CN115587285A

CN115587285A - Target object identification method and device, computer equipment and storage medium

Info

Publication number: CN115587285A
Application number: CN202211382111.4A
Authority: CN
Inventors: 徐春艳; 詹振国; 杜利仲
Original assignee: Industrial and Commercial Bank of China Ltd ICBC; ICBC Technology Co Ltd
Current assignee: Industrial and Commercial Bank of China Ltd ICBC; ICBC Technology Co Ltd
Priority date: 2022-11-07
Filing date: 2022-11-07
Publication date: 2023-01-10

Abstract

The application relates to a target object identification method, a target object identification device, computer equipment and a storage medium, and relates to the field of big data. The method comprises the following steps: determining a target emotion factor of an object to be recognized according to user information of the object to be recognized, determining a target group corresponding to the object to be recognized according to the target emotion factor of the object to be recognized, wherein the target emotion factors of all the objects in the group are within a numerical range corresponding to the group, when the occurrence probability of an event corresponding to the target group is greater than or equal to a first numerical value, determining a target association emotion factor of the object to be recognized according to association information of the object to be recognized, the event occurrence probability represents the probability of the occurrence of the target event, and the occurrence probability of the event is adjusted according to the target association emotion factor to obtain the occurrence probability of the target event of the object to be recognized, and when the occurrence probability of the target event of the object to be recognized is greater than or equal to a second numerical value, taking the object to be recognized as the target object. By adopting the method, the accuracy of target object identification can be improved.

Description

Target object identification method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of big data technologies, and in particular, to a target object identification method and apparatus, a computer device, and a storage medium.

Background

With the development of network technology, a target object identification technology based on big data analysis appears, and the technology analyzes big data information of an object to be identified in a network to finally identify a target object meeting conditions, wherein the target object can be an object in which a target event occurs.

In the traditional target object identification technology, the target to be identified can be analyzed through objective information such as virtual resources and resource interaction data owned by the target to be identified, so that the probability of the target event to occur is obtained.

However, in the process of identifying the target object, the target event occurrence probability is analyzed only through objective information, the information amount is small, that is, the analysis basis is not comprehensive, so that the accuracy of predicting the target event occurrence probability is low, and the accuracy of identifying the target object is low.

Disclosure of Invention

In view of the above, it is necessary to provide a target object identification method, an apparatus, a computer device, a computer readable storage medium, and a computer program product capable of accurately identifying a target object in view of the above technical problems.

In a first aspect, the present application provides a target object identification method. The method comprises the following steps:

determining a target emotion factor of an object to be identified according to user information of the object to be identified;

determining a target group corresponding to the object to be identified from groups according to the target emotion factors of the object to be identified, wherein the target emotion factors of the objects in the groups are in a numerical range corresponding to the groups aiming at any one group;

determining a target associated emotional factor of the object to be identified according to the associated information of the object to be identified under the condition that the event occurrence probability corresponding to the target group is greater than or equal to a first numerical value, wherein the event occurrence probability is used for representing the probability of occurrence of a target event;

adjusting the event occurrence probability according to the target associated emotion factors to obtain the target event occurrence probability of the object to be identified;

and taking the object to be recognized as a target object when the target event occurrence probability of the object to be recognized is greater than or equal to a second numerical value.

In one embodiment, the adjusting the event occurrence probability according to the target associated emotion factor to obtain the target event occurrence probability of the object to be recognized includes:

acquiring a probability correction formula corresponding to the target group;

and inputting the target associated emotion factor of the object to be recognized into the probability correction formula to obtain the target event occurrence probability of the object to be recognized.

In one embodiment, the method further comprises:

aiming at any one group, determining a factor coefficient corresponding to the target associated emotion factor according to the event occurrence probability corresponding to the group, the target associated emotion factor of each historical object in the group and the event occurrence tagging probability of each historical object in the group;

and constructing a probability correction formula corresponding to the group according to the factor coefficient and the event occurrence probability corresponding to the group.

In one embodiment, the method further comprises:

aiming at any one group, determining a first numerical value corresponding to a historical object of the target event in the group;

and determining the occurrence probability of the event corresponding to the group according to the first numerical value and the number of the historical objects in the group.

In one embodiment, the event occurrence probability corresponding to the group includes an event occurrence probability corresponding to at least one event, and the method further includes:

matching the target event from the target group;

and under the condition that the target event is matched, taking the event occurrence probability of the target event as the event occurrence probability corresponding to the target group.

In one embodiment, the association information includes at least one of user information of an association object having an association relation with the object to be identified and domain information of a domain in which the object to be identified is located, and the target association emotional factor includes at least one of a first target association emotional factor and a second target association emotional factor; the determining the target associated emotional factor of the object to be identified according to the associated information of the object to be identified includes:

under the condition that the associated information comprises the user information of the associated objects, acquiring each associated object of the objects to be identified;

determining the associated emotional factors of the associated objects according to the user information of the associated objects;

determining a first target associated emotion factor of the object to be identified according to the associated emotion factor of each associated object;

or determining a second target associated emotion factor of the object to be recognized according to the field information under the condition that the associated information comprises the field information.

In a second aspect, the present application further provides a target object recognition apparatus. The device comprises:

the first determining module is used for determining a target emotion factor of an object to be identified according to user information of the object to be identified;

a second determining module, configured to determine, according to the target emotion factor of the object to be recognized, a target group corresponding to the object to be recognized from a group, where, for any one of the groups, the target emotion factor of each object in the group is within a value range corresponding to the group;

a third determining module, configured to determine a target associated emotion factor of the object to be identified according to the associated information of the object to be identified when an event occurrence probability corresponding to the target group is greater than or equal to a first numerical value, where the event occurrence probability is used to represent a probability of occurrence of a target event;

the adjusting module is used for adjusting the event occurrence probability according to the target associated emotion factor to obtain the target event occurrence probability of the object to be identified;

and the identification module is used for taking the object to be identified as a target object under the condition that the target event occurrence probability of the object to be identified is greater than or equal to a second numerical value.

In one embodiment, the adjusting module is further configured to:

acquiring a probability correction formula corresponding to the target group;

In one embodiment, the apparatus further comprises:

a fourth determining module, configured to determine, for any one of the groups, a factor coefficient corresponding to the target associated emotion factor according to the event occurrence probability corresponding to the group, the target associated emotion factor of each historical object in the group, and the event occurrence tagging probability of each historical object in the group;

and the construction module is used for constructing a probability correction formula corresponding to the group according to the factor coefficient and the event occurrence probability corresponding to the group.

In one embodiment, the apparatus further comprises:

a fifth determining module, configured to determine, for any one of the groups, a first numerical value corresponding to a history object in the group where the target event occurs;

a sixth determining module, configured to determine, according to the first numerical value and the number of the historical objects in the group, an event occurrence probability corresponding to the group.

In one embodiment, the event occurrence probability corresponding to the group includes an event occurrence probability corresponding to at least one event, and the apparatus further includes:

and the matching module is used for matching the target event from the target group, and taking the event occurrence probability of the target event as the event occurrence probability corresponding to the target group under the condition that the target event is matched.

In one embodiment, the association information includes at least one of user information of an association object having an association relation with the object to be identified and domain information of a domain where the object to be identified is located, and the target association emotion factor includes at least one of a first target association emotion factor and a second target association emotion factor; the third determining module is further configured to:

determining a first target associated emotional factor of the object to be identified according to the associated emotional factor of each associated object;

or under the condition that the associated information comprises the domain information, determining a second target associated emotion factor of the object to be identified according to the domain information.

In a third aspect, the application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

determining a target emotion factor of an object to be recognized according to user information of the object to be recognized;

determining a target group corresponding to the object to be identified from groups according to the target emotion factors of the object to be identified, wherein the target emotion factor of each object in the group is in a numerical value range corresponding to the group aiming at any group;

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

under the condition that the event occurrence probability corresponding to the target group is larger than or equal to a first numerical value, determining a target associated emotional factor of the object to be recognized according to the associated information of the object to be recognized, wherein the event occurrence probability is used for representing the probability of occurrence of a target event;

The target object identification method, the target object identification device, the computer equipment, the storage medium and the computer program product are characterized in that a target emotion factor of an object to be identified is determined according to user information of the object to be identified, a target group corresponding to the object to be identified is determined from groups according to the target emotion factor of the object to be identified, the target emotion factor of each object in each group is in a numerical value range corresponding to each group, under the condition that the event occurrence probability corresponding to each target group is larger than or equal to a first numerical value, the target associated emotion factor of the object to be identified is determined according to the associated information of the object to be identified, the event occurrence probability is used for representing the probability of the target event, the event occurrence probability is adjusted according to the target associated emotion factor to obtain the target event occurrence probability of the object to be identified, and under the condition that the target event occurrence probability of the object to be identified is larger than or equal to a second numerical value, the object to be identified is used as the target object. Based on the target object identification method, the target object identification device, the computer equipment, the storage medium and the computer program product, the event occurrence probability is determined according to the user information of the object to be identified and the group to which the object to be identified belongs, and is adjusted according to the associated information of the object to be identified under the condition that the event occurrence probability meets a certain condition, so that the target event occurrence probability is obtained.

Drawings

FIG. 1 is a schematic flow chart diagram illustrating a method for identifying a target object in one embodiment;

FIG. 2 is a schematic flow chart diagram illustrating a target object recognition method according to another embodiment;

FIG. 3 is a flowchart illustrating a target object recognition method according to another embodiment;

FIG. 4 is a flowchart illustrating a target object recognition method according to another embodiment;

FIG. 5 is a flowchart illustrating a target object recognition method according to another embodiment;

FIG. 6 is a flowchart illustrating a target object recognition method according to another embodiment;

FIG. 7 is a block diagram of a target object recognition apparatus in one embodiment;

FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 present application and are not intended to limit the present application.

In an embodiment, as shown in fig. 1, a target object identification method is provided, and this embodiment is illustrated by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. In this embodiment, the method includes the steps of:

and step 102, determining a target emotion factor of the object to be recognized according to the user information of the object to be recognized.

The object to be recognized is an object to be subjected to target object recognition, and the user information is information generated when the object to be recognized uses each network platform, for example: the user information can be word information issued by the object to be recognized on the social platform, keyword extraction can be performed on the user information of the object to be recognized through the text extraction model, and the target emotion factor of the object to be recognized is determined according to each keyword. The target emotion factor can be used for representing subjective emotion of the object to be identified, the target emotion factor can be positive number, negative number or 0, and when the target emotion factor is positive number, the target emotion factor indicates that the object to be identified is in positive, optimistic and positive emotional tendency; when the target emotion factor is negative, the negative emotion factor indicates that the object to be identified is in negative, pessimistic and negative emotional tendency; when the target emotion factor is 0, the neutral, objective and rational emotional tendency of the object to be recognized is represented, and the absolute value of the target emotion factor is used for representing the emotional intensity of the object to be recognized.

For example, the target emotion factor may be determined in the following manner: firstly, an emotion keyword database is established, the database comprises a plurality of emotion keywords and emotion scores corresponding to the emotion keywords, then, keywords in user information of an object to be recognized are extracted based on a Natural Language Processing (NLP) technology, the extracted keywords are matched with the emotion keywords in the emotion keyword database to obtain the emotion scores corresponding to the keywords, and the emotion scores are accumulated to obtain a target emotion factor of the object to be recognized.

Illustratively, taking an object to be identified as a client a and user information as text information published by the client a on a social platform as an example, an emotion keyword database is constructed and shown in table one, and keywords are extracted from the text information published by the client a on the social platform by using an NLP technology: keyword 1, keyword 2, keyword 3, and keyword 4, which are matched in table, the target emotion factor of client a is-70 +30= -80.

Watch 1

It should be noted that the foregoing example of the present application is only one example of determining the target emotion factor of the object to be recognized, and the present application does not specifically limit the method for determining the target emotion factor of the object to be recognized.

And 104, determining a target group corresponding to the object to be identified from the groups according to the target emotion factors of the object to be identified, wherein the target emotion factors of all the objects in the group are in the numerical range corresponding to the group aiming at any group.

In the embodiment of the application, different groups correspond to different numerical ranges of the target emotion factors, and the target emotion factors of all the objects in the groups are in the numerical ranges corresponding to the groups, so that the target emotion factors of the objects to be recognized can be matched with the numerical ranges corresponding to the groups, and when the numerical ranges to which the target emotion factors of the objects to be recognized belong are matched, the target groups corresponding to the objects to be recognized can be determined to be the groups corresponding to the numerical ranges.

Illustratively, still taking the above example as an example, the target emotion factor of the client a is-80, the known value range 1 corresponding to the group 1 is-100 to-70, the value range 2 corresponding to the group 2 is-70 to 30, the value range 3 corresponding to the group 3 is-30 to 40, the value range 4 corresponding to the group 4 is 40 to 100, and the target group corresponding to the client a can be determined to be the group 1 according to the target emotion factor-80 within the value range 1.

And 106, under the condition that the event occurrence probability corresponding to the target group is greater than or equal to the first numerical value, determining a target associated emotional factor of the object to be identified according to the associated information of the object to be identified, wherein the event occurrence probability is used for representing the probability of occurrence of the target event.

In the embodiment of the present application, the event occurrence probability may be used to represent the probability of occurrence of a target event, the target event may be set by a worker according to actual needs, different target events may be set according to the time period of occurrence of a certain event, or different target events may also be set according to the difference of occurrence events, for example: the target event is the occurrence of event A within the last 3 months, or the target event is the occurrence of event A within the last 6 months, or the target event is the occurrence of event B within the last 3 months.

After the target group corresponding to the object to be recognized is determined, the event occurrence probability corresponding to the target group can represent the probability of the object to be recognized for the target event to occur in the future to a certain extent, but the accuracy is not high, if the target object is recognized directly according to the event occurrence probability corresponding to the target group, the accuracy of target object recognition is reduced, so that the event occurrence probability corresponding to the target group is compared with a first numerical value (which can be set by a worker), and the object to be recognized, of which the event occurrence probability corresponding to the target group is greater than or equal to the first numerical value, is further processed.

Specifically, when the occurrence probability of the event corresponding to the target group corresponding to the object to be identified is greater than or equal to the first numerical value, the association information of the object to be identified may be obtained, where the association information is information related to the object to be identified, and for example, the association information may be user information of an association object having an association relationship with the object to be identified, for example: the associated information is user information of an object interacting with the object to be recognized on the social platform, or the associated information may also be domain information of a domain where the object to be recognized is located, for example: the associated information is the domain information of the professional domain where the object to be identified is located.

Secondly, extracting keywords from the associated information of the object to be recognized based on the NLP technology, and determining a target associated emotion factor of the object to be recognized according to each keyword, where the specific step of determining the target associated emotion factor may refer to the description about determining the target emotion factor in the above embodiments, and is not described herein again.

And 108, adjusting the event occurrence probability according to the target associated emotion factors to obtain the target event occurrence probability of the object to be identified.

In the embodiment of the application, for one object to be recognized, a plurality of target associated emotion factors can be determined, wherein each target associated emotion factor has a certain influence on the probability of occurrence of a target event (namely, the event occurrence probability) of the object to be recognized in the future, so that the event occurrence probability can be adjusted according to the target associated emotion factors to obtain the target event occurrence probability of the object to be recognized.

And step 110, taking the object to be recognized as the target object when the target event occurrence probability of the object to be recognized is greater than or equal to the second numerical value.

In the embodiment of the application, the target event occurrence probability of the object to be recognized is compared with a second numerical value (which can be set by a worker), and the object to be recognized is taken as the target object when the target event occurrence probability of the object to be recognized is greater than or equal to the second numerical value.

For example, taking the object to be identified as the client a, the target event as the event a, the second value as 70%, and the target event occurrence probability of the client a as 83%, where the target event occurrence probability of the client a is greater than the second value, the client a is the target object, that is, the client a is the client needing the attention of the staff.

According to the target object identification method, the occurrence probability of an event is determined according to the user information of the object to be identified and the group to which the object to be identified belongs, the occurrence probability of the event is adjusted according to the associated information of the object to be identified under the condition that the occurrence probability of the event meets a certain condition, and the occurrence probability of the target event is obtained.

And secondly, the object to be recognized is further processed only when the occurrence probability of the event corresponding to the group to which the object to be recognized belongs is greater than or equal to the first numerical value, so that the cost of data acquisition and processing is saved.

In one embodiment, as shown in fig. 2, step 108, adjusting the event occurrence probability according to the target associated emotion factor to obtain a target event occurrence probability of the object to be identified, includes:

step 202, obtaining a probability correction formula corresponding to the target group.

In the embodiment of the application, for each object in the same group, the target associated emotion factor of each object has the same influence trend on the event occurrence probability corresponding to the group, so that the probability correction formula corresponding to the group can be determined according to the rule, wherein the probability correction formula represents a functional relationship between the event occurrence probability, the target associated emotion factor of the object to be identified, and the target event occurrence probability corresponding to the object to be identified.

The probability correction formula corresponding to the target group can be obtained according to the target group corresponding to the object to be identified.

And 204, inputting the target associated emotion factors of the object to be recognized into a probability correction formula to obtain the target event occurrence probability of the object to be recognized.

In the embodiment of the application, the target associated emotion factor of the object to be recognized can be input into the probability correction formula, and the target event occurrence probability of the object to be recognized is obtained through calculation. Illustratively, still taking the above example as an example, taking the target associated emotion factor 1 of the client a as 80, the target associated emotion factor 2 as-50, the target associated emotion factor 3 as 20, and the probability correction formula as 85% +0.15 + target associated emotion factor 1+0.25 + target associated emotion factor 2+0.02 + target event occurrence probability as an example, respectively inputting the three target associated emotion factors into the probability correction formula to obtain the target event occurrence probability =85% +0.15 + 80+0.25 (-50) +0.02 + 20=75%.

In the embodiment, a probability correction formula corresponding to the object to be recognized is determined according to a target group to which the object to be recognized belongs, then, a target associated emotion factor of the object to be recognized is input into the probability correction formula, the event occurrence probability is adjusted, and the target event occurrence probability is further determined, wherein the target associated emotion factor is obtained according to the associated information of the object to be recognized, that is, the event occurrence probability is adjusted according to the associated information of the object to be recognized in the method, so that the target event occurrence probability is obtained, comprehensive analysis is performed by combining the user information and the associated information of the object to be recognized, more accurate target event occurrence probability can be obtained, and the accuracy of target object recognition is further improved.

In one embodiment, as shown in fig. 3, the method further comprises:

step 302, aiming at any group, determining a factor coefficient corresponding to the target associated emotion factor according to the event occurrence probability corresponding to the group, the target associated emotion factor of each historical object in the group and the event occurrence tagging probability of each historical object in the group.

In the embodiment of the application, before an object to be identified is identified, a probability correction formula corresponding to each group may be determined, specifically, for any group, an event occurrence probability corresponding to the group is known, a target associated emotion factor of each history object may be determined according to history associated information of each history object in the group in a past period (for example, in past six months), and a worker (for example, a credit specialist) predicts a probability that a target event occurs in the future to the history object according to objective information (for example, history resource interaction information) of the history object, user information, and associated information, so as to obtain an event occurrence tagging probability of each history object. And then, determining a factor coefficient corresponding to the target associated emotion factor according to the event occurrence probability corresponding to the group, the target associated emotion factor of each historical object in the group and the event occurrence tagging probability of each historical object in the group.

In this embodiment, the factor coefficient corresponding to the target associated emotion factor may be determined according to a regression calculation method, that is, the event occurrence probability corresponding to the group and the target associated emotion factor of each historical object in the group are used as independent variables, the event occurrence tagging probability of each historical object is used as a dependent variable, and the factor coefficient corresponding to each target associated emotion factor is obtained through regression calculation, where the factor coefficient corresponds to the target associated emotion factor one to one.

And 304, constructing a probability correction formula corresponding to the group according to the factor coefficient and the event occurrence probability corresponding to the group.

In the embodiment of the application, after each factor coefficient is obtained, a probability correction formula corresponding to the group is constructed according to the factor coefficient and the event occurrence probability corresponding to the group. Illustratively, the probability correction formula is: the event occurrence probability + factor coefficient 1+ target associated emotion factor 1+ factor coefficient 2+ target associated emotion factor 2+ factor coefficient 3= target event occurrence probability corresponding to the group.

In the embodiment, the probability correction formula is determined according to the event occurrence probability, the target associated emotion factor of each historical object in the group and the event occurrence tagging probability of each historical object in the group, then the event occurrence probability can be further adjusted according to the associated information of the object to be identified to obtain the target event occurrence probability, and comprehensive analysis is performed by combining the user information and the associated information of the object to be identified, so that more accurate target event occurrence probability can be obtained, and the accuracy of target object identification is improved.

In one embodiment, as shown in fig. 4, the method further comprises:

step 402, aiming at any group, determining a first numerical value corresponding to a history object of a target event in the group.

In the embodiment of the present application, before identifying an object to be identified, event occurrence probabilities corresponding to each group need to be determined, and the specific steps of determining the event occurrence probabilities are as follows: aiming at any group, historical resource interaction data of each historical object in the group in a past period of time is obtained, and according to the historical resource interaction data of each historical object, the number of the historical objects is determined to generate a target event (namely a first numerical value).

Illustratively, taking historical objects as historical clients and historical resource interaction data as resource interaction data of each historical client in the past year as an example, the group 1 comprises 100 historical clients, the preset event is an event a, and according to the resource interaction data of 100 historical clients in the past year, if 80 historical clients have the event a, the first value is 80.

Step 404, determining the event occurrence probability corresponding to the group according to the first value and the number of the historical objects in the group.

In the embodiment of the present application, the first value is divided by the number of the historical objects in the group, and the ratio is the occurrence probability of the event corresponding to the group. Illustratively, still taking the above example as an example, the first value is 80, and the group 1 includes 100 history clients, then the time occurrence probability corresponding to the group 1 is 80%.

In this embodiment, each group is obtained by classifying according to a target emotion factor of an object, and then according to historical resource interaction data of each historical object included in the group, an event occurrence probability corresponding to the group is determined by a mathematical statistics method, that is, the event occurrence probability obtained at this time is obtained through the target emotion factor of the object, and the event occurrence probability can represent the probability of the target event occurring to each object in the same group to a certain extent, and then the event occurrence probability is adjusted according to the association information of the object to be identified, so that a more accurate target event occurrence probability is obtained, and further, the accuracy of identifying the target object is improved.

In one embodiment, as shown in fig. 5, the event occurrence probability corresponding to the group includes an event occurrence probability corresponding to at least one event, and the method further includes:

step 502, matching target events from a target group;

and step 504, taking the event occurrence probability of the target event as the event occurrence probability corresponding to the target group under the condition that the target event is matched.

In the embodiment of the present application, for a group, the event occurrence probabilities of different target events corresponding to the group are different, that is, the event occurrence probabilities corresponding to the group are multiple, including the event occurrence probabilities of the target events corresponding to the group. For example, taking group 1 as an example, the corresponding event occurrence probability includes: the event occurrence probability corresponding to the event a is 50%, the event occurrence probability corresponding to the event B is 80%, and the event occurrence probability corresponding to the event C is 95%.

When the browsed target event is the same as the target event of the object to be identified (namely, the target event is matched with the target event), the event occurrence probability corresponding to the target object at the moment is used as the event occurrence probability corresponding to the target group.

Illustratively, still taking the above example as an example, the event occurrence probability corresponding to the group 1 includes: the event occurrence probability corresponding to the event A is 50%, the event occurrence probability corresponding to the event B is 80%, the event occurrence probability corresponding to the event C is 95%, the target event of the object to be identified is the event B, the target event is matched from the events, and the event occurrence probability corresponding to the event B is 80% as the event occurrence probability corresponding to the group.

In this embodiment, different target events may also correspond to different probability correction formulas, so that, when a target event is matched, the probability correction formula corresponding to the target event may be used as the probability correction formula corresponding to the target group.

In the embodiment of the application, the event occurrence probability corresponding to the group may include event occurrence probabilities of different target events corresponding to the group, wherein the target event may be set by a worker according to actual needs, in the target object identification process, the target event is matched from the target group, the event occurrence probability corresponding to the matched target event is used as the event occurrence probability corresponding to the target group, and then subsequent identification processing may be performed on the basis of the event occurrence probability, so that target object identification requirements for different target events may be met, and the identification range of the target object is improved.

In one embodiment, as shown in fig. 6, the association information includes at least one of user information of an association object having an association relationship with the object to be recognized and domain information of a domain where the object to be recognized is located, and the target association emotion factor includes at least one of a first target association emotion factor and a second target association emotion factor; step 106, determining a target associated emotion factor of the object to be identified according to the associated information of the object to be identified, including:

step 602, acquiring each associated object of the object to be identified under the condition that the associated information includes the user information of the associated object.

In the embodiment of the application, the association information includes user information of an association object having an association relationship with the object to be identified and domain information of a domain in which the object to be identified is located, for example, the association relationship may be that the object to be identified interacts on a social platform, or the association relationship may also be that the object to be identified interacts with resources, and the domain in which the object to be identified is located may be an industry domain in which the object to be identified works.

In the case that the association information includes user information of the associated object, each associated object of the object to be recognized may be obtained from an association list of the object to be recognized, where the association list includes associated objects having association relations with the object to be recognized, and the association list may be, for example, an address list of the object to be recognized, or, in some scenarios, an information registration table needs to be filled correspondingly to be recognized, where the registration table includes contacts and relations between the contacts and the object to be recognized, and the associated object of the object to be recognized may be obtained according to the information registration table filled by the object to be recognized.

And step 604, determining the associated emotion factors of the associated objects according to the user information of the associated objects.

In the embodiment of the present application, on the condition of the association relationship with the object to be identified, the association objects of the object to be identified may be classified, and for each association object in the same association relationship, the association emotion factor of each association object may be determined according to the user information of each association object, where the specific step of determining the association emotion factor of each association object refers to the content described in the above embodiment, and is not described herein again.

Step 606, determining a first target associated emotion factor of the object to be identified according to the associated emotion factors of the associated objects.

In the embodiment of the application, after determining the associated emotion factors of the associated objects in the same association relationship, the average value of the associated emotion factors of the associated objects can be calculated, the average value is the first target associated emotion factor of the object to be identified, and the first target associated emotion factors of the object to be identified are sequentially determined based on the same method.

Exemplary, associating the object with the object to be identified includes: the association object 1, the association object 2, the association object 3, and the association object 4 are taken as examples, wherein the association object 1 and the association object 2 interact with the object to be recognized on the social platform, and the association object 3 and the association object 4 interact with the object to be recognized through resources. Determining a related emotion factor 1 of the related object 1 and a related emotion factor 2 of the related object 2 according to the user information of the related object 1 and the related object 2, and calculating an average value of the related emotion factor 1 and the related emotion factor 2 (namely, a first target related emotion factor 1 of the object to be identified); and then, determining the associated emotion factors 3 and 4 of the associated objects 3 and 4 respectively according to the user information of the associated objects 3 and 4, and calculating the average value of the associated emotion factors 3 and 4 (namely the first target associated emotion factor 2 of the object to be identified).

Step 608, in the case that the associated information includes the domain information, determining a second target associated emotion factor of the object to be identified according to the domain information.

In the embodiment of the present application, when the associated information includes the domain information, the second target associated emotion factor of the object to be identified may be determined directly according to the domain information, and the method for determining the second target associated emotion factor refers to the contents described in the above embodiment, which are not described herein again.

The method comprises the steps of establishing a domain information database, wherein the domain information database comprises a plurality of keywords capable of representing the development condition of the domain and emotion scores of all keyword objects, extracting the keywords of the domain information according to an NLP (non line segment) technology, matching the keywords with the keywords in the domain information database, determining the emotion scores corresponding to all the keywords, and obtaining target associated emotion factors according to all the emotion scores.

Illustratively, the domain information database is shown in table two. Taking the area where the object to be identified is located as the industry a as an example, the area information is the industry information of the industry a, wherein the industry development policy and the industry development condition in the past period (for example, the past 6 months) can be obtained from a network platform related to the industry a, and keywords are extracted from the industry development policy and the industry development condition: and matching the keywords with the keywords in the second table, determining the emotion scores corresponding to the keywords to be 20 and 20 respectively, and accumulating the two emotion scores to obtain a second target associated emotion factor of 40.

Watch two

In the embodiment of the application, the target associated emotional factor of the object to be recognized can be determined according to the associated information of the object to be recognized, wherein the target associated emotional factor can influence the probability of the object to be recognized for generating the target event to a certain extent, so that the event occurrence probability is adjusted according to the target associated emotional factor, the accuracy of the target event occurrence probability is improved, the target object is recognized according to the target event occurrence probability, and the accuracy of the target object recognition is further improved.

In a specific embodiment, keywords in the text information can be extracted based on an NLP technology according to the text information of each historical object published on a social platform in the past year, matching is performed in an emotion keyword database, emotion scores corresponding to the keywords are determined, the emotion scores are accumulated to obtain target emotion factors of each historical object, and then, each historical object is classified according to the target emotion factors of each historical object to obtain a plurality of groups. The step of obtaining the groups by classification is as follows: the staff can set the value range 1 of the target emotion factor corresponding to the group 1 to-100 to-70, the value range 2 corresponding to the group 2 to-70 to 30, the value range 3 corresponding to the group 3 to-30 to 40, and the value range 4 corresponding to the group 4 to 40 to 100, and classify the history objects according to the value ranges to obtain that the group 1 includes 100 history objects, the group 2 includes 189 history objects, the group 3 includes 250 history objects, and the group 4 includes 400 history objects.

The staff can set a target event comprising an event a, an event B and time C, acquire historical resource interaction data of each historical object in the group 1 in the past 12 months aiming at the group 1, and respectively determine that a first numerical value 1 corresponding to the historical object in which the event a occurs is 80, a first numerical value 2 corresponding to the historical object in which the event B occurs is 82, a first numerical value 3 corresponding to the historical object in which the event C occurs is 90, and the number of the historical objects in the group 1 is 100, so that the event occurrence probability 1 corresponding to the event a in the group 1 can be determined to be 80%, the event occurrence probability 2 corresponding to the event B is 82%, and the event occurrence probability 3 corresponding to the event C is 90%.

When the event occurrence probability is greater than or equal to 80% of the first numerical value, taking event a as an example, a credit specialist predicts the occurrence probability of event a of each historical object in the group 1 to obtain the event occurrence tagging probability 1 of event a of each historical object in the group 1, determines the target associated emotional factor of each historical object according to the association information of each historical object in the group 1, then processes the target associated emotional factor, the event occurrence probability 1 and the event occurrence tagging probability 1 of each historical object according to a regression calculation method to obtain a factor coefficient corresponding to the target associated emotional factor, and constructs a probability correction formula 1 corresponding to event a in the group 1 according to the factor coefficient and the event occurrence probability 1. By repeating the above steps, the probability correction formula 2 corresponding to the event B and the probability correction formula 3 corresponding to the event C can be determined respectively.

Secondly, the above steps are repeated for other groups respectively, and a plurality of probability correction formulas corresponding to other groups can be obtained.

In the process of identifying the target object, according to user information of the object to be identified (namely, character information of the object to be identified, which is published on a social platform in the last 6 months), determining that a target emotion factor of the object to be identified is-80, and according to the target emotion factor, determining that a group to which the object to be identified belongs is a group 1, wherein a target event of the object to be identified is an event a, matching the event a from the group 1 to obtain an event occurrence probability of 1.

At this time, the first numerical value is 80%, and the event occurrence probability of the group 1 is equal to the first numerical value, so that the target associated emotion factor of the object to be recognized is determined according to the associated information of the object to be recognized, and the target associated emotion factor is input into the probability correction formula 1 corresponding to the event a in the group 1, and the target event occurrence probability of the object to be recognized is 75%. Taking the second numerical value as 70% as an example, comparing the target event occurrence probability of the object to be recognized with the second numerical value to obtain that the target event occurrence probability of the object to be recognized is greater than the second numerical value, and taking the object to be recognized as the target object. The staff can correspondingly limit the loan amount of the target object and improve the post-loan management level of the target object.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the application also provides a target object identification device for realizing the target object identification method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the target object recognition device provided below can be referred to the limitations in the above target object recognition method, and are not described herein again.

In one embodiment, as shown in fig. 7, there is provided a target object recognition apparatus 700, including: a first determination module 702, a second determination module 704, a third determination module 706, an adjustment module 708, and an identification module 710, wherein:

a first determining module 702, configured to determine a target emotion factor of an object to be identified according to user information of the object to be identified;

a second determining module 704, configured to determine, according to the target emotion factor of the object to be identified, a target group corresponding to the object to be identified from the group, where, for any group, the target emotion factor of each object in the group is within a value range corresponding to the group;

a third determining module 706, configured to determine a target associated emotion factor of the object to be identified according to the associated information of the object to be identified, where the event occurrence probability is used to represent a probability of occurrence of a target event, when the event occurrence probability corresponding to the target group is greater than or equal to the first numerical value;

an adjusting module 708, configured to adjust the event occurrence probability according to the target associated emotion factor to obtain a target event occurrence probability of the object to be identified;

and the identifying module 710 is configured to take the object to be identified as the target object when the target event occurrence probability of the object to be identified is greater than or equal to the second value.

According to the method and the device, the event occurrence probability is determined according to the user information of the object to be recognized and the group to which the object to be recognized belongs, the event occurrence probability is adjusted according to the associated information of the object to be recognized under the condition that the event occurrence probability meets a certain condition, and the target event occurrence probability is obtained.

In one embodiment, the adjustment module 708 is further configured to:

acquiring a probability correction formula corresponding to the target group;

and inputting the target associated emotion factors of the object to be recognized into a probability correction formula to obtain the target event occurrence probability of the object to be recognized.

In one embodiment, the apparatus further comprises:

a fourth determining module, configured to determine, for any group, a factor coefficient corresponding to a target associated emotion factor according to an event occurrence probability corresponding to the group, the target associated emotion factor of each historical object in the group, and an event occurrence tagging probability of each historical object in the group;

In one embodiment, the apparatus further comprises:

the fifth determining module is used for determining a first numerical value corresponding to a historical object with a target event in any group;

and the sixth determining module is used for determining the event occurrence probability corresponding to the group according to the first numerical value and the number of the historical objects in the group.

and the matching module is used for matching the target events from the target group, and taking the event occurrence probability of the target events as the event occurrence probability corresponding to the target group under the condition of matching the target events.

In one embodiment, the association information comprises at least one of user information of an association object having an association relation with the object to be identified and field information of the field of the object to be identified, and the target association emotional factor comprises at least one of a first target association emotional factor and a second target association emotional factor; the third determining module 706 is further configured to:

under the condition that the associated information comprises user information of the associated objects, acquiring each associated object of the object to be identified;

determining a first target associated emotion factor of an object to be identified according to the associated emotion factors of all associated objects;

or determining a second target associated emotion factor of the object to be recognized according to the domain information under the condition that the associated information comprises the domain information.

The modules in the target object recognition device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a target object recognition 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 a 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. 8 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, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

determining a target group corresponding to the object to be identified from the groups according to the target emotion factors of the object to be identified, wherein the target emotion factors of all the objects in the group are in the numerical value range corresponding to the group aiming at any group;

under the condition that the event occurrence probability corresponding to the target group is greater than or equal to a first numerical value, determining a target associated emotional factor of the object to be identified according to the associated information of the object to be identified, wherein the event occurrence probability is used for representing the probability of occurrence of the target event;

and taking the object to be recognized as the target object when the target event occurrence probability of the object to be recognized is greater than or equal to the second numerical value.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

determining a target group corresponding to the object to be identified from the groups according to the target emotion factors of the object to be identified, wherein the target emotion factors of all the objects in the group are in the numerical range corresponding to the group aiming at any group;

In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

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 hardware instructions of 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, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as 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 application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A target object identification method, the method comprising:

2. The method according to claim 1, wherein the adjusting the event occurrence probability according to the target associated emotion factor to obtain a target event occurrence probability of the object to be recognized comprises:

acquiring a probability correction formula corresponding to the target group;

3. The method of claim 2, further comprising:

4. The method of claim 1, further comprising:

5. The method of claim 1, wherein the event occurrence probability corresponding to the group comprises an event occurrence probability corresponding to at least one event, and wherein the method further comprises:

matching the target event from the target group;

6. The method according to claim 1, wherein the association information includes at least one of user information of an association object having an association relation with the object to be recognized and domain information of a domain where the object to be recognized is located, and the target association emotion factor includes at least one of a first target association emotion factor and a second target association emotion factor; the determining the target associated emotional factor of the object to be identified according to the associated information of the object to be identified includes:

under the condition that the associated information comprises user information of the associated objects, acquiring each associated object of the objects to be identified;

7. An apparatus for identifying a target object, the apparatus comprising:

the first determining module is used for determining a target emotion factor of an object to be recognized according to user information of the object to be recognized;

a third determining module, configured to determine a target associated emotion factor of the object to be identified according to the associated information of the object to be identified, where an event occurrence probability corresponding to the target group is greater than or equal to a first numerical value, where the event occurrence probability is used to represent a probability of occurrence of a target event;

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.