A method for obtaining a target value, an electronic device and a storage medium

Abstract

The present invention provides a target value acquisition method, an electronic device and a storage medium, and relates to the field of data processing technology. The method comprises: matching a first target event label value list with a first target event rule value list, and if the match is successful, executing the next step, performing similarity matching on a second target event label value list and a second target event rule value list, obtaining an initial matching score list, and obtaining an initial score value and an initial candidate value based on the initial matching score list. If the initial candidate value is greater than a preset pre-rule value, obtaining a target value based on the initial score value and the initial candidate value, and the target value is a matching result between the target event and the first target event rule and the second target event rule, thereby improving the efficiency of obtaining the target value.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a target value acquisition method, electronic equipment and storage medium. Background Art

[0002] In the prior art, it is very common to match the event information of the target user with the conditions in the rule table, obtain the matching results, and process the events of the target user according to the matching results; for example, the target user has insured medical insurance. When the target user receives medical treatment in the hospital, the amount of compensation needs to be determined based on the event of the target user receiving medical treatment in the hospital and the terms of the medical insurance.

[0003] Since the conditions in the event information and rule tables are often hidden in unstructured document files, it is not convenient to match them directly. Therefore, in the prior art, the matching results, that is, whether to claim and the amount of insurance compensation, are often determined manually. However, manual matching is inefficient and has a poor experience. Summary of the invention

[0004] In view of the above technical problems, the technical solution adopted by the present invention is: a method for obtaining a target value, the method comprising the following steps:

[0005] Match the first target event label value list and the first target event rule value list, and if the match is successful, execute the next step; wherein the first target event label value list contains a plurality of first target event label values ​​for recording target events, and the first target event label values ​​correspond to the first preset labels one by one, and the first target event rule value contains a plurality of first target event rule values ​​for recording target events, and the first target event label values ​​correspond to the first preset rules one by one;

[0006] Perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list, wherein the first target event label value list corresponds to the second target event label value list, the first target event rule value list corresponds to the second target event rule value list, the second target event label value list includes a plurality of second target event label values ​​for recording target events, the second target event label values ​​correspond one-to-one to the second preset labels respectively, the second target event rule value list includes a plurality of second target event rule values ​​for recording target events, the second target event rule values ​​correspond one-to-one to the second preset rules respectively, and the initial matching score list includes a plurality of initial matching scores;

[0007] Based on the initial matching score list, obtaining an initial score value and an initial candidate value, wherein the initial candidate value is obtained based on the number of initial matching scores that meet a preset threshold rule, and the initial score value is a weighted sum of the initial matching scores;

[0008] If the initial candidate value is greater than the preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value, where the target value is a matching result between the target event and the first target event rule and the second target event rule.

[0009] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned method.

[0010] According to yet another aspect of the present invention, an electronic device is provided, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0011] The present invention has at least the following beneficial effects: In summary, the first target event label value list and the first target event rule value list are matched. If the match is successful, the next step is executed to perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list. Based on the initial matching score list, an initial score value and an initial candidate value are obtained. If the initial candidate value is greater than a preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value. The target value is the matching result of the target event and the first target event rule and the second target event rule, thereby realizing automatic acquisition of the target value and improving the efficiency of acquiring the target value. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A flowchart of a method for obtaining a target value provided in Embodiment 1 of the present invention;

[0014] Figure 2 This is a flow chart of S300 provided in the first embodiment of the present invention;

[0015] Figure 3 This is a flow chart of S310 provided in the first embodiment of the present invention;

[0016] Figure 4A flowchart of the steps to be performed after obtaining the target value list provided in the first embodiment of the present invention;

[0017] Figure 5 This is a flow chart of S100 provided in the first embodiment of the present invention;

[0018] Figure 6 A schematic diagram of the structure of a target value acquisition device provided in Embodiment 2 of the present invention;

[0019] Figure 7 A schematic diagram of the structure of a first matching module provided in Embodiment 2 of the present invention;

[0020] Figure 8 A schematic diagram of the structure of the initial weight list acquisition submodule provided in the second embodiment of the present invention;

[0021] Fig. 9 A schematic diagram of the structure of a second matching module provided in Embodiment 2 of the present invention;

[0022] Fig.10 This is a schematic diagram of the structure of a target event rule list acquisition module provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] Embodiment 1 of the present invention provides a method for obtaining a target value, such as Figure 1 As shown, the method comprises the following steps:

[0025] S100, match the first target event label value list and the first target event rule value list, and if the match is successful, execute the next step; wherein, the first target event label value list contains several first target event label values ​​for recording target events, and the first target event label values ​​correspond one-to-one to the first preset labels, and the first target event rule value contains several first target event rule values ​​for recording target event rules, and the first target event label values ​​correspond one-to-one to the first preset rules.

[0026] Specifically, the first preset tag list A={A 1 , A 2 , …, A i , …, A m}, A iis the i-th first preset tag, the value range of i is 1 to m, and m is the number of first preset tags; the first target event tag value list B={B 1 , B 2 , …, B i , …, B m}, B i The target event is in A i The corresponding label value.

[0027] The first preset rule list C={C 1 , C 2 , …, C i , …, C m}, C i is the first preset rule of the ith instance, the first target event rule value list D={D 1 , D 2 , …, D i , …, D m}, D i is the target event rule in C i The corresponding value.

[0028] Specifically, those skilled in the art know that methods for cleaning the target event description information to obtain the target event tag value corresponding to the preset tag all belong to the protection scope of the present invention and are not described in detail here. Wherein, the first preset tag at least includes a user ID, wherein the user ID is a unique identifier of the user.

[0029] Specifically, get B i and D i Similarity of SA i , if any SA i ≥ first preset threshold SA 0 , it is considered that the match is successful. In one embodiment of the present invention, SA 0 =1.

[0030] Further, the first target event label value list and the first target event rule value list are matched, and if the match fails, the target value is set to a preset fixed value.

[0031] S200, perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list, wherein the first target event label value list corresponds to the second target event label value list, the first target event rule value list corresponds to the second target event rule value list, the second target event label value list includes several second target event label values ​​for recording target events, the second target event label values ​​correspond one-to-one to the second preset labels respectively, the second target event rule value list includes several second target event rule values ​​for recording target event rules, the second target event rule values ​​correspond one-to-one to the second preset rules respectively, and the initial matching score list includes several initial matching scores.

[0032] Specifically, the second preset tag list E={E 1 , E 2 , …, E j , …, En}, Ej is the jth second preset label, the value range of j is 1 to n, n is the number of second preset labels, and the second preset label is different from the first preset label, the second target event label value list F={F1, F2, …, Fj, …, Fn}, Fj is the value of Ej corresponding to the target event.

[0033] The second preset rule list G={G1, G2, …, Gj, …, Gn}, where Gj is the jth second preset rule, and the second preset rule is different from the first preset rule. The second target event rule value list H={H1, H2, …, Hj, …, Hn}, where Hj is the value of Gj corresponding to the target event rule.

[0034] Specifically, obtain the similarity between Fj and Hj as the initial matching score J j , thereby obtaining the initial matching score list J={J 1 , J 2 , …, J j , …, J n}.

[0035] S300, based on the initial matching score list, obtaining an initial score value and an initial candidate value, wherein the initial candidate value is obtained based on the number of initial matching scores that meet a preset threshold rule, and the initial score value is a weighted sum of the initial matching scores.

[0036] Specifically, the initial score value J 0 =∑ n j=1 (w j ×J j ), w jis the initial weight corresponding to the second preset tag; the initial matching score that satisfies the preset threshold rule is the initial matching score greater than the second preset threshold, and the number a of initial matching scores greater than the second preset threshold is obtained, and the initial candidate value K=a×K 0 , K 0 is a preset candidate value.

[0037] S400: If the initial candidate value is greater than the preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value, where the target value is a matching result between the target event and the first target event rule and the second target event rule.

[0038] Specifically, if the initial score value is not greater than the preset pre-rule value, the target value is set to a preset fixed value.

[0039] In summary, the first target event label value list and the first target event rule value list are matched. If the match is successful, the next step is executed to perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list. Based on the initial matching score list, an initial score value and an initial candidate value are obtained. If the initial candidate value is greater than the preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value. The target value is the matching result between the target event and the first target event rule and the second target event rule. By executing the above steps, the target value can be automatically obtained and the efficiency of obtaining the target value can be improved.

[0040] Specifically, Figure 2 As shown, in S300, the initial score value is calculated based on the initial matching score list, and the following steps are also included:

[0041] S310, obtaining an initial weight list, wherein the initial weight list includes a plurality of initial weights, and the initial weights correspond to the second preset labels one by one. Specifically, the initial weight list w={w 1 , w 2 ,…,w j ,…,w n}.

[0042] S320: Based on the initial weight list, perform weighted summation on the initial matching scores to obtain an initial score value.

[0043] In one embodiment of the present invention, the initial score value J 0 =∑ n j=1 (w j ×J j / (∑ n j= 1w j )).

[0044] Further, such as Figure 3 As shown, in S310, the initial weight list is obtained through the following steps:

[0045] S311, obtain the first historical event label value list and the first historical event rule value list for matching, if the match is successful, execute the next step, wherein the first historical event label value list contains several first historical event label values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset labels, and the first historical event rule value contains several first historical event rule values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset rules.

[0046] S312, perform similarity matching on the second historical event label value list corresponding to the first historical event label value list and the second historical event rule value list corresponding to the first historical event rule value list, and obtain a historical matching score list, wherein the second historical event label value list includes several second historical event label values ​​for recording historical events, and the second historical event label values ​​correspond one-to-one to the second preset labels respectively; the second historical event rule value list includes several second historical event rule values ​​for recording historical events, and the second historical event rule values ​​correspond one-to-one to the second preset rules respectively; and the historical matching score list includes several historical matching scores.

[0047] S313, obtaining a historical real target value corresponding to the historical event, where the historical real target value is a real matching result between the historical event and the first historical event rule and the second historical event rule.

[0048] S314, based on the historical matching score list and the historical true target value, obtain an initial weight list.

[0049] Further, based on S311-S314, obtain the historical matching score list set L={L 1 , L 2 , …, L a , …, L b} and L a The corresponding target value M a , the ath historical matching score list L a ={L a1 , L a2 , …, L ae , …, L ah}, L ae is the e-th historical match score in the a-th historical match score list. The value of a ranges from 1 to b, and b is the number of historical match score lists.

[0050] Specifically, w j =[∑ ba=1 (L ae ×M a )] / (∑ b a=1 L ae ).

[0051] In summary, obtain the first historical event label value list and the first historical event rule value list for matching. If the match is successful, execute the next step, perform similarity matching on the second historical event label value list corresponding to the first historical event label value list and the second historical event rule value list corresponding to the first historical event rule value list, obtain a historical matching score list, obtain the historical real target value corresponding to the historical event, obtain an initial weight list based on the historical matching score list and the historical real target value, and obtain the initial weight list based on the historical data, so as to obtain the initial score more accurately.

[0052] Furthermore, Figure 4 As shown, in S400, after the target value is obtained by performing calculation based on the initial score value and the initial candidate value, the following is further included:

[0053] S410, obtaining a first weighting factor and a second weighting factor, and obtaining a weighted intermediate value based on the first weighting factor and the second weighting factor; wherein the target value is the sum of a first product value and a second product value, the first product value is the product of an initial score value and a first weighting factor, the second product value is the product of an initial rule value and a second weighting factor, and the first weighting factor is greater than zero, and the second weighting factor is less than zero.

[0054] S420: If the weighted intermediate value satisfies the preset matching rule, the initial candidate value is used as the target value.

[0055] Furthermore, if the weighted middle value meets the preset matching rules, it enters the manual review process.

[0056] Specifically, Figure 5 As shown, in S100, the first preset rule and the second preset rule are obtained through the following steps:

[0057] S110, obtaining rule description information, and performing word segmentation processing on the rule description information to obtain an initial word segmentation list, wherein the initial word segmentation list includes a plurality of initial word segmentations.

[0058] Specifically, those skilled in the art know that any method for word segmentation in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0059] S120, taking the target preset tag as the preset topic, using the preset topic model to divide the initial word segmentation into the target preset tag, obtaining the intermediate word segmentation list corresponding to the target preset tag and the matching probability of each intermediate word segmentation, wherein the intermediate word segmentation list includes a plurality of initial word segmentations assigned to the same target preset tag, the matching probability is the semantic similarity between the intermediate word segmentation and the target preset tag corresponding to the intermediate word segmentation list where the intermediate word segmentation is located, and the target preset tag includes a first preset tag and a second preset tag.

[0060] In one embodiment of the present invention, the preset topic model is an LDA model.

[0061] S130, screening the middle participles based on the matching probability, and obtaining a target participle list corresponding to the preset label, wherein the target participle list includes a plurality of target participles, and the target participles are the middle participles whose matching probability meets the preset matching threshold.

[0062] Specifically, the preset matching requirement is: the matching probability is greater than the preset matching threshold. Therefore, when the matching probability of a middle participle is greater than the preset matching threshold, the middle participle is used as the target participle, thereby obtaining a target participle list.

[0063] S140: Generate a first preset rule and a second preset rule based on the target word segmentation list and the rule description information.

[0064] Specifically, based on the sentence where the target word segmentation list is located in the rule description information, a regular expression is generated to obtain a first preset rule and a first preset rule value, a second preset rule and a second preset rule value.

[0065] In summary, the rule description information is obtained, and the rule description information is segmented to obtain an initial segmentation list. Based on the historical matching score list and the historical real target value, an initial weight list is obtained. The intermediate segmentations are screened based on the matching probability, and a target segmentation list corresponding to the preset label is obtained. Based on the target segmentation list and the rule description information, the first preset rule and the second preset rule are generated, so as to obtain the first preset rule and the second preset rule more accurately.

[0066] Embodiment 2 of the present invention provides a target value acquisition device, such as Figure 6 As shown, the device comprises:

[0067] The target event description information acquisition module 10 is used to match the first target event label value list and the first target event rule value list. If the match is successful, the target event rule list acquisition module 20 is executed; wherein, the first target event label value list contains a plurality of first target event label values ​​for recording target events, and the first target event label values ​​correspond one-to-one to the first preset labels respectively; the first target event rule value contains a plurality of first target event rule values ​​for recording target event rules, and the first target event label values ​​correspond one-to-one to the first preset rules respectively.

[0068] The target event rule list acquisition module 20 is used to perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list, wherein the first target event label value list corresponds to the second target event label value list, the first target event rule value list corresponds to the second target event rule value list, the second target event label value list includes several second target event label values ​​for recording target events, and the second target event label values ​​correspond one-to-one to the second preset labels respectively, the second target event rule value list includes several second target event rule values ​​for recording target event rules, and the second target event rule values ​​correspond one-to-one to the second preset rules respectively, and the initial matching score list includes several initial matching scores.

[0069] The first matching module 30 obtains an initial score value and an initial candidate value based on the initial matching score list, wherein the initial candidate value is obtained based on the number of initial matching scores that meet a preset threshold rule, and the initial score value is a weighted sum of the initial matching scores.

[0070] The second matching module 40 obtains a target value based on the initial score value and the initial candidate value if the initial candidate value is greater than the preset pre-rule value, wherein the target value is a matching result between the target event and the first target event rule and the second target event rule.

[0071] Specifically, Figure 7 As shown, the first matching module 30 also includes the following submodules:

[0072] The initial weight list acquisition submodule 31 is used to acquire an initial weight list, wherein the initial weight list includes a plurality of initial weights, and the initial weights correspond to the second preset labels one by one.

[0073] The weighted sum submodule 32 is used to perform weighted summation on the initial matching scores based on the initial weight list to obtain an initial score value.

[0074] Specifically, Figure 8 As shown, the initial weight list acquisition submodule 31 also includes the following subunits:

[0075] The first historical matching subunit 33 is used to obtain a first historical event label value list and a first historical event rule value list for matching. If the match is successful, the next step is executed, wherein the first historical event label value list contains a plurality of first historical event label values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset labels respectively; the first historical event rule value contains a plurality of first historical event rule values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset rules respectively.

[0076] The second historical matching subunit 34 is used to perform similarity matching on the second historical event label value list corresponding to the first historical event label value list and the second historical event rule value list corresponding to the first historical event rule value list to obtain a historical matching score list, wherein the second historical event label value list includes a plurality of second historical event label values ​​for recording historical events, and the second historical event label values ​​correspond one-to-one to the second preset labels respectively; the second historical event rule value list includes a plurality of second historical event rule values ​​for recording historical events, and the second historical event rule values ​​correspond one-to-one to the second preset rules respectively; and the historical matching score list includes a plurality of historical matching scores.

[0077] The historical matching score acquisition subunit 35 is used to acquire the historical real target value corresponding to the historical event, where the historical real target value is the real matching result between the historical event and the first historical event rule and the second historical event rule.

[0078] The initial weight acquisition subunit 36 ​​is used to acquire an initial weight list based on the historical matching score list and the historical true target value.

[0079] Specifically, Fig. 9 As shown, the second matching module 40 further includes an execution submodule, and the execution submodule includes the following subunits:

[0080] The final value acquisition subunit 41 is used to obtain the first weighting factor and the second weighting factor, and obtain the weighted intermediate value based on the first weighting factor and the second weighting factor; wherein the target value is the sum of the first product value and the second product value, the first product value is the product of the initial score value and the first weighting factor, the second product value is the product of the initial rule value and the second weighting factor, and the first weighting factor is greater than zero, and the second weighting factor is less than zero.

[0081] The target value subunit 42 is used to use the initial candidate value as the target value if the weighted intermediate value meets the preset matching rule.

[0082] Specifically, Fig.10 As shown, the target event rule list acquisition module 20 includes the following submodules:

[0083] The initial segmentation acquisition submodule 21 is used to acquire rule description information, and perform segmentation processing on the rule description information to acquire an initial segmentation list, wherein the initial segmentation list includes a plurality of initial segmentations.

[0084] The matching probability acquisition submodule 22 is used to take the target preset tag as the preset topic, use the preset topic model to divide the initial word segmentation into the target preset tag, obtain the intermediate word segmentation list corresponding to the target preset tag and the matching probability of each intermediate word segmentation, wherein the intermediate word segmentation list contains a number of initial word segmentations assigned to the same target preset tag, and the matching probability is the semantic similarity between the intermediate word segmentation and the target preset tag corresponding to the intermediate word segmentation list where the intermediate word segmentation is located, and the target preset tag includes a first preset tag and a second preset tag.

[0085] The target segmentation acquisition submodule 23 screens the intermediate segmentations based on the matching probability to obtain a target segmentation list corresponding to a preset tag, wherein the target segmentation list includes a plurality of target segmentations, and the target segmentations are intermediate segmentations whose matching probability meets a preset matching threshold.

[0086] The generating submodule 24 generates a first preset rule and a second preset rule based on the target word segmentation list and the rule description information.

[0087] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the steps:

[0088] S100, match the first target event label value list and the first target event rule value list, and if the match is successful, execute the next step; wherein, the first target event label value list contains several first target event label values ​​for recording target events, and the first target event label values ​​correspond one-to-one to the first preset labels, and the first target event rule value contains several first target event rule values ​​for recording target event rules, and the first target event label values ​​correspond one-to-one to the first preset rules.

[0089] S200, perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list, wherein the first target event label value list corresponds to the second target event label value list, the first target event rule value list corresponds to the second target event rule value list, the second target event label value list includes several second target event label values ​​for recording target events, the second target event label values ​​correspond one-to-one to the second preset labels respectively, the second target event rule value list includes several second target event rule values ​​for recording target event rules, the second target event rule values ​​correspond one-to-one to the second preset rules respectively, and the initial matching score list includes several initial matching scores.

[0090] S300, based on the initial matching score list, obtaining an initial score value and an initial candidate value, wherein the initial candidate value is obtained based on the number of initial matching scores that meet a preset threshold rule, and the initial score value is a weighted sum of the initial matching scores.

[0091] S400: If the initial candidate value is greater than the preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value, where the target value is a matching result between the target event and the first target event rule and the second target event rule.

[0092] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0093] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for obtaining a target value, characterized in that: The method comprises the following steps: Match the first target event label value list and the first target event rule value list, and if the match is successful, execute the next step; wherein the first target event label value list contains a plurality of first target event label values ​​for recording target events, and the first target event label values ​​correspond one-to-one to the first preset labels, and the first target event rule value contains a plurality of first target event rule values ​​for recording target events, and the first target event rule values ​​correspond one-to-one to the first preset rules; Perform similarity matching on the second target event label value list and the second target event rule value list to obtain an initial matching score list, wherein the first preset corresponds to the second target event label value list, the first target event rule value list corresponds to the second target event rule value list, the second target event label value list includes a plurality of second target event label values ​​for recording target events, the second target event label values ​​correspond one-to-one to the second preset labels, the second target event rule value list includes a plurality of second target event rule values ​​for recording target events, the second target event rule values ​​correspond one-to-one to the second preset rules, and the initial matching score list includes a plurality of initial matching scores; Based on the initial matching score list, obtaining an initial score value and an initial candidate value, wherein the initial candidate value is obtained based on the number of initial matching scores that meet a preset threshold rule, and the initial score value is a weighted sum of the initial matching scores; If the initial candidate value is greater than the preset pre-rule value, a target value is obtained based on the initial score value and the initial candidate value, where the target value is a matching result between the target event and the first target event rule and the second target event rule; The first preset rule and the second preset rule are obtained through the following steps: Obtaining rule description information corresponding to the target event rule, and performing word segmentation processing on the rule description information to obtain an initial word segmentation list, wherein the initial word segmentation list includes a plurality of initial word segmentations; Taking the target preset tag as the preset topic, using the preset topic model to divide the initial participles into the target preset tag, obtaining the intermediate participle list corresponding to the target preset tag and the matching probability of each intermediate participle, wherein the intermediate participle list includes a plurality of initial participles assigned to the same target preset tag, and the matching probability is the semantic similarity between the intermediate participle and the target preset tag corresponding to the intermediate participle list where the intermediate participle is located, and the target preset tag includes a first preset tag and a second preset tag; The intermediate participles are screened based on the matching probability to obtain a target participle list corresponding to the preset label, wherein the target participle list includes a plurality of target participles, and the target participles are intermediate participles whose matching probability meets the preset matching threshold; A first preset rule and a second preset rule are generated based on the target word segmentation list and the rule description information.

2. The target value acquisition method according to claim 1, characterized in that: The initial score value is calculated based on the initial matching score list, and the following steps are also included: Obtain an initial weight list, wherein the initial weight list includes a plurality of initial weights, and the initial weights correspond to the second preset label one by one; Based on the initial weight list, the initial matching scores are weighted summed to obtain an initial score value.

3. The target value acquisition method according to claim 2, characterized in that: Get the initial weight list by following the steps below: Obtain a first historical event label value list and a first historical event rule value list for matching, and if the match is successful, execute the next step, wherein the first historical event label value list includes a plurality of first historical event label values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset labels, and the first historical event rule value list includes a plurality of first historical event rule values ​​for recording historical events, and the first historical event label values ​​correspond one-to-one to the first preset rules; Performing similarity matching on the second historical event label value list corresponding to the first historical event label value list and the second historical event rule value list corresponding to the first historical event rule value list to obtain a historical matching score list, wherein the second historical event label value list includes a plurality of second historical event label values ​​for recording historical events, and the second historical event label values ​​correspond one-to-one to the second preset labels, respectively; the second historical event rule value list includes a plurality of second historical event rule values ​​for recording historical events, and the second historical event rule values ​​correspond one-to-one to the second preset rules, respectively; and the historical matching score list includes a plurality of historical matching scores; Obtaining a historical real target value corresponding to the historical event, where the historical real target value is a real matching result between the historical event and the first historical event rule and the second historical event rule; Based on the historical matching score list and the historical true target value, an initial weight list is obtained.

4. The target value acquisition method according to claim 1, characterized in that: The first target event label value list and the first target event rule value list are matched, and if the match fails, the target value is set to a preset fixed value.

5. The target value acquisition method according to claim 4, characterized in that: If the initial score value is not greater than the preset pre-rule value, the target value is set to a preset fixed value.

6. The target value acquisition method according to claim 1, characterized in that: After obtaining the target value, the calculation is performed based on the initial score value and the initial candidate value, and the following is also included: Obtaining a first weighting factor and a second weighting factor, and obtaining a weighted intermediate value based on the first weighting factor and the second weighting factor; wherein the target value is the sum of a first product value and a second product value, the first product value is the product of an initial score value and a first weighting factor, the second product value is the product of an initial rule value and a second weighting factor, and the first weighting factor is greater than zero, and the second weighting factor is less than zero; If the weighted intermediate value meets the preset matching rule, the initial candidate value is used as the target value.

7. The target value acquisition method according to claim 6, characterized in that: If the weighted middle value meets the preset matching rules, it will enter manual review processing.

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the target value acquisition method as described in any one of claims 1-7.

9. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 8.

Images