set comprises:
obtaining an updating weight according to a current correlation coefficient corresponding to the current reference resource rating information set and an initial weight corresponding to the current target resource rating information set;
obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight, and entering the step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, and obtaining a target weight corresponding to the current target resource rating information set according to the updated weight;
the preset stop condition comprises at least one of the steps that the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is larger than a first preset threshold value, the deviation value of the initial weight before updating and the initial weight after updating is smaller than a second preset threshold value, and the deviation value of the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is smaller than a third preset threshold value.
3. The method according to claim 2, wherein the step of obtaining an updated initial weight corresponding to the current target resource rating information set according to the updated weight comprises:
and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
4. The method according to claim 1, wherein the step of calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set comprises:
calculating a covariance between the initial set of resource scores and the current set of reference resource rating information;
calculating a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set;
performing multiplication operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result;
and carrying out quotient operation according to the covariance and the standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
5. The method of claim 1, further comprising:
acquiring corresponding growth information of each resource in preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource;
acquiring an algorithm set, wherein the algorithm set comprises a plurality of different resource rating algorithms;
and calculating the corresponding resource rating information of each resource according to the current resource rating algorithm and the growth information corresponding to each resource, and forming a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
6. The method according to any one of claims 1 to 5, further comprising:
and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
7. An information processing apparatus, the apparatus comprising:
the resource grading information collection comprises resource identification and corresponding resource grade information, and each resource grading information collection has at least one same resource;
a current resource obtaining module, configured to obtain a current resource from the resource rating information set, where the current resource exists in at least two different resource rating information sets;
the second set acquisition module is used for acquiring the rating information sets of all target resources where the current resources are located;
the deviation obtaining module is used for calculating the grade deviation of the current resource in the current target resource rating information set according to the grade of the current resource in the current target resource rating information set and the grade of other resources;
a level determining module, configured to obtain, according to a level deviation of the current resource in each target resource rating information set, a level score corresponding to the current resource in each target resource rating information set; acquiring initial weights corresponding to the target resource rating information sets; obtaining an initial score corresponding to the current resource according to the initial weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set; forming an initial resource rating set by the initial rating corresponding to each current resource, and obtaining resource rating information of each current resource from the current target resource rating information set to form a current reference resource rating information set; calculating the correlation between the current reference resource rating information set and the initial resource rating set to obtain a current correlation coefficient corresponding to the current reference resource rating information set; obtaining a target weight corresponding to the current target resource rating information set according to a current correlation coefficient corresponding to the current reference resource rating information set and an initial weight corresponding to the current target resource rating information set; obtaining a comprehensive score of the current resource according to the target weight corresponding to each target resource rating information set and the grade score of the current resource corresponding to the target resource rating information set; and determining the comprehensive level of the current resource according to the comprehensive score of the current resource.
8. The apparatus of claim 7, wherein the level determining module is further configured to:
obtaining an updating weight according to a current correlation coefficient corresponding to the current reference resource rating information set and an initial weight corresponding to the current target resource rating information set;
obtaining an updated initial weight corresponding to the current target resource rating information set according to the update weight, and entering the step of obtaining the initial weight corresponding to each target resource rating information set until a preset stop condition is met, obtaining a target weight corresponding to the current target resource rating information set according to the update weight;
the preset stop condition includes at least one of the number of times of entering the step of obtaining the initial weight corresponding to each target resource rating information set is greater than a first preset threshold, a deviation value according to the initial weight before updating and the initial weight after updating is less than a second preset threshold, and a deviation value according to the initial score obtained according to the initial weight before updating and the initial score obtained according to the initial weight after updating is less than a third preset threshold.
9. The apparatus of claim 8, wherein the level determining module is further configured to:
and normalizing the updating weight to obtain an updated initial weight corresponding to the current target resource rating information set.
10. The apparatus of claim 7, wherein the level determining module is further configured to:
calculating a covariance between the initial set of resource scores and the current set of reference resource rating information;
calculating a standard deviation corresponding to the initial resource rating set and a standard deviation corresponding to the current reference resource rating information set;
performing multiplication operation according to the standard deviation corresponding to the initial resource rating set and the standard deviation corresponding to the current reference resource rating information set to obtain a standard deviation calculation result;
and carrying out quotient operation according to the covariance and the standard deviation calculation result to obtain a current correlation coefficient corresponding to the current reference resource rating information set.
11. The apparatus of claim 7, wherein the apparatus is further configured to:
acquiring corresponding growth information of each resource in preset time, wherein the growth information comprises the growth rate and the fluctuation rate of the current resource;
acquiring an algorithm set, wherein the algorithm set comprises a plurality of different resource rating algorithms;
and calculating the corresponding resource rating information of each resource according to the current resource rating algorithm and the growth information corresponding to each resource, and forming a resource rating information set corresponding to the current resource rating algorithm until each resource rating algorithm in the algorithm set has a corresponding resource rating information set.
12. The apparatus of any one of claims 7 to 11, further configured to:
and obtaining the push information corresponding to the current resource according to the comprehensive level of the current resource.
13. A computer arrangement comprising a memory and a processor, a computer program being stored in the memory, which computer program, when being executed by the processor, causes the processor to carry out the steps of the information processing method as claimed in any one of the claims 1 to 6.
14. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, causes the processor to carry out the steps of the information processing method according to any one of claims 1 to 6.
CN201711164561.5A 2017-11-21 2017-11-21 Information processing method, information processing device, computer equipment and storage medium Active CN109816187B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711164561.5A CN109816187B (en) 2017-11-21 2017-11-21 Information processing method, information processing device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711164561.5A CN109816187B (en) 2017-11-21 2017-11-21 Information processing method, information processing device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN109816187A CN109816187A (en) 2019-05-28
CN109816187B true CN109816187B (en) 2022-09-23

Family

ID=66599635

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711164561.5A Active CN109816187B (en) 2017-11-21 2017-11-21 Information processing method, information processing device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN109816187B (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102760275B (en) * 2012-05-10 2015-09-09 上海交通大学 A kind of information handling system for agriculture of city type comprehensive evaluation
EP2701111A1 (en) * 2012-08-24 2014-02-26 Nederlandse Organisatie voor toegepast -natuurwetenschappelijk onderzoek TNO Group composition based recommender system and method
US20170046752A1 (en) * 2015-08-13 2017-02-16 International Business Machines Corporation Multi-criteria rating for different entity types
CN105468722A (en) * 2015-11-20 2016-04-06 百度在线网络技术（北京）有限公司 Reputation information processing method and device
CN107203558B (en) * 2016-03-17 2021-03-09 腾讯科技（深圳）有限公司 Object recommendation method and device, and recommendation information processing method and device

Also Published As

Publication number Publication date
CN109816187A (en) 2019-05-28

Similar Documents

Publication Publication Date Title
CN109902708B (en) Recommendation model training method and related device
CN109241415B (en) Project recommendation method and device, computer equipment and storage medium
CN108427708B (en) Data processing method, data processing apparatus, storage medium, and electronic apparatus
CN112148987B (en) Message pushing method based on target object activity and related equipment
CN108491511B (en) Data mining method and device based on graph data and model training method and device
CN112328909B (en) Information recommendation method and device, computer equipment and medium
CN110287250B (en) User grade quantification method and device
CN108182633B (en) Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium
CN107203558B (en) Object recommendation method and device, and recommendation information processing method and device
CN113609345B (en) Target object association method and device, computing equipment and storage medium
CN112308173B (en) Multi-target object evaluation method based on multi-evaluation factor fusion and related equipment thereof
CN115082209A (en) Business data risk early warning method and device, computer equipment and storage medium
CN113516417A (en) Service evaluation method and device based on intelligent modeling, electronic equipment and medium
JP2014206791A (en) Social network information processor, processing method, and processing program
CN111177500A (en) Data object classification method and device, computer equipment and storage medium
CN113850669A (en) User grouping method and device, computer equipment and computer readable storage medium
Song et al. Research on personalized hybrid recommendation system
CN109816187B (en) Information processing method, information processing device, computer equipment and storage medium
CN114912627A (en) Recommendation model training method, system, computer device and storage medium
CN114092216A (en) Enterprise credit rating method, apparatus, computer device and storage medium
CN113850523A (en) ESG index determining method based on data completion and related product
CN112862570A (en) Business display industry chain transaction recommendation method, device, equipment, storage medium and system
CN110659347A (en) Associated document determining method and device, computer equipment and storage medium
CN110610378A (en) Product demand analysis method and device, computer equipment and storage medium
CN112861034B (en) Method, device, equipment and storage medium for detecting information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant