A data return method and device based on multi-platform and multi-data

Abstract

The present invention discloses a data return method and device based on multi-platform and multi-data, the method comprising: obtaining return data that needs to be returned to a target media platform, the target media platform being any media platform that needs to return data, the return data being any data of all return data that needs to be returned to the target media platform, matching the return data with a pre-generated return policy library, obtaining a policy matching result corresponding to the return data, the return policy library including several return policies, when the policy matching result indicates that a target return policy matching the return data is matched, determining the return data as target return data that needs to be returned to the target media platform through the target return policy, and returning the target return data to the target media platform. It can be seen that the implementation of the present invention can be beneficial to improving the return efficiency of data returned to the media platform, and can be beneficial to improving the accuracy of data returned to the media platform.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data return method and device based on multi-platform and multi-data. Background Art

[0002] In real life, with the popularization and development of Internet technology, Internet advertising has become an important channel for marketing. Merchants place advertisements on Internet platforms to quickly expose and spread their products on the Internet. After placing advertisements, it is necessary to monitor the feedback information on the platforms where the advertisements are placed, and then manage and adjust the corresponding advertising strategies based on the feedback information.

[0003] At present, the feedback of advertising feedback information usually requires the configuration of the interface of each media platform separately, and each feedback rule needs to be hard-coded separately. However, there are many types of feedback information for each advertisement, and the optimization rules required to be used on different media platforms are different, which makes the feedback efficiency low and the accuracy low. It can be seen that it is particularly important to provide a new data feedback method to improve the efficiency and accuracy of data feedback. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a data return method and device based on multi-platform and multi-data, which can help improve the return efficiency of data returned to the media platform, and can help improve the accuracy of data returned to the media platform.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a data return method based on multi-platform and multi-data, the method comprising:

[0006] Acquire feedback data that needs to be transmitted back to a target media platform, where the target media platform is any media platform that needs to transmit data back, and the feedback data is any data among all feedback data that needs to be transmitted back to the target media platform;

[0007] Matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, wherein the return policy library includes a plurality of return policies;

[0008] When the strategy matching result indicates that a target return strategy matching the return data is matched, the return data is determined as target return data that needs to be returned to the target media platform through the target return strategy;

[0009] The target return data is returned to the target media platform.

[0010] As an optional implementation, in the first aspect of the present invention, before determining the return data as target return data that needs to be returned to the target media platform through the target return strategy, the method further includes:

[0011] Determine whether the target return policy is enabled;

[0012] When it is determined that the state of the target return policy is the enabled state, determining whether the current time is within the effective time period corresponding to the target return policy;

[0013] When it is determined that the current moment is within the effective time period corresponding to the target return policy, it is determined whether the target return policy has a return quantity restriction;

[0014] When it is determined that the target return policy has the return quantity limit, determining whether the quantity of returned data and to-be-returned data that matches the target return policy is less than or equal to a preset return quantity threshold;

[0015] When it is determined that the number of returned data and data to be returned that matches the target return strategy is less than or equal to the preset return quantity threshold, determining whether the returned data meets the return condition that matches the target return strategy;

[0016] When it is determined that the return data meets the return condition that matches the target return strategy, the step of determining the return data as target return data that needs to be returned to the target media platform through the target return strategy is performed.

[0017] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0018] When it is determined that the returned data does not meet the return condition that matches the target return policy, analyzing the abnormal reason why the returned data does not meet the return condition;

[0019] When the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the return condition, an operation matching the target conversion event is performed on the returned data to obtain corrected data, and the corrected data is determined as the target returned data.

[0020] As an optional implementation, in the first aspect of the present invention, matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data includes:

[0021] Determine the matching number, and determine at least one key information group from all the key information included in the returned data according to the matching number, wherein the number of key information included in each key information group is the matching number;

[0022] For each of the key information groups, matching is performed in a pre-generated return strategy library to obtain a matching result for each of the key information groups;

[0023] Determining whether the matching results of all the key information groups indicate that no corresponding return strategy is matched;

[0024] When it is determined that the matching results of all the key information groups indicate that no corresponding return strategy is matched, the matching number is reduced according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all the key information included in each of the return data according to the matching number is repeated;

[0025] When it is determined that the matching results of at least two of the key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all the first key information groups that match the corresponding return strategies, and the return strategy that matches the target key information group is determined as the strategy matching result corresponding to the return data;

[0026] When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

[0027] As an optional implementation manner, in the first aspect of the present invention, the step of filtering out the target key information group from all first key information groups matched to the corresponding return strategy includes:

[0028] For each of the first key information groups that each matching result indicates matches to the corresponding return strategy, extracting the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group;

[0029] For each of the first key information groups that the matching result indicates matches the corresponding return strategy, calculate the correlation degree between the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, and obtain the correlation degree corresponding to the first key information group;

[0030] The correlation levels corresponding to each of the first key information groups are summarized, and the first key information group with the highest correlation level is determined as the target key information group.

[0031] As an optional implementation, in the first aspect of the present invention, before matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, the method further includes:

[0032] According to a number of predetermined feedback requirements, a feedback strategy corresponding to each feedback requirement is determined, and all the feedback strategies are summarized to obtain a feedback strategy library, wherein the feedback strategy includes one or more of delivery method, strategy name, product category, media platform, operating system, attribution method, strategy effective time period, feedback ratio, and feedback quantity.

[0033] As an optional implementation manner, in the first aspect of the present invention, after obtaining the return data that needs to be returned to the target media platform, the method further includes:

[0034] Determine matching conditions, where the matching conditions include one or more of a media platform condition, an advertising event condition, a delivery method condition, and a conversion target condition;

[0035] Determine whether the returned data meets the matching condition;

[0036] When it is determined that the returned data meets the matching condition, the operation of matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data is triggered;

[0037] When it is determined that the returned data does not satisfy the matching condition, the returned data is determined as non-matching data, and the non-matching data is input into the target database.

[0038] The second aspect of the present invention discloses a data return device based on multi-platform and multi-data, the device comprising:

[0039] An acquisition module, used for acquiring feedback data that needs to be transmitted back to a target media platform, wherein the target media platform is any media platform that needs to transmit data back, and the feedback data is any data among all the feedback data that needs to be transmitted back to the target media platform;

[0040] A matching module, used for matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, wherein the return policy library includes a plurality of return policies;

[0041] A determination module, configured to determine the return data as target return data that needs to be returned to the target media platform through the target return strategy when the strategy matching result indicates that a target return strategy matching the return data is matched;

[0042] The feedback module is used to transmit the target feedback data back to the target media platform.

[0043] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0044] A judging module, used for judging whether the state of the target return policy is enabled before the determining module determines the return data as target return data that needs to be returned to the target media platform through the target return policy;

[0045] The determination module is further configured to determine whether the current time is within the effective time period corresponding to the target backhaul policy when it is determined that the state of the target backhaul policy is the enabled state;

[0046] The judging module is further configured to judge whether there is a limit on the number of returns for the target return policy when it is judged that the current moment is within the effective time period corresponding to the target return policy;

[0047] The determination module is further configured to determine whether the number of returned data and to-be-returned data that matches the target return strategy is less than or equal to a preset return strategy threshold when it is determined that the target return strategy has the return strategy limit.

[0048] The judgment module is further configured to judge whether the returned data meets the return condition matching the target return strategy when it is judged that the number of returned data and data to be returned that matches the target return strategy is less than or equal to the preset return quantity threshold;

[0049] The judgment module is also used to trigger the determination module to execute the step of determining the return data as target return data that needs to be returned to the target media platform through the target return strategy when it is determined that the return data meets the return condition that matches the target return strategy.

[0050] As an optional implementation, in the second aspect of the present invention, the device further includes:

[0051] An analysis module, configured to analyze an abnormal reason why the returned data does not meet the return condition when the judgment module judges that the returned data does not meet the return condition matching the target return policy;

[0052] An execution module, configured to, when the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the return condition, execute an operation matching the target conversion event on the returned data to obtain corrected data;

[0053] The determination module is further configured to determine the corrected data as target return data.

[0054] As an optional implementation, in the second aspect of the present invention, the matching module matches the return data with a pre-generated return policy library to obtain a policy matching result corresponding to the return data in the following manner:

[0055] Determine the matching number, and determine at least one key information group from all the key information included in the returned data according to the matching number, wherein the number of key information included in each key information group is the matching number;

[0056] For each of the key information groups, matching is performed in a pre-generated return strategy library to obtain a matching result for each of the key information groups;

[0057] Determining whether the matching results of all the key information groups indicate that no corresponding return strategy is matched;

[0058] When it is determined that the matching results of all the key information groups indicate that no corresponding return strategy is matched, the matching number is reduced according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all the key information included in each of the return data according to the matching number is repeated;

[0059] When it is determined that the matching results of at least two of the key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all the first key information groups that match the corresponding return strategies, and the return strategy that matches the target key information group is determined as the strategy matching result corresponding to the return data;

[0060] When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

[0061] As an optional implementation, in the second aspect of the present invention, the matching module selects the target key information group from all first key information groups matched to the corresponding return strategy in the following manner:

[0062] For each first key information group that each matching result indicates matches to a corresponding feedback strategy, extracting the information keyword of the first key information group and the feedback keyword of the feedback strategy corresponding to the first key information group;

[0063] For each of the first key information groups that the matching result indicates matches the corresponding return strategy, calculate the correlation degree between the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, and obtain the correlation degree corresponding to the first key information group;

[0064] The correlation levels corresponding to each of the first key information groups are summarized, and the first key information group with the highest correlation level is determined as the target key information group.

[0065] As an optional implementation, in the second aspect of the present invention, the determination module is further configured to determine a return strategy corresponding to each return requirement according to a plurality of return requirements determined in advance, before the matching module matches the return data with a pre-generated return strategy library to obtain a strategy matching result corresponding to the return data;

[0066] The device also includes:

[0067] The summary module is used to summarize all the feedback strategies to obtain a feedback strategy library, wherein the feedback strategy includes one or more of the delivery method, strategy name, product category, media platform, operating system, attribution method, strategy effective time period, feedback ratio, and feedback quantity.

[0068] As an optional implementation, in the second aspect of the present invention, the determination module is further used to determine a matching condition after the acquisition module acquires the return data that needs to be returned to the target media platform, and the matching condition includes one or more of a media platform condition, an advertising event condition, a delivery method condition, and a conversion target condition;

[0069] The judging module is further configured to judge whether the returned data satisfies the matching condition;

[0070] The judgment module is further configured to trigger the matching module to perform the operation of matching the returned data with a pre-generated returned policy library to obtain a policy matching result corresponding to the returned data when it is determined that the returned data meets the matching condition;

[0071] The determination module is further configured to determine the returned data as non-matching data and input the non-matching data into the target database when the determination module determines that the returned data does not satisfy the matching condition.

[0072] The third aspect of the present invention discloses another data return device based on multi-platform and multi-data, the device comprising:

[0073] A memory storing executable program code;

[0074] a processor coupled to the memory;

[0075] The processor calls the executable program code stored in the memory to execute the data return method based on multi-platform and multi-data disclosed in the first aspect of the present invention.

[0076] The fourth aspect of the present invention discloses a computer storable medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the multi-platform and multi-data based data return method disclosed in the first aspect of the present invention.

[0077] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0078] In an embodiment of the present invention, the feedback data that needs to be transmitted back to the target media platform is obtained, and the feedback data is matched with a pre-generated feedback strategy library to obtain a strategy matching result corresponding to the feedback data. The feedback strategy library includes several feedback strategies. When the strategy matching result indicates that a target feedback strategy that matches the feedback data is matched, the feedback data is determined as target feedback data that needs to be transmitted back to the target media platform through the target feedback strategy, and the target feedback data is transmitted back to the target media platform. It can be seen that the implementation of the present invention can help improve the efficiency of transmitting data back to the media platform, and can help improve the accuracy of transmitting data back to the media platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] 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.

[0080] Figure 1 It is a flowchart of a data return method based on multi-platform and multi-data disclosed in an embodiment of the present invention;

[0081] Figure 2 It is a flowchart of another data return method based on multi-platform and multi-data disclosed in an embodiment of the present invention;

[0082] Figure 3 It is a structural schematic diagram of a data return device based on multi-platform and multi-data disclosed in an embodiment of the present invention;

[0083] Figure 4 It is a structural schematic diagram of another data return device based on multi-platform and multi-data disclosed in an embodiment of the present invention;

[0084] Figure 5It is a structural schematic diagram of another data return device based on multi-platform and multi-data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0086] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0087] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0088] The present invention discloses a data return method and device based on multi-platform and multi-data, which can help improve the return efficiency of data returned to the media platform, and can help improve the accuracy of data returned to the media platform. The following are detailed descriptions.

[0089] Embodiment 1

[0090] See also Figure 1 , Figure 1 : is a flow chart of a data return method based on multi-platform and multi-data disclosed in an embodiment of the present invention. Figure 1 The described data return method based on multi-platform multi-data can be applied to a data return device based on multi-platform multi-data, and can also be applied to a cloud server or a local server for data return based on multi-platform multi-data, which is not limited in the embodiments of the present invention. Figure 1 As shown, the data return method based on multi-platform and multi-data may include the following operations:

[0091] 101. Obtain feedback data that needs to be transmitted back to the target media platform.

[0092] In the embodiment of the present invention, the target media platform is any media platform that needs to transmit back data, and the transmitted data is any data among all transmitted data that needs to be transmitted back to the target media platform.

[0093] In the embodiment of the present invention, optionally, after the feedback data that needs to be transmitted back to the target media platform is obtained, all the feedback data are input into a preset target database. Further optionally, the preset target database can be a MySQL database. It should be noted that the MySQL database is a relational database management system. The relational database stores data in different tables, which increases speed and flexibility. In this way, by inputting the obtained feedback data into the MySQL database, it can be helpful to improve the efficiency of subsequent strategy matching of the feedback strategy, thereby being helpful to improve the efficiency of transmitting the feedback data back to the target media platform.

[0094] In the embodiment of the present invention, the acquired feedback data can be optionally pushed to a pre-set message middleware. It should be noted that the message middleware is a supporting software system that provides synchronous or asynchronous, reliable message transmission for the application system in a network environment based on queue and message transmission technology, and can improve performance, reduce coupling, and perform traffic peak shaving through asynchronization. In this way, by pushing the acquired feedback data to the pre-set message middleware, local events can be activated by passing messages between different objects to complete corresponding operations, which can help improve the efficiency of subsequent strategy matching of the feedback strategy, thereby helping to improve the efficiency of returning the feedback data to the target media platform, and helping to improve the accuracy of returning the feedback data to the media platform.

[0095] 102. Match the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data.

[0096] In the embodiment of the present invention, the return strategy library includes several return strategies.

[0097] In the embodiment of the present invention, one return data only matches one return policy in the return policy library, and one return policy in the return policy library can match multiple return data. Optionally, the policy matching result includes matching the target return policy that matches the return data or not matching the target return policy that matches the return data.

[0098] 103. When the strategy matching result indicates that a target return strategy matching the return data is matched, the return data is determined as target return data that needs to be returned to the target media platform through the target return strategy.

[0099] In the embodiment of the present invention, further optionally, when the policy matching result indicates that the target return policy that matches the return data is not matched, the state of the return data corresponding to the target return policy that does not match the return data is modified to return data that does not meet the matching policy, and all return data that does not meet the matching policy is input into a pre-set target database. In this way, by modifying the state of the return data that does not match the return data, which indicates that the policy matching result indicates, to return data that does not meet the matching policy, and inputting all return data that does not meet the matching policy into a pre-set target database, it can be helpful to improve the accuracy of determining the target return policy, and it can be helpful to improve the accuracy of returning the target return data to the target media platform.

[0100] In an embodiment of the present invention, optionally, after the return data is determined as target return data that needs to be returned to the target media platform through the target return strategy, the target media platform's required format for the return data is analyzed, and the necessary parameters required by the target media platform are assembled according to the required format of the target media platform, and spliced ​​with the corresponding upload data network request address of the target media platform, wherein the necessary parameters required by the target media platform include one or more of event type, event time, and media return tag ID. In this way, by assembling the necessary parameters required by the target media platform according to the required format of the target media platform, and splicing with the corresponding upload data network request address of the target media platform, it can be helpful to improve the accuracy of returning the target data to the target media platform, and it can be helpful to improve the success rate of returning the target data to the target media platform.

[0101] 104. Send the target feedback data back to the target media platform.

[0102] In an embodiment of the present invention, optionally, before the target return data is returned to the target media platform, the target information in the target return data is extracted, and all the target information is inserted into a pre-set cache database, wherein the target information includes one or more information in the target media platform representation and event representation. Further optionally, the pre-set cache database can be a redis database, and the redis (Remote Dictionary Server) database is a remote dictionary service, which is a key-value storage system. The redis database supports relatively more value types for storage, including string, list, set, zset (sorted set ordered set) and hash, and the redis database has the characteristic of fast data reading speed. In this way, by extracting the target information in the target return data and inserting all the target information into the pre-set cache database, duplicate items can be deleted, and the same data can be returned to the target media platform without duplication, which is conducive to improving the efficiency of returning the target return data to the target media platform, and is conducive to improving the accuracy of returning the target return data to the target media platform.

[0103] In an optional embodiment, before transmitting the target return data back to the target media platform, the method may further include:

[0104] According to the target feedback strategy, determine whether to transmit the target feedback data back to the target media platform;

[0105] Among them, judging whether to transmit the target return data back to the target media platform according to the target return strategy may include: judging whether the target return data conforms to the event agreement corresponding to the target return strategy according to the target return strategy;

[0106] When it is determined that the target return data meets the event agreement corresponding to the target return strategy, an operation of returning the target return data to the target media platform is triggered;

[0107] When it is determined that the target return data does not conform to the event agreement corresponding to the target return policy, an operation matching the event agreement corresponding to the target return policy is performed on the target return data; or

[0108] The state of the target return data is changed to return-forbidden data, and the return-forbidden data is input into a preset database.

[0109] In this optional embodiment, optionally, the operation of performing an operation on the target return data that matches the event agreement corresponding to the target return policy may be to replace the target return data with data of the event agreement corresponding to the target return policy. In this way, by judging whether the target return data conforms to the event agreement corresponding to the target return policy according to the target return policy, and then judging whether to return the target return data to the target media platform, it can be helpful to improve the accuracy of returning the target return data to the target media platform, and it can be helpful to improve the success rate of returning the target return data to the target media platform.

[0110] In an optional embodiment, after the target return data is returned to the target media platform, the method may further include:

[0111] According to a preset time interval, counting the strategy matching result indicates a first quantity of the returned data corresponding to the target returned data strategy that matches the returned data, and counting the strategy matching result indicates a second quantity of the returned data corresponding to the target returned data strategy that does not match the returned data;

[0112] A visual display interface is generated based on the first quantity and the second quantity obtained by statistics. The visual display interface is used to display the first quantity of return data that matches the corresponding target return strategy, and the second quantity of return data that does not match the corresponding target return strategy. The visual display interface is sent to the management terminal.

[0113] In this optional embodiment, the visual display interface may also include the first reason for the return data that does not match the corresponding target return strategy, and further, may perform an operation matching the first reason on the return data that does not match the corresponding target return strategy according to the first reason. In this way, by generating a visual display interface and sending the visual display interface to the management terminal, the management personnel can visually know the amount of data that can be returned and the amount of successfully returned data, which is conducive to enabling the management personnel to intuitively understand the situation of data return and to improve the convenience of the management personnel in managing data return.

[0114] It can be seen that the implementation Figure 1The described data feedback method based on multi-platform and multi-data can obtain the feedback data that needs to be returned to the target media platform, match the feedback data with a pre-generated feedback strategy library, and obtain the policy matching result corresponding to the feedback data. When the strategy matching result indicates that the target feedback strategy that matches the feedback data is matched, the feedback data is determined as the target feedback data that needs to be returned to the target media platform through the target feedback strategy, and the target feedback data is returned to the target media platform. This can help improve the efficiency of returning the target feedback data to the target media platform, thereby helping to improve the accuracy of returning the target feedback data to the target media platform, and further help to improve the success rate of returning the target feedback data to the target media platform.

[0115] Embodiment 2

[0116] See also Figure 2 , Figure 2 : is a flow chart of a data return method based on multi-platform and multi-data disclosed in an embodiment of the present invention. Figure 2 The described data return method based on multi-platform multi-data can be applied to a data return device based on multi-platform multi-data, and can also be applied to a cloud server or a local server for data return based on multi-platform multi-data, which is not limited in the embodiments of the present invention. Figure 2 As shown, the data return method based on multi-platform and multi-data may include the following operations:

[0117] 201. Obtain feedback data that needs to be transmitted back to the target media platform.

[0118] 202. According to a plurality of pre-determined backhaul requirements, determine a backhaul strategy corresponding to each backhaul requirement, summarize all backhaul strategies, and obtain a backhaul strategy library.

[0119] In the embodiment of the present invention, the feedback strategy includes one or more of the following: delivery method, strategy name, product category, media platform, operating system, attribution method, strategy effective time period, feedback ratio, and feedback quantity.

[0120] In the embodiment of the present invention, optionally, the return strategy corresponding to each return requirement can be determined automatically according to each return requirement based on a number of pre-determined return requirements; or it can be determined by receiving a return strategy selection instruction issued by a data management personnel, which is not limited in the embodiment of the present invention.

[0121] In the embodiment of the present invention, the return strategy may also include data events and event agreements, wherein the data event may include one or more of an activation event, a registration event, a second stay time, a payment event within 7 days, and an attachment event within 30 days, and the event agreement is other data events that the data event agreement returns to the target media platform.

[0122] In the embodiment of the present invention, further optionally, after determining the return strategy corresponding to each return demand, each return strategy can be uploaded to a pre-set target database, so that the pre-set target database can load the latest strategy into the memory, and can be used to improve and change the strategy to achieve flexible change of strategy control data. This can help improve the efficiency of subsequent matching of return data with the pre-generated return strategy library, thereby helping to improve the efficiency of obtaining target return data, and further can help improve the efficiency of returning the target return data to the target media platform.

[0123] 203. Match the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data.

[0124] 204. When the strategy matching result indicates that a target return strategy matching the return data is matched, the return data is determined as target return data that needs to be returned to the target media platform through the target return strategy.

[0125] 205. Send the target feedback data back to the target media platform.

[0126] In the embodiment of the present invention, for other descriptions of step 201 and step 203 to step 205, please refer to the detailed description of step 101 to step 104 in the first embodiment, and the embodiment of the present invention will not be repeated here.

[0127] It can be seen that implementation Figure 2 The described data feedback method based on multi-platform and multi-data can obtain feedback data that needs to be returned to the target media platform, determine the feedback strategy corresponding to each feedback demand according to a number of predetermined feedback demands, summarize all feedback strategies, obtain a feedback strategy library, match the feedback data with the pre-generated feedback strategy library, and obtain the strategy matching result corresponding to the feedback data. When the strategy matching result indicates that the target feedback strategy that matches the feedback data is matched, the feedback data is determined as the target feedback data that needs to be returned to the target media platform through the target feedback strategy, and the target feedback data is returned to the target media platform. This can help improve the efficiency of returning the target feedback data to the target media platform, thereby helping to improve the accuracy of returning the target feedback data to the target media platform, and further help to improve the success rate of returning the target feedback data to the target media platform.

[0128] In an optional embodiment, before determining the return data as target return data that needs to be returned to the target media platform through the target return strategy, the method further includes:

[0129] Determine whether the target return policy is enabled.

[0130] When it is determined that the state of the target return policy is enabled, it is determined whether the current time is within the effective time period corresponding to the target return policy;

[0131] When it is determined that the current time is within the effective time period corresponding to the target return policy, it is determined whether the target return policy has a return quantity restriction;

[0132] When it is determined that the target return policy has a return quantity limit, it is determined whether the quantity of returned data and to-be-returned data that matches the target return policy is less than or equal to a preset return quantity threshold;

[0133] When it is determined that the number of returned data and data to be returned that match the target return strategy is less than or equal to a preset return quantity threshold, determining whether the returned data meets the return condition that matches the target return strategy;

[0134] When it is determined that the returned data meets the return condition matching the target return strategy, a step of determining the returned data as target return data that needs to be returned to the target media platform through the target return strategy is performed.

[0135] In this optional embodiment, optionally, when it is determined that the state of the target feedback policy is not enabled, the state of the feedback data is changed to the target feedback policy not enabled state, and the feedback data is input into a pre-set database.

[0136] In this optional embodiment, optionally, when it is determined that the current time is not within the effective time period corresponding to the target feedback policy, the state of the feedback data is changed to a state of not being within the effective time period of the target feedback policy, and the feedback data is input into a pre-set database.

[0137] In this optional embodiment, optionally, when it is determined that the target return policy does not have a return quantity limit, an operation of determining whether the return data meets a return condition that matches the target return policy is triggered.

[0138] In this optional embodiment, optionally, when it is determined that the number of returned data and data to be returned that match the target return strategy is greater than a preset return quantity threshold, the state of the returned data is changed to a state greater than the return quantity threshold, and the returned data is input into a preset database. For example, when the preset return quantity threshold of the target return data is 200 and the number of returned data and data to be returned that match the target return data is 1000, the 200 return data that match the target return data are returned to the target media platform. In this way, by judging whether the number of returned data and data to be returned that match the target return strategy is less than or equal to the preset return quantity threshold, it can be helpful to improve the efficiency of returning the returned data to the target media platform, and it can be helpful to improve the accuracy of returning the returned data to the target media platform.

[0139] In this optional embodiment, optionally, judging whether the return data meets the return conditions that match the target return strategy can be judging whether the target return data meets the return ratio. It should be noted that the return ratio is a preset ratio value. For example, when the preset ratio value is 60%, for each return data, a target integer between 0-100 is taken in the return data, and when the target integer is greater than or equal to 60, the return data is returned to the target media platform, but when the target integer is less than 60, the return data is not returned to the target media platform. In this way, by determining the return strategy corresponding to each return demand according to a number of return demands determined in advance, aggregating all return strategies, and obtaining a return strategy library, the accuracy of generating the return strategy library can be improved, which is conducive to improving the accuracy of determining the return data as the target return data that needs to be returned to the target media platform through the target return strategy, and is conducive to improving the accuracy of returning the target return data to the target media platform.

[0140] It can be seen that the implementation of this optional embodiment can determine whether the target return policy has been enabled, determine whether the current moment is within the effective time period corresponding to the target return policy, determine whether the target return policy has a return quantity limit, determine whether the number of returned data and data to be returned that match the target return policy is less than or equal to a preset return quantity threshold, and determine whether the return data meets the return conditions that match the target return policy. When the judgment results of the return data all meet the return conditions, the step of determining the return data as the target return data that needs to be returned to the target media platform through the target return policy is executed. This can help improve the accuracy of returning the return data to the target media platform, and can help improve the success rate of returning the return data to the target media platform.

[0141] In another optional embodiment, the method further comprises:

[0142] When it is determined that the returned data does not meet the return conditions that match the target return strategy, analyze the abnormal reasons why the returned data does not meet the return conditions;

[0143] When the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the return condition, an operation matching the target conversion event is performed on the returned data to obtain corrected data, and the corrected data is determined as the target returned data.

[0144] In this optional embodiment, optionally, performing an operation matching the target conversion event on the returned data may include: performing a modification operation on the returned data according to the target conversion event, converting data in the returned data that does not match the target conversion event into data matching the target conversion event. In this way, by performing an operation matching the target conversion event on the returned data, it is possible to improve the intelligence of analyzing the abnormal reasons why the returned data does not meet the return conditions, and to improve the accuracy of subsequently returning the returned data to the target media platform.

[0145] It can be seen that the implementation of this optional embodiment can analyze the abnormal reason why the returned data does not meet the return conditions when it is determined that the returned data does not meet the return conditions that match the target return policy, and perform operations matching the abnormal reason on the returned data to obtain corrected data, and determine the corrected data as the target return data, which can help improve the intelligence of analyzing the abnormal reason why the returned data does not meet the return conditions, and help improve the accuracy of subsequently returning the returned data to the target media platform.

[0146] In yet another optional embodiment, matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data includes:

[0147] Determine the matching quantity, and determine at least one key information group from all the key information included in the returned data according to the matching quantity, wherein the quantity of key information included in each key information group is the matching quantity;

[0148] For each key information group, a match is performed in the pre-generated return strategy library to obtain a matching result for each key information group;

[0149] Determine whether the matching results of all key information groups indicate that no corresponding return strategy is matched;

[0150] When it is determined that the matching results of all key information groups indicate that no corresponding return strategy is matched, a reduction operation is performed on the matching number according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all key information included in each return data according to the matching number is repeated, and the number of key information included in each key information group is the matching number;

[0151] When it is determined that the matching results of at least two key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all first key information groups that match the corresponding return strategies, and the return strategies that match the target key information group are determined as the strategy matching results corresponding to the return data;

[0152] When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

[0153] In this optional embodiment, for example, the number of matches can be 4. According to the number of matches, at least one key information group with a number of 4 key information is determined from all the key information included in the returned data. For each key information group with a number of 4 key information, a match is performed in the pre-generated return policy library to obtain a matching result for each key information group. When the key information group with a number of 4 key information matches the key information of one of the return policies in the return policy library, it is determined that the key information group matches the return policy. Further optionally, when the matching results of each key information group with a number of 4 key information indicate that the corresponding return policy is not matched, the predetermined number interval can be 1, and then a reduction operation is performed on the number of matches to update the number of matches. The updated number of matches is 3, and the operation of determining at least one key information group from the key information included in each return data according to the number of matches is repeated until a target return policy matching the return data is found or it is determined that there is no target return policy matching the return data. Further optionally, when the number of matches is 2 and the matching result of each key information group indicates that no corresponding feedback strategy is matched, it is determined that there is no target feedback strategy that matches the feedback data.

[0154] In this optional embodiment, optionally, when it is determined that there is no target return policy that matches the return data, the state of the return data is updated to a state of not matching the target return policy, and the return data is input into a pre-set database.

[0155] It can be seen that the implementation of this optional embodiment can determine at least one key information group from all the key information included in the returned data according to the determined number of matches, and for each key information group, match it in a pre-generated return strategy library. When the matching results of all key information groups indicate that there is no match to the corresponding return strategy, a reduction operation is performed on the number of matches. When the matching results of at least two key information groups indicate that the corresponding return strategy is matched, the target key information group is screened out from all the first key information groups that match the corresponding return strategy. When the matching result of only one key information group indicates that the corresponding return strategy is matched, the return strategy that matches the key information group is determined as the strategy matching result corresponding to the return data, which can help improve the accuracy of obtaining the strategy matching result corresponding to the return data, thereby helping to improve the accuracy of subsequent determination of the target return data, and further helping to improve the accuracy of subsequent return of the target return data to the target media platform.

[0156] In yet another optional embodiment, filtering out the target key information group from all first key information groups that match the corresponding return strategy includes:

[0157] For each first key information group that each matching result indicates matches to the corresponding feedback strategy, extract the information keyword of the first key information group and the feedback keyword of the feedback strategy corresponding to the first key information group;

[0158] For each first key information group that the matching result indicates matches the corresponding return strategy, calculate the correlation degree between the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, and obtain the correlation degree corresponding to the first key information group;

[0159] The correlation levels corresponding to each first key information group are summarized, and the first key information group with the highest correlation level is determined as the target key information group.

[0160] In this optional embodiment, the degree of association may be the degree of synonymy between the information keyword and the return keyword. For example, when the number of the first key information group is 2, the information keyword extracted from the first key information group A is "lipstick" and the return keyword of the return strategy corresponding to the first key information group A is "beauty makeup", the information keyword extracted from the first key information group B is "foundation" and the return keyword of the return strategy corresponding to the first key information group B is "skin care", the degree of association between "lipstick" and "beauty makeup" is calculated, and the degree of association between "foundation" and "skin care" is calculated, and the degree of association corresponding to the first key information group A is 0.9, and the degree of association corresponding to the first key information group B is 0.8, and the first key group A is determined as the target key information group.

[0161] It can be seen that the implementation of this optional embodiment can, for each first key information group that matches the corresponding return strategy for each matching result, extract the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, calculate the degree of association between the information keyword and the return keyword, obtain the degree of association corresponding to each first key information group, and determine the first key information group with the highest degree of association as the target key information group, which can help improve the accuracy of determining the target key information group, thereby can help improve the accuracy of determining the target return strategy, and further can help improve the accuracy of returning the target return data to the target media platform.

[0162] In yet another optional embodiment, after obtaining the return data to be returned to the target media platform, the method further includes:

[0163] Determine matching conditions, which include one or more of media platform conditions, advertising event conditions, delivery method conditions, and conversion target conditions;

[0164] Determine whether the returned data meets the matching conditions;

[0165] When it is determined that the returned data meets the matching condition, the operation of matching the returned data with the pre-generated returned policy library to obtain the policy matching result corresponding to the returned data is triggered;

[0166] When it is determined that the returned data does not satisfy the matching condition, the returned data is determined as non-matching data, and the non-matching data is input into the target database.

[0167] In this optional embodiment, the conversion target condition may optionally include one or more of an activation event, a registration event, and a payment event within 7 days.

[0168] In this optional embodiment, further optionally, the matching condition may also include determining whether the returned data is returned data, and when it is determined that the returned data is returned data, changing the state of the returned data to a returned state, and inputting the returned data into a pre-set database; when it is determined that the returned data is not returned data, triggering the execution of an operation of matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data. In this way, by determining whether each returned data is returned data, if so, changing the state of the returned data to a returned state and inputting it into a pre-set database, and if not, matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, it is possible to avoid returning the same returned data to the target media platform, which is beneficial to improving the efficiency of obtaining the policy matching result corresponding to the returned data, thereby facilitating improving the efficiency of determining the target returned data, and further facilitating improving the efficiency of returning the target returned data to the target media platform.

[0169] It can be seen that the implementation of this optional embodiment determines the matching conditions and judges whether the returned data meets the matching conditions. If so, it triggers the execution of matching the returned data with the pre-generated return policy library to obtain the policy matching result corresponding to the returned data. If not, the returned data is determined as non-matching data and the non-matching data is input into the target database. This can reduce the amount of returned data for policy matching in the return policy library, which is beneficial to improving the efficiency of obtaining the policy matching result corresponding to the returned data, thereby helping to improve the efficiency of determining the target returned data, and further helping to improve the efficiency of returning the target returned data to the target media platform.

[0170] Embodiment 3

[0171] See also Figure 3 , Figure 3 Schematic diagram of a device for data transmission based on multiple platforms and multiple data disclosed in an embodiment of the present invention. Figure 3 As shown, the device may include:

[0172] The acquisition module 301 is used to acquire the feedback data that needs to be transmitted back to the target media platform. The target media platform is any media platform that needs to transmit data back. The feedback data is any data among all the feedback data that needs to be transmitted back to the target media platform.

[0173] The matching module 302 is used to match the feedback data with a pre-generated feedback strategy library to obtain a strategy matching result corresponding to the feedback data. The feedback strategy library includes a plurality of feedback strategies.

[0174] The determination module 303 is configured to determine the returned data as target returned data that needs to be returned to the target media platform through the target returned policy when the policy matching result indicates that a target returned policy matching the returned data is matched.

[0175] The feedback module 304 is used to transmit the target feedback data back to the target media platform.

[0176] visible, Figure 3 The described device can obtain feedback data that needs to be returned to the target media platform, match the feedback data with a pre-generated feedback policy library, and obtain a policy matching result corresponding to the feedback data. When the policy matching result indicates that the target feedback policy that matches the feedback data is matched, the feedback data is determined as target feedback data that needs to be returned to the target media platform through the target feedback policy, and the target feedback data is returned to the target media platform. This can help improve the efficiency of returning the target feedback data to the target media platform, thereby helping to improve the accuracy of returning the target feedback data to the target media platform, and further helping to improve the success rate of returning the target feedback data to the target media platform.

[0177] In an optional embodiment, if Figure 4 As shown, the device also includes:

[0178] The determination module 305 is used to determine whether the state of the target return policy is enabled before the determination module 303 determines that the return data is the target return data that needs to be returned to the target media platform through the target return policy.

[0179] The judgment module 305 is further configured to judge whether the current time is within the effective time period corresponding to the target backhaul policy when it is judged that the state of the target backhaul policy is enabled.

[0180] The judgment module 305 is further configured to judge whether the target backhaul policy has a backhaul quantity limit when it is judged that the current moment is within the effective time period corresponding to the target backhaul policy.

[0181] The judgment module 305 is further used to judge whether the quantity of returned data and to-be-returned data that matches the target return policy is less than or equal to a preset return policy threshold when it is judged that the target return policy has a return policy limit.

[0182] The judgment module 305 is further used to judge whether the returned data meets the return conditions matching the target return strategy when it is judged that the number of returned data and data to be returned that match the target return strategy is less than or equal to a preset return quantity threshold.

[0183] The judgment module 305 is also used to trigger the step of determining the return data as target return data that needs to be returned to the target media platform through the target return strategy when it is determined that the return data meets the return conditions that match the target return strategy.

[0184] visible, Figure 4 The described apparatus can help improve the accuracy of transmitting the returned data to the target media platform, and can help improve the success rate of transmitting the returned data to the target media platform.

[0185] In another optional embodiment, Figure 4 As shown, the device also includes:

[0186] The analysis module 306 is used to analyze the abnormal reason why the returned data does not meet the return condition when the judgment module 305 judges that the returned data does not meet the return condition matching the target return policy.

[0187] The execution module 307 is used to execute an operation matching the target conversion event on the returned data to obtain corrected data when the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the returned condition.

[0188] The determination module 303 is further configured to determine the corrected data as target return data.

[0189] visible, Figure 4 The described device can, when it is determined that the returned data does not meet the return conditions that match the target return strategy, analyze the abnormal reasons why the returned data does not meet the return conditions, and perform operations matching the abnormal reasons on the returned data to obtain corrected data, and determine the corrected data as the target return data. This can help improve the intelligence of analyzing the abnormal reasons why the returned data does not meet the return conditions, and help improve the accuracy of subsequently returning the returned data to the target media platform.

[0190] In yet another optional embodiment, Figure 4 As shown, the matching module 302 matches the returned data with the pre-generated returned policy library to obtain the policy matching result corresponding to the returned data in the following manner:

[0191] Determine the matching quantity, and determine at least one key information group from all the key information included in the returned data according to the matching quantity, wherein the quantity of key information included in each key information group is the matching quantity;

[0192] For each key information group, a match is performed in the pre-generated return strategy library to obtain a matching result for each key information group;

[0193] Determine whether the matching results of all key information groups indicate that no corresponding return strategy is matched;

[0194] When it is determined that the matching results of all key information groups indicate that no corresponding return strategy is matched, a reduction operation is performed on the matching number according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all key information included in each return data according to the matching number is repeatedly performed;

[0195] When it is determined that the matching results of at least two key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all first key information groups that match the corresponding return strategies, and the return strategies that match the target key information group are determined as the strategy matching results corresponding to the return data;

[0196] When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

[0197] visible, Figure 4 The described device can help improve the accuracy of obtaining policy matching results corresponding to the feedback data, thereby helping to improve the accuracy of subsequent determination of target feedback data, and further helping to improve the accuracy of subsequent transmission of the target feedback data to the target media platform.

[0198] In yet another optional embodiment, Figure 4 As shown, the matching module 302 selects the target key information group from all first key information groups that match the corresponding return strategy in the following manner:

[0199] For each first key information group that each matching result indicates matches to the corresponding feedback strategy, extract the information keyword of the first key information group and the feedback keyword of the feedback strategy corresponding to the first key information group;

[0200] For each first key information group that the matching result indicates matches the corresponding return strategy, calculate the correlation degree between the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, and obtain the correlation degree corresponding to the first key information group;

[0201] The correlation levels corresponding to each first key information group are summarized, and the first key information group with the highest correlation level is determined as the target key information group.

[0202] visible, Figure 4The described device can help improve the accuracy of determining the target key information group, thereby helping improve the accuracy of determining the target feedback strategy, and further helping improve the accuracy of returning the target feedback data to the target media platform.

[0203] In yet another optional embodiment, Figure 4 As shown, the determination module 303 is also used to determine the return strategy corresponding to each return requirement according to a plurality of return requirements determined in advance before the matching module 302 matches the return data with the pre-generated return strategy library to obtain the strategy matching result corresponding to the return data;

[0204] The device also includes:

[0205] The summary module 308 is used to summarize all feedback strategies to obtain a feedback strategy library, wherein the feedback strategy includes one or more of delivery method, strategy name, product category, media platform, operating system, attribution method, strategy effective time period, feedback ratio, and feedback quantity.

[0206] visible, Figure 4 The described device can determine the return strategy corresponding to each return requirement based on a number of predetermined return requirements, and summarize all return strategies to obtain a return strategy library, which is conducive to improving the efficiency of returning the target return data to the target media platform, thereby helping to improve the accuracy of returning the target return data to the target media platform, and further helping to improve the success rate of returning the target return data to the target media platform.

[0207] In yet another optional embodiment, Figure 4 As shown, the determination module 303 is further used to determine the matching conditions after the acquisition module 301 acquires the return data that needs to be returned to the target media platform, and the matching conditions include one or more of the media platform conditions, the advertising event conditions, the delivery method conditions, and the conversion target conditions;

[0208] The judgment module 305 is also used to judge whether the returned data meets the matching condition;

[0209] The judgment module 305 is further used to trigger the matching module 302 to match the returned data with the pre-generated returned policy library to obtain the policy matching result corresponding to the returned data when it is judged that the returned data meets the matching condition;

[0210] The determination module 303 is further configured to determine the returned data as non-matching data and input the non-matching data into the target database when the determination module 305 determines that the returned data does not meet the matching condition.

[0211] visible, Figure 4The described device can reduce the amount of feedback data that undergoes policy matching in the feedback policy library, which is beneficial to improving the efficiency of obtaining policy matching results corresponding to the feedback data, thereby helping to improve the efficiency of determining target feedback data, and further helping to improve the efficiency of returning the target feedback data to the target media platform.

[0212] Embodiment 4

[0213] See also Figure 5 , Figure 5 1 is a schematic diagram of the structure of another device for data transmission based on multiple platforms and multiple data disclosed in an embodiment of the present invention. Figure 5 As shown, the device for data return based on multi-platform and multi-data may include:

[0214] A memory 401 storing executable program codes;

[0215] a processor 402 coupled to the memory 401;

[0216] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the data return method based on multi-platform and multi-data described in the first embodiment of the present invention or the second embodiment of the present invention.

[0217] Embodiment 5

[0218] An embodiment of the present invention discloses a computer storable medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the data return method based on multi-platform and multi-data described in Embodiment 1 or Embodiment 2 of the present invention.

[0219] Embodiment 6

[0220] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the method for data transmission based on multi-platform and multi-data described in Embodiment 1 or Embodiment 2.

[0221] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0222] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0223] Finally, it should be noted that the data return method and device based on multi-platform and multi-data disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A data return method based on multi-platform and multi-data, characterized in that: The method comprises: Acquire feedback data that needs to be transmitted back to a target media platform, where the target media platform is any media platform that needs to transmit data back, and the feedback data is any data among all feedback data that needs to be transmitted back to the target media platform; Matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, wherein the return policy library includes a plurality of return policies; When the strategy matching result indicates that a target return strategy matching the return data is matched, the return data is determined as target return data that needs to be returned to the target media platform through the target return strategy; Transmitting the target return data back to the target media platform; Before determining the return data as target return data that needs to be returned to the target media platform through the target return strategy, the method further includes: Determine whether the target return policy is enabled. When it is determined that the state of the target return policy is the enabled state, determining whether the current time is within the effective time period corresponding to the target return policy; When it is determined that the current moment is within the effective time period corresponding to the target backhaul policy, it is determined whether the target backhaul policy has a backhaul quantity restriction; When it is determined that the target return policy has the return quantity limit, determining whether the quantity of returned data and to-be-returned data that matches the target return policy is less than or equal to a preset return quantity threshold; When it is determined that the number of returned data and data to be returned that matches the target return strategy is less than or equal to the preset return quantity threshold, determining whether the returned data meets the return condition that matches the target return strategy; When it is determined that the return data meets the return condition that matches the target return strategy, the step of determining the return data as target return data that needs to be returned to the target media platform through the target return strategy is performed; The method further comprises: When it is determined that the returned data does not meet the return condition that matches the target return policy, analyzing the abnormal reason why the returned data does not meet the return condition; When the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the return condition, an operation matching the target conversion event is performed on the returned data to obtain corrected data, and the corrected data is determined as the target returned data; The matching of the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data includes: Determine the matching number, and determine at least one key information group from all the key information included in the returned data according to the matching number, wherein the number of key information included in each key information group is the matching number; For each of the key information groups, matching is performed in a pre-generated return strategy library to obtain a matching result for each of the key information groups; Determining whether the matching results of all the key information groups indicate that no corresponding return strategy is matched; When it is determined that the matching results of all the key information groups indicate that no corresponding return strategy is matched, the matching number is reduced according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all the key information included in each of the return data according to the matching number is repeated; When it is determined that the matching results of at least two of the key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all the first key information groups that match the corresponding return strategies, and the return strategy that matches the target key information group is determined as the strategy matching result corresponding to the return data; When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

2. The data return method based on multi-platform and multi-data according to claim 1, characterized in that: The step of selecting the target key information group from all first key information groups that match the corresponding return strategy includes: For each of the first key information groups that each matching result indicates matches to the corresponding return strategy, extracting the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group; For each of the first key information groups that the matching result indicates matches the corresponding return strategy, calculate the correlation degree between the information keyword of the first key information group and the return keyword of the return strategy corresponding to the first key information group, and obtain the correlation degree corresponding to the first key information group; The correlation levels corresponding to each of the first key information groups are summarized, and the first key information group with the highest correlation level is determined as the target key information group.

3. The data return method based on multi-platform and multi-data according to claim 2, characterized in that: Before matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, the method further includes: According to a number of predetermined feedback requirements, a feedback strategy corresponding to each feedback requirement is determined, and all the feedback strategies are summarized to obtain a feedback strategy library, wherein the feedback strategy includes one or more of delivery method, strategy name, product category, media platform, operating system, attribution method, strategy effective time period, feedback ratio, and feedback quantity.

4. The data return method based on multi-platform and multi-data according to claim 3, characterized in that: After obtaining the return data to be returned to the target media platform, the method further includes: Determine matching conditions, where the matching conditions include one or more of a media platform condition, an advertising event condition, a delivery method condition, and a conversion target condition; Determine whether the returned data meets the matching condition; When it is determined that the returned data meets the matching condition, the operation of matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data is triggered; When it is determined that the returned data does not satisfy the matching condition, the returned data is determined as non-matching data, and the non-matching data is input into the target database.

5. A data return device based on multi-platform and multi-data, characterized in that: The device comprises: An acquisition module, used for acquiring feedback data that needs to be transmitted back to a target media platform, wherein the target media platform is any media platform that needs to transmit data back, and the feedback data is any data among all the feedback data that needs to be transmitted back to the target media platform; A matching module, used for matching the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data, wherein the return policy library includes a plurality of return policies; A determination module, configured to determine the return data as target return data that needs to be returned to the target media platform through the target return strategy when the strategy matching result indicates that a target return strategy matching the return data is matched; A feedback module, used for transmitting the target feedback data back to the target media platform; The device also includes: A judging module, used for judging whether the state of the target return policy is enabled before the determining module determines the return data as target return data that needs to be returned to the target media platform through the target return policy; The determination module is further configured to determine whether the current time is within the effective time period corresponding to the target backhaul policy when it is determined that the state of the target backhaul policy is the enabled state; The judging module is further configured to judge whether there is a limit on the number of returns for the target return policy when it is judged that the current moment is within the effective time period corresponding to the target return policy; The determination module is further configured to determine whether the number of returned data and to-be-returned data that matches the target return strategy is less than or equal to a preset return strategy threshold when it is determined that the target return strategy has the return strategy limit. The judgment module is further configured to judge whether the returned data meets the return condition matching the target return strategy when it is judged that the number of returned data and data to be returned that matches the target return strategy is less than or equal to the preset return quantity threshold; The judging module is further configured to trigger the determining module to execute the step of determining the returned data as target returned data that needs to be returned to the target media platform through the target returned policy when it is determined that the returned data meets the return condition that matches the target returned policy; The device also includes: An analysis module, configured to analyze an abnormal reason why the returned data does not meet the return condition when the judgment module judges that the returned data does not meet the return condition matching the target return policy; An execution module, configured to, when the abnormal reason is used to indicate that the returned data does not meet the target conversion event preset in the return condition, execute an operation matching the target conversion event on the returned data to obtain corrected data; The determination module is further used to determine the corrected data as target return data; The matching module matches the returned data with a pre-generated return policy library to obtain a policy matching result corresponding to the returned data in the following manner: Determine the matching number, and determine at least one key information group from all the key information included in the returned data according to the matching number, wherein the number of key information included in each key information group is the matching number; For each of the key information groups, matching is performed in a pre-generated return strategy library to obtain a matching result for each of the key information groups; Determining whether the matching results of all the key information groups indicate that no corresponding return strategy is matched; When it is determined that the matching results of all the key information groups indicate that no corresponding return strategy is matched, the matching number is reduced according to a predetermined number interval to update the matching number, and the operation of determining at least one key information group from all the key information included in each of the return data according to the matching number is repeated; When it is determined that the matching results of at least two of the key information groups indicate that the corresponding return strategies are matched, a target key information group is selected from all the first key information groups that match the corresponding return strategies, and the return strategy that matches the target key information group is determined as the strategy matching result corresponding to the return data; When it is determined that only one matching result of the key information group indicates that the corresponding return policy is matched, the return policy matching the key information group is determined as the policy matching result corresponding to the return data.

6. A data return device based on multi-platform and multi-data, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the multi-platform and multi-data based data return method as described in any one of claims 1 to 4.

7. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the data return method based on multi-platform and multi-data as described in any one of claims 1-4.

Images