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

Abstract

The present application relates to a target object identification method, device, computer equipment and storage medium, and relates to the field of big data. The method comprises: determining the target emotional factor of the object to be identified based on the user information of the object to be identified, determining the target group corresponding to the object to be identified based on the target emotional factor of the object to be identified, the target emotional factor of each object in the group being within the numerical range corresponding to the group, and when the probability of an event occurrence corresponding to the target group is greater than or equal to a first numerical value, determining the target associated emotional factor of the object to be identified based on the associated information of the object to be identified, the event occurrence probability characterizing the probability of the target event occurring, and adjusting the event occurrence probability based on the target associated emotional factor to obtain the target event occurrence probability of the object to be identified, and when the target event occurrence probability of the object to be identified is greater than or equal to a second numerical value, the object to be identified is used as the target object. The use of this method can improve the accuracy of target object identification.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a target object recognition method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the development of network technology, target object recognition technology based on big data analysis has emerged. This technology analyzes the big data information of the object to be identified in the network and finally identifies the target object that meets the conditions. The target object may be the object where the target event occurs.

[0003] In traditional target object recognition technology, the probability of the target event occurring can be obtained by analyzing the target object through objective information such as the virtual resources and resource interaction data owned by the target object.

[0004] However, in the above target object identification process, the probability of the target event is analyzed only through objective information, and the amount of information is small, that is, the analysis basis is not comprehensive, resulting in a low prediction accuracy of the probability of the target event, and thus a low accuracy of target object identification. Summary of the Invention

[0005] Based on this, it is necessary to provide a target object recognition method, apparatus, computer equipment, computer-readable storage medium and computer program product that can accurately identify the target object in order to address the above technical problems.

[0006] In a first aspect, the present application provides a method for identifying a target object. The method comprises:

[0007] Determining a target emotion factor of the object to be identified based on user information of the object to be identified;

[0008] Determining a target group corresponding to the object to be identified from a group according to the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0009] When the event occurrence probability corresponding to the target group is greater than or equal to a first value, determining a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0010] Adjusting the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified;

[0011] When the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, the object to be identified is taken as a target object.

[0012] In one embodiment, 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 includes:

[0013] Obtaining a probability correction formula corresponding to the target group;

[0014] The target-associated emotion factor of the object to be identified is input into the probability correction formula to obtain the probability of occurrence of the target event of the object to be identified.

[0015] In one embodiment, the method further comprises:

[0016] For any of the groups, 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 labeling probability of each historical object in the group;

[0017] A probability correction formula corresponding to the group is constructed based on the factor coefficient and the probability of occurrence of the event corresponding to the group.

[0018] In one embodiment, the method further comprises:

[0019] For any of the groups, determining a first numerical value corresponding to a historical object in the group where the target event occurs;

[0020] The occurrence probability of the event corresponding to the group is determined according to the first value and the number of the historical objects in the group.

[0021] In one embodiment, the event occurrence probability corresponding to the group includes the event occurrence probability corresponding to at least one event, and the method further includes:

[0022] matching the target event from the target group;

[0023] When the target event is matched, the event occurrence probability of the target event is used as the event occurrence probability corresponding to the target group.

[0024] In one embodiment, the association information includes at least one of user information of an associated object having an association relationship with the object to be identified and domain information of the domain in which the object to be identified is located; the target-associated emotional factor includes at least one of a first target-associated emotional factor and a second target-associated emotional factor; and determining the target-associated emotional factor of the object to be identified based on the association information of the object to be identified includes:

[0025] In a case where the association information includes user information of the associated objects, obtaining each of the associated objects of the object to be identified;

[0026] Determining an associated emotion factor of each associated object according to the user information of each associated object;

[0027] Determining a first target associated emotional factor of the object to be identified according to the associated emotional factor of each associated object;

[0028] Alternatively, in a case where the association information includes the domain information, the second target association emotion factor of the object to be identified is determined based on the domain information.

[0029] In a second aspect, the present application further provides a target object recognition device. The device comprises:

[0030] A first determining module is used to determine a target emotion factor of the object to be identified based on user information of the object to be identified;

[0031] A second determining module is configured to determine a target group corresponding to the object to be identified from a group based on the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0032] A third determination module is configured to determine a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified when the event occurrence probability corresponding to the target group is greater than or equal to a first value, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0033] An adjustment module, configured to adjust the event occurrence probability according to the target-associated emotion factor to obtain the target event occurrence probability of the object to be identified;

[0034] The identification module is configured to, when the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, take the object to be identified as a target object.

[0035] In one embodiment, the adjustment module is further configured to:

[0036] Obtaining a probability correction formula corresponding to the target group;

[0037] The target-associated emotion factor of the object to be identified is input into the probability correction formula to obtain the probability of occurrence of the target event of the object to be identified.

[0038] In one embodiment, the apparatus further comprises:

[0039] a fourth determining module, configured to determine, for any of the groups, a factor coefficient corresponding to the target-associated sentiment factor based on the event occurrence probability corresponding to the group, the target-associated sentiment factor of each historical object in the group, and the event occurrence labeling probability of each historical object in the group;

[0040] A construction module is used to construct a probability correction formula corresponding to the group according to the factor coefficient and the probability of occurrence of the event corresponding to the group.

[0041] In one embodiment, the apparatus further comprises:

[0042] A fifth determining module, configured to determine, for any of the groups, a first numerical value corresponding to a historical object in the group where the target event occurs;

[0043] The sixth determining module is configured to determine a probability of occurrence of an event corresponding to the group according to the first value and the number of the historical objects in the group.

[0044] In one embodiment, the event occurrence probability corresponding to the group includes the event occurrence probability corresponding to at least one event, and the apparatus further includes:

[0045] The matching module is configured to match the target event from the target group, and when the target event is matched, use the event occurrence probability of the target event as the event occurrence probability corresponding to the target group.

[0046] In one embodiment, the association information includes at least one of user information of an associated object having an association relationship with the object to be identified and domain information of the domain in which the object to be identified is located; the target-associated emotional factor includes at least one of a first target-associated emotional factor and a second target-associated emotional factor; and the third determination module is further configured to:

[0047] In a case where the association information includes user information of the associated objects, obtaining each of the associated objects of the object to be identified;

[0048] Determining an associated emotion factor of each associated object according to the user information of each associated object;

[0049] Determining a first target associated emotional factor of the object to be identified according to the associated emotional factor of each associated object;

[0050] Alternatively, in a case where the association information includes the domain information, the second target association emotion factor of the object to be identified is determined based on the domain information.

[0051] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0052] Determining a target emotion factor of the object to be identified based on user information of the object to be identified;

[0053] Determining a target group corresponding to the object to be identified from a group according to the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0054] When the event occurrence probability corresponding to the target group is greater than or equal to a first value, determining a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0055] Adjusting the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified;

[0056] When the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, the object to be identified is taken as a target object.

[0057] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0058] Determining a target emotion factor of the object to be identified based on user information of the object to be identified;

[0059] Determining a target group corresponding to the object to be identified from a group according to the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0060] When the event occurrence probability corresponding to the target group is greater than or equal to a first value, determining a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0061] Adjusting the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified;

[0062] When the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, the object to be identified is taken as a target object.

[0063] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0064] Determining a target emotion factor of the object to be identified based on user information of the object to be identified;

[0065] Determining a target group corresponding to the object to be identified from a group according to the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0066] When the event occurrence probability corresponding to the target group is greater than or equal to a first value, determining a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0067] Adjusting the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified;

[0068] When the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, the object to be identified is taken as a target object.

[0069] The above-mentioned target object identification method, device, computer equipment, storage medium and computer program product determine the target emotional factor of the object to be identified based on the user information of the object to be identified, and determine the target group corresponding to the object to be identified from the group based on the target emotional factor of the object to be identified. For any group, the target emotional factor of each object in the group is within the numerical range corresponding to the group. When the probability of occurrence of the event corresponding to the target group is greater than or equal to the first numerical value, the target associated emotional factor of the object to be identified is determined based on the associated information of the object to be identified, wherein the event occurrence probability is used to characterize the probability of occurrence of the target event, and the event occurrence probability is adjusted according to the target associated emotional factor to obtain the target event occurrence probability of the object to be identified. When the probability of occurrence of the target event of the object to be identified is greater than or equal to the second numerical value, the object to be identified is taken as the target object. Based on the above-mentioned target object identification method, device, computer equipment, storage medium and computer program product, the probability of an event occurrence is first determined based on the user information of the object to be identified and the group to which the object to be identified belongs. When the probability of an event occurrence meets certain conditions, the probability of an event occurrence is adjusted based on the associated information of the object to be identified to obtain the probability of a target event occurrence. The above process combines the user information and associated information of the object to be identified for comprehensive analysis, resulting in richer information and more comprehensive analysis basis, thereby improving the prediction accuracy of the probability of a target event occurrence and thus improving the accuracy of target object identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 Schematic diagram of a target object identification method according to an embodiment;

[0071] Figure 2 is a flow chart of a target object identification method according to another embodiment;

[0072] Figure 3 is a flow chart of a target object identification method according to another embodiment;

[0073] Figure 4 is a flow chart of a target object identification method according to another embodiment;

[0074] Figure 5 is a flow chart of a target object identification method according to another embodiment;

[0075] Figure 6 is a flow chart of a target object identification method according to another embodiment;

[0076] Figure 7 is a structural block diagram of a target object identification device in one embodiment;

[0077] Figure 8 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0079] In one embodiment, Figure 1 As shown, a target object identification method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0080] Step 102: Determine the target emotion factor of the object to be identified based on the user information of the object to be identified.

[0081] The object to be identified is the object to be identified as the target object, and the user information is the information generated when the object to be identified uses various network platforms. For example, the user information can be the text information posted by the object to be identified on the social platform. The user information of the object to be identified can be subjected to keyword extraction through the text extraction model, and the target emotional factor of the object to be identified can be determined based on each keyword. The target emotional factor can be used to characterize the subjective emotion of the object to be identified. The target emotional factor can be positive, negative, or 0. When the target emotional factor is positive, it indicates that the object to be identified is in a positive, optimistic, and positive emotional tendency; when the target emotional factor is negative, it indicates that the object to be identified is in a negative, pessimistic, and negative emotional tendency; when the target emotional factor is 0, it indicates that the object to be identified is in a neutral, objective, and rational emotional tendency. The absolute value of the target emotional factor is used to indicate the emotional intensity of the object to be identified.

[0082] Exemplarily, the target emotional factor can be determined in the following manner: first, an emotional keyword database is constructed, which includes multiple emotional keywords and emotional scores corresponding to the emotional keywords. Then, based on natural language processing (NLP) technology, keywords in the user information of the object to be identified are extracted, and the extracted keywords are matched with the emotional keywords in the emotional keyword database to obtain the emotional scores corresponding to each keyword. The emotional scores are then accumulated to obtain the target emotional factor of the object to be identified.

[0083] For example, taking the object to be identified as customer A and the user information as the text information posted by customer A on the social platform as an example, the constructed emotional keyword database is shown in Table 1. The NLP technology is used to extract keywords from the text information posted by customer A on the social platform: keyword 1, keyword 2, keyword 3, keyword 4. By matching the above keywords in Table 1, the target emotional factor of customer A can be obtained as -70-70+30+30=-80.

[0084] Table (1)

[0085]

[0086] It should be noted that the above example of the present application is only an example of determining the target emotional factor of the object to be identified, and the present application does not specifically limit the method of determining the target emotional factor of the object to be identified.

[0087] Step 104 , based on the target emotion factor of the object to be identified, determine the target group corresponding to the object to be identified from the group. For any group, the target emotion factor of each object in the group is within the numerical range corresponding to the group.

[0088] In an embodiment of the present application, different groups will correspond to different numerical ranges of target emotional factors, and the target emotional factors of each object in the group are all within the numerical range corresponding to the group. Therefore, the target emotional factors of the objects to be identified can be matched with the numerical ranges corresponding to each group. When the numerical range to which the target emotional factors of the objects to be identified belong is matched, it can be determined that the target group corresponding to the objects to be identified is the group corresponding to the numerical range.

[0089] For example, still taking the above example, the target emotional factor of customer A is -80. The known numerical range 1 corresponding to group 1 is -100 to -70, the numerical range 2 corresponding to group 2 is -70 to 30, the numerical range 3 corresponding to group 3 is -30 to 40, and the numerical range 4 corresponding to group 4 is 40 to 100. Based on the target emotional factor -80 being within the numerical range 1, it can be determined that the target group corresponding to customer A is group 1.

[0090] Step 106, when the event occurrence probability corresponding to the target group is greater than or equal to the first value, determine the target associated emotional factor of the object to be identified based on the associated information of the object to be identified, where the event occurrence probability is used to represent the probability of the target event occurring.

[0091] In an embodiment of the present application, the probability of an event occurrence can be used to characterize the probability of a target event occurring. The target event can be set by the staff according to actual needs. Different target events can be set according to the length of the time period in which a certain event occurs, or different target events can be set according to different events that occur. For example: the target event is event A occurring within the past 3 months, or the target event is event A occurring within the past 6 months, or the target event is event B occurring within the past 3 months.

[0092] After determining the target group corresponding to the object to be identified, the probability of event occurrence corresponding to the target group can, to a certain extent, characterize the probability of the target event occurring in the future for the object to be identified, but the accuracy is not high. If the target object is identified directly based on the probability of event occurrence corresponding to the target group, the accuracy of target object identification will be reduced. Therefore, the probability of event occurrence corresponding to the target group is compared with a first value (which can be set by the staff), and further processing is performed on the object to be identified whose probability of event occurrence corresponding to the target group is greater than or equal to the first value.

[0093] Specifically, when the probability of an event occurring corresponding to the target group corresponding to the object to be identified is greater than or equal to a first numerical value, the associated information of the object to be identified can be obtained, wherein the associated information is information related to the object to be identified. Exemplarily, the associated information can be user information of an associated object that has an associated relationship with the object to be identified, for example: the associated information is user information of an object that interacts with the object to be identified on a social platform, or, the associated information can also be field information of the field in which the object to be identified is located, for example: the associated information is field information of the professional field in which the object to be identified is located.

[0094] Secondly, based on NLP technology, keywords are extracted from the associated information of the object to be identified, and the target associated emotional factors of the object to be identified are determined according to each keyword. The specific steps for determining the target associated emotional factors can refer to the description of determining the target emotional factors in the above embodiment, and will not be repeated here.

[0095] Step 108: Adjust the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified.

[0096] In an embodiment of the present application, for an object to be identified, multiple target-associated emotional factors can be determined, wherein each target-associated emotional factor will have a certain impact on the probability of a target event occurring in the future for the object to be identified (i.e., the probability of the event occurring). Therefore, the probability of the event occurring can be adjusted according to the target-associated emotional factor to obtain the probability of the target event occurring for the object to be identified.

[0097] Step 110 : When the probability of occurrence of the target event of the object to be identified is greater than or equal to the second value, the object to be identified is taken as the target object.

[0098] In an embodiment of the present application, the probability of occurrence of the target event of the object to be identified is compared with a second value (which can be set by the staff). If the probability of occurrence of the target event of the object to be identified is greater than or equal to the second value, the object to be identified is taken as the target object.

[0099] For example, taking the object to be identified as customer A, the target event as event A, the second value as 70%, and the probability of occurrence of customer A's target event as 83%, if the probability of occurrence of customer A's target event 83% is greater than the second value, then customer A is the target object, that is, customer A is a customer who needs the staff's special attention.

[0100] In the above-mentioned target object identification method, the probability of an event occurrence is first determined based on the user information of the object to be identified and the group to which the object to be identified belongs. When the probability of an event occurrence meets certain conditions, the probability of an event occurrence is adjusted based on the associated information of the object to be identified to obtain the probability of a target event occurrence. The above-mentioned process conducts a comprehensive analysis based on the user information and associated information of the object to be identified. The amount of information is large, and the analysis basis is more comprehensive, which improves the prediction accuracy of the probability of a target event occurrence, thereby improving the accuracy of target object identification.

[0101] Secondly, only when the probability of occurrence of an event corresponding to the group to which the object to be identified belongs is greater than or equal to the first value, the object to be identified is further processed, thereby saving the cost of data acquisition and processing.

[0102] In one embodiment, Figure 2 As shown, step 108, adjusting the event occurrence probability according to the target-related emotional factor to obtain the target event occurrence probability of the object to be identified, includes:

[0103] Step 202: Obtain the probability correction formula corresponding to the target group.

[0104] In an embodiment of the present application, for each object in the same group, the target-associated emotional factor of each object has the same influence trend on the probability of occurrence of the event corresponding to the group, so the probability correction formula corresponding to the group can be determined according to the above rules, wherein the probability correction formula represents the functional relationship between the probability of event occurrence, the target-associated emotional factor of the object to be identified, and the probability of occurrence of the target event corresponding to the object to be identified.

[0105] The probability correction formula corresponding to the target group can be obtained according to the target group corresponding to the object to be identified.

[0106] Step 204: input the target-related emotion factor of the object to be identified into the probability correction formula to obtain the probability of occurrence of the target event of the object to be identified.

[0107] In an embodiment of the present application, the target-related emotional factors of the object to be identified can be input into the probability correction formula, and the probability of occurrence of the target event of the object to be identified can be obtained by calculation. For example, still taking the above example, the target-related emotional factor 1 of customer A is 80, the target-related emotional factor 2 is -50, and the target-related emotional factor 3 is 20, and the probability correction formula is 85% + 0.15 * target-related emotional factor 1 + 0.25 * target-related emotional factor 2 + 0.02 * target-related emotional factor 3 = probability of occurrence of the target event. For example, the three target-related emotional factors are input into the probability correction formula respectively, and the probability of occurrence of the target event is obtained = 85% + 0.15 * 80 + 0.25 * (-50) + 0.02 * 20 = 75%.

[0108] In this embodiment, the probability correction formula corresponding to the object to be identified is determined based on the target group to which the object to be identified belongs. Then, the target-associated emotional factor of the object to be identified is input into the probability correction formula to adjust the probability of event occurrence, thereby determining the probability of target event occurrence. The target-associated emotional factor is obtained based on the associated information of the object to be identified, that is, in the above method, the probability of event occurrence is adjusted based on the associated information of the object to be identified to obtain the probability of target event occurrence. A comprehensive analysis is performed in combination with the user information and associated information of the object to be identified to obtain a more accurate probability of target event occurrence, thereby improving the accuracy of target object identification.

[0109] In one embodiment, Figure 3 As shown, the method further includes:

[0110] Step 302 : For any group, determine the factor coefficient corresponding to the target-associated emotional factor according to the event occurrence probability corresponding to the group, the target-associated emotional factor of each historical object in the group, and the event occurrence labeling probability of each historical object in the group.

[0111] In an embodiment of the present application, before identifying the object to be identified, the probability correction formula corresponding to each group can be determined separately. Specifically, for any group, the probability of event occurrence corresponding to the group is known, and the target-related emotional factor of each historical object can be determined based on the historical association information of each historical object in the group over a period of time (e.g., the past six months). The staff (e.g., a credit officer) predicts the probability of the target event occurring in the future for the historical object based on the objective information of the historical object (e.g., historical resource interaction information), user information, and association information, and obtains the event occurrence labeling probability of each historical object. Afterwards, the factor coefficient corresponding to the target-related emotional factor is determined based on the event occurrence probability corresponding to the group, the target-related emotional factor of each historical object in the group, and the event occurrence labeling probability of each historical object in the group.

[0112] In this embodiment, the factor coefficient corresponding to the target-associated emotional factor can be determined according to the regression calculation method, that is, the event occurrence probability corresponding to the group and the target-associated emotional factor of each historical object in the group are used as independent variables, and the event occurrence marking probability of each historical object is used as the dependent variable. Through regression calculation, the factor coefficient corresponding to each target-associated emotional factor is obtained, wherein the factor coefficient corresponds to the target-associated emotional factor one-to-one.

[0113] Step 304: construct a probability correction formula corresponding to the group based on the factor coefficients and the probability of occurrence of the event corresponding to the group.

[0114] In the embodiment of the present application, after obtaining each factor coefficient, a probability correction formula corresponding to the group is constructed based on the factor coefficient and the probability of event occurrence corresponding to the group. For example, the probability correction formula is: probability of event occurrence corresponding to the group + factor coefficient 1 * target-related emotion factor 1 + factor coefficient 2 * target-related emotion factor 2 + factor coefficient * target-related emotion factor 3 = probability of target event occurrence.

[0115] In this embodiment, the probability correction formula is determined based on the probability of event occurrence, the target-related emotional factors of each historical object in the group, and the probability of event occurrence annotation of each historical object in the group. After that, the probability of event occurrence can be further adjusted according to the associated information of the object to be identified to obtain the probability of target event occurrence. Combined with the user information and associated information of the object to be identified, a comprehensive analysis can be performed to obtain a more accurate probability of target event occurrence, thereby improving the accuracy of target object identification.

[0116] In one embodiment, Figure 4 As shown, the method further includes:

[0117] Step 402 : For any group, determine a first value corresponding to a historical object in which a target event occurs in the group.

[0118] In an embodiment of the present application, before identifying the object to be identified, it is necessary to first determine the probability of event occurrence corresponding to each group. The specific steps for determining the probability of event occurrence are as follows: for any group, obtain the historical resource interaction data of each historical object in the group over the past period of time, and based on the historical resource interaction data of each historical object, determine how many historical objects have experienced the target event (i.e., the first numerical value).

[0119] For example, taking the historical object as a historical customer and the historical resource interaction data as the resource interaction data of each historical customer in the past year, group 1 includes 100 historical customers, and the preset event is event A. Based on the resource interaction data of the 100 historical customers in the past year, it is determined that 80 of the historical customers have experienced event A, then the first value is 80.

[0120] Step 404 : Determine the occurrence probability of the event corresponding to the group based on the first value and the number of historical objects in the group.

[0121] In this embodiment, the first value is divided by the number of historical objects in the group. This ratio is the probability of the event occurring for the group. For example, using the above example, if the first value is 80 and Group 1 includes 100 historical customers, the probability of the event occurring for Group 1 is 80%.

[0122] In this embodiment, each group is classified according to the target emotional factor of the object, and then the probability of the event corresponding to the group is determined by mathematical statistics based on the historical resource interaction data of each historical object included in the group. That is, the event occurrence probability obtained at this time is obtained through the target emotional factor of the object. The event occurrence probability can characterize the probability of the target event occurring for each object in the same group to a certain extent. The event occurrence probability is then adjusted according to the associated information of the object to be identified to obtain a more accurate probability of the target event occurrence, thereby improving the accuracy of target object identification.

[0123] In one embodiment, Figure 5 As shown, the event occurrence probability corresponding to the group includes the event occurrence probability corresponding to at least one event, and the method further includes:

[0124] Step 502, matching target events from the target group;

[0125] Step 504: When a target event is matched, the event occurrence probability of the target event is used as the event occurrence probability corresponding to the target group.

[0126] In this embodiment of the present application, for a group, the probability of occurrence of different target events corresponding to the group is not the same. That is, the group corresponds to multiple event probabilities, including the probability of occurrence of each target event corresponding to the group. For example, taking Group 1 as an example, the corresponding event probabilities include: the probability of occurrence of event A corresponding to event A is 50%, the probability of occurrence of event B corresponding to event B is 80%, and the probability of occurrence of event C corresponding to event C is 95%.

[0127] In the process of identifying the object to be identified, the target events of the target group to which the object to be identified belongs are browsed in turn. When the browsed target event is the same as the target event of the object to be identified (that is, the target event is matched), the probability of occurrence of the event corresponding to the target object at this time is used as the probability of occurrence of the event corresponding to the target group.

[0128] For example, still taking the above example, the event occurrence probability corresponding to group 1 includes: the event occurrence probability corresponding to event A is 50%, the event occurrence probability corresponding to event B is 80%, and the event occurrence probability corresponding to event C is 95%. The target event of the object to be identified is event B. The target event is matched from the above events, and the event occurrence probability corresponding to event B of 80% is used as the event occurrence probability corresponding to the group.

[0129] In this embodiment, different target events may correspond to different probability correction formulas. Therefore, 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.

[0130] In an embodiment of the present application, the event occurrence probability corresponding to the group may include the event occurrence probability of different target events corresponding to the group, wherein the target event can be set by the staff according to actual needs. During the target object identification process, the target event is matched from the target group, and the event occurrence probability corresponding to the matched target event is used as the event occurrence probability corresponding to the target group. Subsequent identification processing can be performed based on this, which can meet the target object identification requirements for different target events and improve the identification range of the target object.

[0131] In one embodiment, Figure 6 As shown, the association information includes at least one of user information of an associated object that has an association relationship with the object to be identified and domain information of the domain in which the object to be identified is located, and the target-associated emotional factor includes at least one of a first target-associated emotional factor and a second target-associated emotional factor. Step 106, determining the target-associated emotional factor of the object to be identified based on the association information of the object to be identified, includes:

[0132] Step 602: When the association information includes user information of the associated object, obtain each associated object of the object to be identified.

[0133] In an embodiment of the present application, the associated information includes user information of an associated object that has an associated relationship with the object to be identified, and field information of the field in which the object to be identified is located. For example, the associated relationship may be an interaction with the object to be identified on a social platform, or the associated relationship may be a resource interaction with the object to be identified. The field in which the object to be identified is located may be the industry field in which the object to be identified works.

[0134] In which, when the association information includes user information of the associated object, each associated object of the object to be identified can be obtained from the association list of the object to be identified, and the association list includes associated objects that have an association relationship with the object to be identified. Exemplarily, the association list can be an address book list of the object to be identified, or, in some scenarios, it is necessary to fill out an information registration form corresponding to the object to be identified, and the registration form includes contacts and the relationship between contacts and the object to be identified. The associated objects of the object to be identified can be obtained based on the information registration form filled out by the object to be identified.

[0135] Step 604: Determine the associated emotion factor of each associated object based on the user information of each associated object.

[0136] In an embodiment of the present application, the associated objects of the object to be identified can be classified based on the association relationship with the object to be identified. For each associated object in the same association relationship, the associated emotional factor of each associated object can be determined based on the user information of each associated object. The specific steps for determining the associated emotional factor of each associated object refer to the contents described in the above embodiment and will not be repeated here.

[0137] Step 606: Determine a first target associated emotional factor of the object to be identified based on the associated emotional factors of each associated object.

[0138] In an embodiment of the present application, for each associated object in the same association relationship, after determining the associated emotional factor of each associated object, the average value of the associated emotional factor of each associated object can be calculated. The average value is the first target associated emotional factor of the object to be identified. Based on the same method, the first target associated emotional factors of the objects to be identified are determined in turn.

[0139] Exemplarily, the associated objects of the object to be identified include: associated object 1, associated object 2, associated object 3 and associated object 4. Among them, associated object 1 and associated object 2 have interacted with the object to be identified on the social platform, and associated object 3 and associated object 4 have interacted with resources with the object to be identified. The associated emotional factor 1 of associated object 1 and the associated emotional factor 2 of associated object 2 can be determined based on the user information of associated object 1 and associated object 2, and the average value of the associated emotional factor 1 and the associated emotional factor 2 (that is, the first target associated emotional factor 1 of the object to be identified) can be calculated; then, the associated emotional factor 3 of associated object 3 and the associated emotional factor 4 of associated object 4 can be determined based on the user information of associated object 3 and associated object 4, and the average value of the associated emotional factor 3 and the associated emotional factor 4 (that is, the first target associated emotional factor 2 of the object to be identified) can be calculated.

[0140] Step 608: When the association information includes domain information, determine a second target association emotion factor of the object to be identified based on the domain information.

[0141] In an embodiment of the present application, when the association information includes domain information, the second target-associated emotional factor of the object to be identified can be determined directly based on the domain information. The method for determining the second target-associated emotional factor refers to the content described in the above embodiment and will not be repeated here.

[0142] Among them, a domain information database can be constructed, which includes multiple keywords that can represent the development status of the domain, as well as the emotional scores of each keyword object. Afterwards, the domain information can be extracted based on NLP technology, and the keywords can be matched with the keywords in the domain information database to determine the emotional scores corresponding to each keyword, and the target-related emotional factors can be obtained according to each emotional score.

[0143] For example, the domain information database is shown in Table 2. Taking the field of the object to be identified as Industry A as an example, the domain information is the industry information of Industry A, wherein the industry development policies and industry development status in the past period of time (for example, the past 6 months) can be obtained from the network platform related to Industry A, and keywords are extracted from the industry development policies and industry development status: keyword A, keyword B, and the above keywords are matched with the keywords in Table 2, and the emotion scores corresponding to each keyword are determined to be 20 and 20 respectively. The two emotion scores are accumulated to obtain the second target-related emotional factor of 40.

[0144] Table 2

[0145]

[0146] In an embodiment of the present application, the target-associated emotional factor of the object to be identified can be determined based on the associated information of the object to be identified, wherein the target-associated emotional factor will affect the probability of the target event occurring in the object to be identified to a certain extent. Therefore, the probability of the event occurring is adjusted according to the target-associated emotional factor, thereby improving the accuracy of the probability of the target event occurring. The target object is identified based on the probability of the target event occurring, thereby improving the accuracy of the target object identification.

[0147] In a specific embodiment, based on the text information published by each historical object on a social platform in the past year, keywords in the text information can be extracted based on NLP technology, and matched in a sentiment keyword database to determine the sentiment score corresponding to each keyword. Each sentiment score is accumulated to obtain the target sentiment factor of each historical object, and then each historical object is classified according to the target sentiment factor of each historical object to obtain multiple groups. The steps for classifying the groups are as follows: the staff can set the numerical range 1 of the target sentiment factor corresponding to group 1 to -100 to -70, the numerical range 2 corresponding to group 2 to -70 to 30, the numerical range 3 corresponding to group 3 to -30 to 40, and the numerical range 4 corresponding to group 4 to 40 to 100. According to the above numerical ranges, the historical objects are classified to obtain 100 historical objects in group 1, 189 historical objects in group 2, 250 historical objects in group 3, and 400 historical objects in group 4.

[0148] The staff can set the target events including event A, event B and time C. For group 1, the historical resource interaction data of each historical object in group 1 in the past 12 months is obtained, and based on the historical resource interaction data, the first value 1 corresponding to the historical object where event A occurred is 80, the first value 2 corresponding to the historical object where event B occurred is 82, and the first value 3 corresponding to the historical object where event C occurred is 90. The number of historical objects in group 1 is 100. It can be determined that the event occurrence probability 1 corresponding to event A in group 1 is 80%, the event occurrence probability 2 corresponding to event B is 82%, and the event occurrence probability 3 corresponding to event C is 90%.

[0149] When the probability of an event occurring is greater than or equal to the first value of 80%, taking event A as an example, a credit specialist predicts the probability of event A occurring for each historical object in group 1, obtaining the event occurrence labeling probability 1 for each historical object in group 1. Based on the associated information of each historical object in group 1, the target-related sentiment factor of each historical object is determined. Subsequently, the target-related sentiment factor, event occurrence probability 1, and event occurrence labeling probability 1 of the historical object are processed using a regression calculation method to obtain the factor coefficient corresponding to the target-related sentiment factor. Based on the factor coefficient and event occurrence probability 1, a probability correction formula 1 corresponding to event A in group 1 is constructed. Repeating the above steps can determine the probability correction formula 2 for event B and the probability correction formula 3 for event C, respectively.

[0150] Secondly, the above steps are repeated for other groups respectively to obtain multiple probability correction formulas corresponding to other groups.

[0151] In the process of target object identification, based on the user information of the object to be identified (i.e., the text information posted by the object to be identified on the social platform in the past 6 months), the target sentiment factor of the object to be identified is determined to be -80. Based on the target sentiment factor, the group to which the object to be identified belongs is determined to be group 1, where the target event of the object to be identified is event A. Event A is matched from group 1, and the event occurrence probability is 1:80%, and 80% is used as the event occurrence probability of group 1.

[0152] In this case, the first value is 80%, and the probability of the event occurring in Group 1 is equal to the first value. Therefore, based on the associated information of the subject to be identified, the target-related sentiment factor of the subject to be identified is determined. This target-related sentiment factor is then input into the probability correction formula 1 corresponding to Event A in Group 1, resulting in a target event probability of 75% for the subject to be identified. Taking the second value of 70% as an example, the target event probability of the subject to be identified is compared with the second value. If the target event probability of the subject to be identified is greater than the second value, the subject to be identified is designated as a target subject. Staff will then limit the loan amount for the target subject accordingly, improving post-loan management of the target subject.

[0153] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0154] Based on the same inventive concept, embodiments of the present application also provide a target object recognition device for implementing the target object recognition method described above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more target object recognition device embodiments provided below can be referred to the above limitations of the target object recognition method and will not be repeated here.

[0155] In one embodiment, Figure 7 As shown, a target object recognition device 700 is provided, comprising: a first determination module 702, a second determination module 704, a third determination module 706, an adjustment module 708 and a recognition module 710, wherein:

[0156] A first determining module 702 is configured to determine a target emotion factor of the object to be identified based on user information of the object to be identified;

[0157] The second determining module 704 is configured to determine a target group corresponding to the object to be identified from the group based on the target emotion factor of the object to be identified, wherein for any group, the target emotion factor of each object in the group is within a numerical range corresponding to the group;

[0158] A third determining module 706 is configured to determine a target-related emotion factor of the object to be identified based on the associated information of the object to be identified when the event occurrence probability corresponding to the target group is greater than or equal to the first value, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0159] An adjustment module 708 is configured to adjust the event occurrence probability according to the target-related emotional factor to obtain the target event occurrence probability of the object to be identified;

[0160] The identification module 710 is configured to, when the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, take the object to be identified as a target object.

[0161] In an embodiment of the present application, the probability of an event occurrence is first determined based on the user information of the object to be identified and the group to which the object to be identified belongs. When the probability of an event occurrence meets certain conditions, the probability of an event occurrence is adjusted based on the associated information of the object to be identified to obtain the probability of a target event occurrence. The above process conducts a comprehensive analysis based on the user information and associated information of the object to be identified, resulting in richer information and more comprehensive analysis basis, which improves the prediction accuracy of the probability of a target event occurrence and thereby improves the accuracy of target object identification.

[0162] In one embodiment, the adjustment module 708 is further configured to:

[0163] Obtain the probability correction formula corresponding to the target group;

[0164] The target-associated emotion factor of the object to be identified is input into the probability correction formula to obtain the probability of the target event of the object to be identified.

[0165] In one embodiment, the apparatus further comprises:

[0166] A fourth determination module is configured to determine, for any group, a factor coefficient corresponding to the target-related sentiment factor based on the event occurrence probability corresponding to the group, the target-related sentiment factor of each historical object in the group, and the event occurrence labeling probability of each historical object in the group;

[0167] The construction module is used to construct a probability correction formula corresponding to the group based on the factor coefficient and the probability of event occurrence corresponding to the group.

[0168] In one embodiment, the apparatus further comprises:

[0169] A fifth determining module is configured to determine, for any group, a first numerical value corresponding to a historical object in which a target event occurs in the group;

[0170] The sixth determining module is configured to determine a probability of occurrence of an event corresponding to the group according to the first value and the number of historical objects in the group.

[0171] In one embodiment, the event occurrence probability corresponding to the group includes the event occurrence probability corresponding to at least one event, and the apparatus further includes:

[0172] The matching module is used to match the target event from the target group. When the target event is matched, the event occurrence probability of the target event is used as the event occurrence probability corresponding to the target group.

[0173] In one embodiment, the association information includes at least one of user information of an associated object having an association relationship with the object to be identified and domain information of the domain of the object to be identified; the target-associated emotional factor includes at least one of a first target-associated emotional factor and a second target-associated emotional factor; and the third determination module 706 is further configured to:

[0174] In the case where the association information includes user information of the associated object, obtaining each associated object of the object to be identified;

[0175] Determine the associated sentiment factor of each associated object based on the user information of each associated object;

[0176] Determining a first target associated emotional factor of the object to be identified based on the associated emotional factors of each associated object;

[0177] Alternatively, when the association information includes domain information, the second target association emotion factor of the object to be identified is determined based on the domain information.

[0178] Each module in the above-mentioned target object recognition device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0179] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a target object recognition method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0180] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0181] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0182] Determine the target emotional factor of the object to be identified based on the user information of the object to be identified;

[0183] According to the target emotion factor of the object to be identified, a target group corresponding to the object to be identified is determined from the group, and for any group, the target emotion factor of each object in the group is within the numerical range corresponding to the group;

[0184] When the event occurrence probability corresponding to the target group is greater than or equal to the first value, determining the target-related emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0185] Adjust the probability of event occurrence according to the target-related emotional factors to obtain the probability of target event occurrence of the object to be identified;

[0186] When the probability of occurrence of the target event of the object to be identified is greater than or equal to the second value, the object to be identified is taken as the target object.

[0187] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0188] Determine the target emotional factor of the object to be identified based on the user information of the object to be identified;

[0189] According to the target emotion factor of the object to be identified, a target group corresponding to the object to be identified is determined from the group, and for any group, the target emotion factor of each object in the group is within the numerical range corresponding to the group;

[0190] When the event occurrence probability corresponding to the target group is greater than or equal to the first value, determining the target-related emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0191] Adjust the probability of event occurrence according to the target-related emotional factors to obtain the probability of target event occurrence of the object to be identified;

[0192] When the probability of occurrence of the target event of the object to be identified is greater than or equal to the second value, the object to be identified is taken as the target object.

[0193] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0194] Determine the target emotional factor of the object to be identified based on the user information of the object to be identified;

[0195] According to the target emotion factor of the object to be identified, a target group corresponding to the object to be identified is determined from the group, and for any group, the target emotion factor of each object in the group is within the numerical range corresponding to the group;

[0196] When the event occurrence probability corresponding to the target group is greater than or equal to the first value, determining the target-related emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring;

[0197] Adjust the probability of event occurrence according to the target-related emotional factors to obtain the probability of target event occurrence of the object to be identified;

[0198] When the probability of occurrence of the target event of the object to be identified is greater than or equal to the second value, the object to be identified is taken as the target object.

[0199] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0200] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0201] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A target object recognition method, characterized in that: The method comprises: Determining a target emotion factor of the object to be identified based on user information of the object to be identified; Determining a target group corresponding to the object to be identified from a group according to the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group; When the event occurrence probability corresponding to the target group is greater than or equal to a first value, determining a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified, wherein the event occurrence probability is used to represent the probability of the target event occurring; Adjusting the event occurrence probability according to the target-associated emotional factor to obtain the target event occurrence probability of the object to be identified, including: obtaining a probability correction formula corresponding to the target group; inputting the target-associated emotional factor of the object to be identified into the probability correction formula to obtain the target event occurrence probability of the object to be identified; When the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, taking the object to be identified as a target object; Before identifying the object to be identified: For any of the groups, determine a factor coefficient corresponding to the target-associated emotion factor based on the event occurrence probability corresponding to the group, the target-associated emotion factor of each historical object in the group, and the event occurrence annotation probability of each historical object in the group; and construct a probability correction formula corresponding to the group based on the factor coefficient and the event occurrence probability corresponding to the group; For any of the groups, a first value corresponding to the historical objects in the group where the target event occurred is determined; and a probability of occurrence of the event corresponding to the group is determined based on the first value and the number of the historical objects in the group.

2. The method according to claim 1, characterized in that The event occurrence probability corresponding to the group includes the event occurrence probability corresponding to at least one event, and the method further includes: matching the target event from the target group; When the target event is matched, the event occurrence probability of the target event is used as the event occurrence probability corresponding to the target group.

3. The method according to claim 1, characterized in that The association information includes at least one of user information of an associated object that has an association relationship with the object to be identified and domain information of the domain in which the object to be identified is located, and the target-associated emotional factor includes at least one of a first target-associated emotional factor and a second target-associated emotional factor; The step of determining the target-related emotional factor of the object to be identified based on the related information of the object to be identified includes: In a case where the association information includes user information of the associated objects, obtaining each of the associated objects of the object to be identified; Determining an associated emotion factor of each associated object according to the user information of each associated object; Determining a first target associated emotional factor of the object to be identified according to the associated emotional factor of each associated object; Alternatively, in a case where the association information includes the domain information, the second target association emotion factor of the object to be identified is determined based on the domain information.

4. A target object recognition device, characterized in that: The device comprises: A first determining module is used to determine a target emotion factor of the object to be identified based on user information of the object to be identified; A second determining module is configured to determine a target group corresponding to the object to be identified from a group based on the target emotion factor of the object to be identified, wherein for any of the groups, the target emotion factor of each object in the group is within a numerical range corresponding to the group; A third determination module is configured to determine a target-associated emotion factor of the object to be identified based on the associated information of the object to be identified when the event occurrence probability corresponding to the target group is greater than or equal to a first value, wherein the event occurrence probability is used to represent the probability of the target event occurring; An adjustment module, configured to adjust the event occurrence probability according to the target-associated emotion factor to obtain the target event occurrence probability of the object to be identified; The adjustment module is further configured to: obtain a probability correction formula corresponding to the target group; input the target-related emotion factor of the object to be identified into the probability correction formula to obtain the probability of occurrence of the target event of the object to be identified; An identification module, configured to, when the probability of occurrence of the target event of the object to be identified is greater than or equal to a second value, take the object to be identified as a target object; a fourth determination module for determining, for any of the groups, a factor coefficient corresponding to the target-associated emotion factor based on the event occurrence probability corresponding to the group, the target-associated emotion factor of each historical object in the group, and the event occurrence annotation probability of each historical object in the group; and a construction module for constructing a probability correction formula corresponding to the group based on the factor coefficient and the event occurrence probability corresponding to the group; The fifth determination module is used to determine, for any of the groups, a first numerical value corresponding to the historical objects in the group in which the target event occurred; and the sixth determination module is used to determine the probability of occurrence of the event corresponding to the group based on the first numerical value and the number of the historical objects in the group.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

7. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images