Information pushing method and device, equipment and medium

Abstract

The invention provides an information pushing method and device, equipment and a medium, and relates to the technical field of big data and the like, and the method comprises the steps: determining to-be-pushed candidate information and a pushing number list from an information pushing demand; obtaining an information style of each push number in the push number list so as to obtain target information of each push number based on the candidate information; and obtaining respective target pushing time of the multiple pieces of target information, so as to push the multiple pieces of target information. According to the information pushing method and device, the adaptation degree between the information style and the user preference is improved, the adaptation degree between the information pushing time and the readable information time of the user is improved, the possibility that the user reads the information is improved, the pushing precision of the target information to the user side where the pushing number is located is improved, and the user experience is improved. And the effectiveness of information transmission by taking the target information as a carrier is improved.

Description

Technical Field

[0001] This disclosure relates to the field of big data technology, and in particular to an information push method, apparatus, device, and medium. Background Technology

[0002] With the development of technology, people are becoming increasingly reliant on mobile phones in their work and life. In this context, people can access their favorite items through their mobile phones. Therefore, businesses can target information to people's mobile phones to achieve relevant promotional goals.

[0003] Therefore, it is crucial to accurately deliver information to the mobile devices used by users that are compatible with the information content. Summary of the Invention

[0004] The purpose of this disclosure is to at least partially address one of the technical problems in the aforementioned technologies.

[0005] The first aspect of this disclosure provides an information push method, comprising: determining candidate information to be pushed and a list of push numbers from information push requests; obtaining the information style of each push number in the list of push numbers, so as to obtain target information for each push number based on the candidate information; Obtain the target push time for each of the multiple target information items, and then push the multiple target information items.

[0006] The information push method provided in the first aspect of this disclosure also has the following technical features, including: According to one embodiment of this disclosure, obtaining the information style of each push number in the push number list to obtain target information for each push number based on the candidate information includes: obtaining the target user cluster to which each push number in the push number list belongs; determining the information style of each push number according to the user cluster style of the target user cluster; and for any push number, performing style conversion on the candidate information according to the information style corresponding to the push number to obtain the target information of the push number, wherein the target information is obtained by editing the style and content of the candidate information based on the information style of the push number and the SMS editing conditions carried in the information push requirement through the modeling capabilities of a large language model.

[0007] According to one embodiment of this disclosure, obtaining the target user cluster to which each push number in the push number list belongs includes: determining first communication data and second communication data for each user based on the communication behavior data of each user in the user cluster, wherein the first communication data includes at least the average monthly call cost, average monthly SMS cost, average monthly SMS received volume, and average monthly SMS sent volume included in the communication behavior data, and the second communication data includes at least the average monthly received ratio of resource-distributed SMS, the average monthly sent ratio of personal SMS, the average monthly unsubscription volume of resource-distributed SMS, and the proportion of resource-distributed SMS that can be unsubscribed from the communication behavior data; clustering the user cluster based on the first communication data to obtain multiple group clusters; clustering the users included in each of the multiple group clusters based on the second communication data to obtain multiple user clusters included in each of the multiple group clusters; and determining the target user cluster for each push number from the multiple user clusters.

[0008] According to one embodiment of this disclosure, obtaining the target push time for each of the multiple target information items to push the multiple target information items includes: for any target information item, obtaining multiple push information groups obtained by combining the information style corresponding to the target information item with each of the preset multiple candidate push times; obtaining the push evaluation value of each push information item in the multiple push information groups, and determining the target push time of the target information item from the multiple candidate push times based on the push evaluation value; and pushing the target information item at the target push time.

[0009] According to one embodiment of this disclosure, obtaining the push evaluation value of each push information in the plurality of push information groups and determining the target push time of the target information from the plurality of candidate push times based on the push evaluation value includes: for any target information, obtaining the push evaluation value of each of the plurality of push information groups corresponding to the target information based on the first resource deployment data of the target enterprise cluster to which the demand initiator of the information push request belongs, the first communication data of the target user cluster to which the target information belongs, and the load data of each server cluster, wherein the first resource deployment data is obtained based on the resource deployment behavior data of the target enterprise cluster, and the push evaluation value is obtained based on the evaluation model; in response to any push evaluation value satisfying a set condition, determining the candidate push time in any push evaluation value as the target push time of the target information.

[0010] According to one embodiment of this disclosure, the step of pushing the target information at the target push time includes: determining the push time period to which each target information belongs, and the set of target information to be pushed within each push time period; for any push time period, determining the push order of each target information in the target information set corresponding to the push time period, and the target push number corresponding to each target information in the push number list; and pushing each target information to its corresponding target push number according to the push order.

[0011] According to one embodiment of this disclosure, determining the push order of each target information in the target information set corresponding to any push time period includes: determining the demand initiator corresponding to each target information in the target information set to be pushed within the push time period; determining the push level of each demand initiator; and determining the push order of each target information according to the push level.

[0012] According to one embodiment of this disclosure, determining the push level of each demand initiator and determining the push order of each target information according to the push level includes: for any push time period, determining the target information subset to be pushed by each demand initiator from the target information set corresponding to the push time period, so as to obtain the number of information pushed by each demand initiator in the push time period; and dividing each demand initiator into multiple initiator sets based on the number of information pushed. Determine the collection service level parameters for each of the multiple initiator sets, and determine the collection service order of the multiple initiator sets based on the collection service level parameters; determine the push order of each target information based on the collection service order.

[0013] According to one embodiment of this disclosure, the step of dividing each demand initiator into multiple initiator sets based on the number of information pushes includes: determining the minimum number of information pushes from each number of information pushes; for any number of information pushes, obtaining the ratio between the number of information pushes and the minimum number of information pushes, and determining the push parameters corresponding to the demand initiator for the number of information pushes based on the ratio, wherein the push parameters are obtained by rounding up the ratio; dividing each demand initiator into multiple initiator sets based on the push parameters, wherein the absolute value of the difference between the sum of the push parameters of each initiator included in initiator set i and the sum of the push parameters of each initiator included in initiator set j is less than or equal to a set threshold.

[0014] According to one embodiment of this disclosure, the method further includes: updating the first resource deployment data of each enterprise in the enterprise cluster, the load data of each server cluster, and the first communication data of each user in the user cluster based on a set time interval, so as to push information based on the new first resource deployment data, the new load data, and the new first communication data.

[0015] According to one embodiment of this disclosure, the method further includes: obtaining a corresponding information delivery reward based on the second communication data of users included in each of the multiple user clusters and the second resource delivery data of enterprises included in each of the multiple enterprise clusters; optimizing the evaluation model for obtaining the push evaluation value based on the information delivery reward to obtain an optimized new evaluation model, and pushing information based on the new evaluation model.

[0016] According to one embodiment of this disclosure, obtaining the plurality of enterprise clusters includes: determining first resource deployment data and second resource deployment data for each enterprise based on resource deployment behavior data of each enterprise in the enterprise cluster, wherein the first resource deployment data includes at least business data, business volume level data, average monthly resource deployment cost, and total unsubscription ratio of resource deployment SMS included in the resource deployment behavior data, and the second resource deployment data includes at least the average monthly push volume of SMS, average daily push volume of SMS, average monthly unsubscription volume of resource deployment SMS, and immediate unsubscription ratio of resource deployment SMS included in the resource deployment behavior data; clustering the enterprise clusters based on the first resource deployment data to obtain multiple group clusters; and clustering the enterprises included in the multiple group clusters based on the second resource deployment data to obtain multiple enterprise clusters included in each of the multiple group clusters.

[0017] A second aspect of this disclosure provides an information push device, comprising: a determining module, configured to determine candidate information to be pushed and a list of push numbers from information push requests; an obtaining module, configured to obtain the information style of each push number in the list of push numbers, so as to obtain target information for each push number based on the candidate information; and a pushing module, configured to obtain the target push time for each of the multiple target information, so as to push the multiple target information.

[0018] The information push device provided in the second aspect of this disclosure also has the following technical features, including: According to one embodiment of this disclosure, the acquisition module is further configured to: acquire the target user cluster to which each push number in the push number list belongs; determine the information style of each push number according to the user cluster style of the target user cluster; and for any push number, perform style conversion on the candidate information according to the information style corresponding to the push number to obtain the target information of the push number, wherein the target information is obtained by editing the style and content of the candidate information based on the information style of the push number and the SMS editing conditions carried in the information push requirements through the model capabilities of a large language model.

[0019] According to one embodiment of this disclosure, the acquisition module is further configured to: determine first communication data and second communication data for each user based on the communication behavior data of each user in the user cluster, wherein the first communication data includes at least the average monthly call cost, average monthly SMS cost, average monthly SMS reception volume, and average monthly SMS sending volume included in the communication behavior data, and the second communication data includes at least the average monthly reception ratio of resource-distributed SMS, the average monthly sending ratio of personal SMS, the average monthly unsubscription volume of resource-distributed SMS, and the proportion of resource-distributed SMS that can be unsubscribed from the communication behavior data; cluster the user cluster based on the first communication data to obtain multiple group clusters; cluster the users included in each of the multiple group clusters based on the second communication data to obtain multiple user clusters included in each of the multiple group clusters; and determine the target user cluster for each push number from the multiple user clusters.

[0020] According to one embodiment of this disclosure, the push module is further configured to: for any target information, obtain multiple push information groups obtained by combining the information style corresponding to the target information with each of the preset multiple candidate push times; obtain the push evaluation value of each push information in the multiple push information groups, and determine the target push time of the target information from the multiple candidate push times based on the push evaluation value; and push the target information at the target push time.

[0021] According to one embodiment of this disclosure, the push module is further configured to: for any target information, based on the first resource deployment data of the target enterprise cluster to which the demand initiator of the information push request belongs, the first communication data of the target user cluster to which the target information belongs, and the load data of each of the server clusters, obtain the push evaluation value of each of the plurality of push information groups corresponding to the target information, wherein the first resource deployment data is obtained based on the resource deployment behavior data of the target enterprise cluster, and the push evaluation value is obtained based on the evaluation model; in response to any push evaluation value satisfying a set condition, determine the candidate push time in any push evaluation value as the target push time of the target information.

[0022] According to one embodiment of this disclosure, the push module is further configured to: determine the push time period to which each target information belongs, and the set of target information to be pushed within each push time period; for any push time period, determine the push order of each target information in the target information set corresponding to the push time period, and the target push number corresponding to each target information in the push number list; and push each target information to its corresponding target push number according to the push order.

[0023] According to one embodiment of this disclosure, the push module is further configured to: for any push time period, determine the demand initiator corresponding to each target information in the target information set to be pushed within the push time period; determine the push level of each demand initiator, and determine the push order of each target information according to the push level.

[0024] According to one embodiment of this disclosure, the push module is further configured to: for any push time period, determine a subset of target information to be pushed by each request initiator from the target information set corresponding to the push time period, so as to obtain the number of information pushed by each request initiator within the push time period; divide each request initiator into multiple initiator sets based on the number of information pushed; determine the set service level parameters of each of the multiple initiator sets, and determine the set service order of the multiple initiator sets according to the set service level parameters; and determine the push order of each target information according to the set service order.

[0025] According to one embodiment of this disclosure, the push module is further configured to: determine the minimum number of information pushes from the various information push quantities; for any information push quantity, obtain the ratio between the information push quantity and the minimum information push quantity, and determine the push parameters corresponding to the request initiator corresponding to the information push quantity based on the ratio, wherein the push parameters are obtained by rounding up the ratio; and divide each request initiator into multiple sets based on the push parameters to obtain multiple sets of initiators, wherein the absolute value of the difference between the sum of the push parameters of each initiator included in the multiple sets of initiators i and the sum of the push parameters of each initiator included in the sets of initiators j is less than or equal to a set threshold.

[0026] According to one embodiment of this disclosure, the push module is further configured to: update the first resource deployment data of each enterprise in the enterprise cluster, the load data of each server cluster, and the first communication data of each user in the user cluster based on a set time interval, so as to push information based on the new first resource deployment data, the new load data, and the new first communication data.

[0027] According to one embodiment of this disclosure, the apparatus further includes an optimization module, configured to: obtain a corresponding information delivery reward based on the second communication data of users included in each of the multiple user clusters and the second resource delivery data of enterprises included in each of the multiple enterprise clusters; optimize the evaluation model for obtaining the push evaluation value based on the information delivery reward to obtain an optimized new evaluation model, and push information based on the new evaluation model.

[0028] According to one embodiment of this disclosure, the optimization module is further configured to: determine first resource deployment data and second resource deployment data for each enterprise based on resource deployment behavior data of each enterprise in the enterprise cluster, wherein the first resource deployment data includes at least business data, business volume level data, average monthly resource deployment cost, and total unsubscription ratio of resource deployment SMS included in the resource deployment behavior data, and the second resource deployment data includes at least the average monthly push volume of SMS, average daily push volume of SMS, average monthly unsubscription volume of resource deployment SMS, and immediate unsubscription ratio of resource deployment SMS included in the resource deployment behavior data; cluster the enterprise cluster based on the first resource deployment data to obtain multiple group clusters; and cluster the enterprises included in the multiple group clusters based on the second resource deployment data to obtain multiple enterprise clusters included in each of the multiple group clusters.

[0029] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, including: a memory and a processor; wherein the processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the information push method provided in the first aspect of this disclosure.

[0030] To achieve the above objectives, a fourth aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the information push method provided in the first aspect of this disclosure.

[0031] To achieve the above objectives, the fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, is used to implement the information push method provided in the first aspect of this disclosure.

[0032] The information push method and apparatus disclosed herein determine a list of candidate information push numbers based on the information push requirements provided by the enterprise, and transform the candidate information based on the information style of each push number in the push number list to obtain the target information. This improves the adaptability between information style and user preferences. Based on the target information's target push time, the target information is pushed to its corresponding push number, improving the adaptability between the information push time and the user's available reading time, increasing the likelihood of the user reading the information, improving the accuracy of pushing the target information to the user's terminal where the push number is located, improving the effectiveness of information transmission using the target information as a carrier, optimizing the user's information reading experience, and optimizing the user's information push experience on mobile devices.

[0033] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0034] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which: Figure 1 This is a schematic diagram of an information push method according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of an information push method according to another embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an information push device according to an embodiment of the present disclosure; Figure 4 This is a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0035] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0036] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of relevant laws and regulations.

[0037] The information push method, apparatus, device, and medium of this disclosure are described below with reference to the accompanying drawings.

[0038] Figure 1 This is a flowchart illustrating an embodiment of the information push method disclosed herein, as follows: Figure 1 As shown, the method includes: S101, determine the candidate information to be pushed and the list of push numbers from the information push request.

[0039] In this embodiment of the disclosure, when people use a communication terminal, they may receive relevant text messages from relevant organizations. These organizations may include for-profit enterprises or non-profit entities, and no specific limitation is made here.

[0040] In this scenario, organizations that need to push SMS content to people's communication terminals can use an SMS push platform to send the SMS content they want to push to some communication terminals. The platform can receive a request information carrying the SMS content that the relevant organization wants to push and the relevant information of the communication terminal to which the SMS content is to be pushed. The platform can identify the request information as an information push request, identify the SMS content to be pushed carried in the information push request as candidate information, and identify the communication terminal number to which the candidate information is to be pushed as the push number, thereby obtaining a push number list composed of multiple push numbers.

[0041] S102, obtain the information style of each push number in the push number list, so as to obtain the target information of each push number based on the candidate information.

[0042] In this embodiment of the disclosure, users under each push number may have their own way of expressing their preferences, and the way of expressing the preferences of users under each push number can be determined as the information style of user preferences under each push number.

[0043] In this scenario, the information content of candidate information can be obtained, and the expression style of the information content can be transformed based on the information style preferred by users under any push number, so as to obtain the transformed information that matches the information style preferred by users under that push number. This information can be determined as the target information to be pushed to that push number.

[0044] It should be noted that the information style preferred by users under each push number in the push number list may differ. In this scenario, the expression style of the candidate information can be transformed based on the information style of each push number, thereby obtaining the target information corresponding to each push number.

[0045] S103, obtain the target push time of each of the multiple target information, so as to push the multiple target information.

[0046] In this embodiment of the disclosure, the time when users read SMS messages for each push number in the push number list may differ. In this scenario, the user's habitual SMS viewing time for any push number can be obtained, and the push time of the target information corresponding to the push number can be determined based on the viewing time. The push time can be determined as the target push time corresponding to the target information.

[0047] Optionally, after determining the target push time for each push number, the target information can be pushed to each push number in batches based on the target push time.

[0048] The information push method proposed in this disclosure determines a list of candidate information push numbers based on the information push requirements provided by the enterprise, and transforms the candidate information based on the information style of each push number in the list to obtain the target information. This improves the fit between information style and user preferences. Based on the target information's target push time, the target information is pushed to its corresponding push number, improving the fit between the information push time and the user's available reading time, increasing the likelihood of the user reading the information, improving the accuracy of pushing the target information to the user's terminal with the push number, improving the effectiveness of information transmission using the target information as a carrier, optimizing the user's information reading experience, and optimizing the user's information push experience on mobile devices.

[0049] In the above embodiments, the acquisition and push of target information can also be combined with Figure 2 understand, Figure 2 This is a flowchart illustrating another embodiment of the information push method disclosed herein, as shown below. Figure 2 As shown, the method includes: S201, retrieve the target user cluster to which each push number in the push number list belongs.

[0050] Optionally, the first communication data and the second communication data of each user can be determined based on the communication behavior data of each user in the user cluster.

[0051] In this embodiment of the disclosure, the behavioral description data of each user in the user cluster when communicating can be determined as the communication behavior data of each user. The communication behavior data of any user can be classified according to a preset communication behavior data classification method. The relevant data of each user's SMS and calls each month can be determined as the first communication data. The first communication data includes at least the monthly average call cost, monthly average SMS cost, monthly average SMS received volume, and monthly SMS sent volume included in the communication behavior data.

[0052] In addition, relevant data on SMS messages sent by relevant organizations are filtered out from the user's communication behavior data, and this part of the data is determined as the user's second communication data. The second communication data includes at least the monthly average reception ratio of resource-distributed SMS messages, the monthly average sending ratio of personal SMS messages, the monthly average unsubscription volume of resource-distributed SMS messages, and the proportion of resource-distributed SMS messages that can be unsubscribed from the communication behavior data.

[0053] Optionally, the user cluster can be clustered based on the first communication data to obtain multiple user groups.

[0054] In this embodiment of the disclosure, a cluster of users registered on a platform capable of sending SMS messages can be defined as a user cluster.

[0055] In this scenario, clustering algorithms in related technologies can be used to cluster the user clusters on the SMS delivery platform, with each data item included in the first communication data as the cluster center, and the multiple clusters obtained from the clustering can be determined as multiple group clusters.

[0056] Optionally, based on the second communication data, the users included in each of the multiple group clusters are clustered to obtain multiple user clusters included in each of the multiple group clusters.

[0057] In this embodiment of the disclosure, for any group cluster, the users included in any group cluster can be clustered based on each data item included in the second communication data using a clustering algorithm in the related technology, and the multiple clusters obtained by clustering under the group cluster are determined as multiple user clusters included under the group cluster.

[0058] Optionally, the target user group for each push number can be determined from multiple user groups.

[0059] In this embodiment of the disclosure, for any push number, the user cluster to which the push number belongs can be obtained from the multiple user clusters included in each of the multiple group clusters, and the user cluster can be determined as the target user cluster of the push number.

[0060] S202, determine the information style of each push number based on the user cluster style of the target user cluster.

[0061] In this embodiment of the disclosure, for any target user cluster, the users within the cluster include a set preference expression style, which can be determined as the user cluster style of the target user cluster.

[0062] In this scenario, the user cluster style of each push number's target user group can be obtained, and each user cluster style can be determined as the information style preferred by the users of each push number.

[0063] S203: For any push number, perform style conversion on the candidate information according to the information style corresponding to the push number to obtain the target information of the push number.

[0064] The target information is obtained by editing the style and content of candidate information based on the information style of the push number and the SMS editing conditions carried in the information push requirements through the model capabilities of the large language model.

[0065] In this embodiment of the disclosure, the information push request carries preset SMS editing conditions, which may include editing conditions under the dimension of word count and editing conditions under the dimension of character avoidance, etc., without being specifically limited here.

[0066] In this scenario, the capabilities of a large language model can be invoked to perform style conversion on candidate information based on any information style, and to edit the SMS content of candidate information based on SMS editing conditions. Then, the information after style conversion and content editing is determined as the target information for push numbers that prefer that information style.

[0067] S204, for any target information, obtain multiple push information groups obtained by combining the information style corresponding to the target information with each of the preset multiple candidate push times.

[0068] In this embodiment of the disclosure, each push number may have its own preferred information push time for its users. In this scenario, multiple preset push times can be obtained, and the push time for pushing the target information to its corresponding push number can be selected from them.

[0069] In this scenario, multiple preset push times can be defined as multiple candidate push times. The information style of any target information can be combined with each time in the multiple candidate push times to obtain multiple combinations of each candidate push time and information style. These multiple combinations can be defined as multiple push information groups.

[0070] S205, obtain the push evaluation value of each push message in multiple push message groups, and determine the target push time of the target message from multiple candidate push times based on the push evaluation value.

[0071] Optionally, for any target information, based on the first resource deployment data of the target enterprise cluster to which the information push request originates, the first communication data of the target user cluster to which the target information belongs, and the load data of each server cluster, the push evaluation values ​​of multiple push information groups corresponding to the target information are obtained. The first resource deployment data is obtained based on the resource deployment behavior data of the target enterprise cluster, and the push evaluation values ​​are obtained based on the evaluation model.

[0072] As an example, the push evaluation values ​​of multiple push information groups can be obtained through a pre-acquired push evaluation model. Specifically, the first resource deployment data of the target enterprise cluster corresponding to any target information, the first communication data of the target user cluster to which the target information belongs, and the load data of each server cluster can be input into the trained push evaluation model. Based on the data input to the model, the push evaluation values ​​of multiple push information groups corresponding to the target information can be obtained through the model capabilities of the push evaluation model.

[0073] The primary resource allocation data for the target enterprise cluster can include, at a minimum, relevant data such as the main business, business volume level, average monthly marketing expenses, and total unsubscribe rate of marketing SMS messages for the enterprises included in the target enterprise cluster.

[0074] Furthermore, the first communication data of the target user cluster to which the target information belongs may include at least the average monthly communication cost, average monthly SMS cost, average monthly SMS received volume, average monthly percentage of marketing SMS received, average monthly SMS sent volume, average monthly percentage of non-marketing SMS sent to natural persons, average monthly unsubscribe volume of marketing SMS, and unsubscribe ratio of marketing SMS within a set time after receiving the marketing SMS. The set time may be 5 minutes or other set times, which are not specifically limited here.

[0075] In addition, the load data for each server cluster can include at least the computing power utilization, central processing unit (CPU) utilization, and memory utilization of the servers included in the server cluster.

[0076] It should be noted that the push evaluation model proposed in this embodiment can be a model built based on a CNN network in related technologies, a model built based on an RNN network in related technologies, or a model built based on other networks, and no specific limitation is made here.

[0077] Optionally, in response to any push evaluation value satisfying the set conditions, the candidate push time in any push evaluation value is determined as the target push time of the target information.

[0078] In some implementations, the push evaluation values ​​of multiple push information groups can be sorted in descending order to select the push evaluation value with the highest value from the multiple push evaluation values ​​and determine it as the push evaluation value that meets the set conditions.

[0079] In this embodiment of the disclosure, after obtaining a push evaluation value that meets the set conditions, the candidate push time included in the push information group corresponding to the push evaluation value can be determined as the target push time of the target information.

[0080] S206, push target information at the target push time.

[0081] Optionally, the target push time of each target information is determined to be the push time period to which it belongs, and the set of target information to be pushed within each push time period.

[0082] In this embodiment of the disclosure, the server has a preset push time period for the target information. That is, after determining the target push time, the server can send the target information within the push time period to which the target push time belongs.

[0083] In this scenario, the target push time of each target information can be determined from the pre-divided time periods, and the target information corresponding to the target push time of each time period can be statistically analyzed to obtain at least one target information that needs to be sent in each time period, so as to obtain the target information set in each time period.

[0084] Optionally, for any push time period, determine the push order of each target information in the target information set corresponding to the push time period, and the target push number corresponding to each target information in the push number list.

[0085] In this embodiment of the disclosure, for any push time period, the sending order of each target information in the target information set within the push time period can be obtained based on a preset method for determining the information sending order, and used as the push order of each target information.

[0086] As one possible implementation, for any push time period, the request initiator corresponding to each target information in the set of target information to be pushed within the push time period is determined, the push level of each request initiator is determined, and the push order of each target information is determined according to the push level.

[0087] In this embodiment of the disclosure, for any push time period, the request initiator corresponding to each target information can be determined based on the information push request corresponding to each target information in the target information set that needs to be pushed within that time period.

[0088] In this embodiment of the disclosure, the server is configured with the service levels of each enterprise. In this scenario, the service level of the request initiator corresponding to each target information can be determined from the service level records stored in advance on the server, and the push level of the request initiator corresponding to each target information can be determined based on the service level.

[0089] Optionally, for any push time period, a subset of target information to be pushed by each request initiator is determined from the target information set corresponding to the push time period, so as to obtain the number of information pushed by each request initiator within the push time period. Based on the number of information pushed, each request initiator is divided into sets to obtain multiple initiator sets.

[0090] In this embodiment of the disclosure, the information that each information push request initiator needs to send can be determined from the target information set under any push time period, so as to obtain the target information subset that each information push request initiator needs to push information under the push time period.

[0091] This allows us to obtain the number of information items in each target information subset and, based on that number, determine the number of information items that the request initiator of each information push request needs to send on the server within the current push period.

[0092] In this scenario, the request initiators can be divided into sets based on the number of information pushes. At least one request initiator that meets the set conditions can be divided into the same set, thus obtaining multiple sets after division, which can be used as multiple initiator sets.

[0093] The process of obtaining multiple sets of initiators can also be understood in conjunction with the following: Optionally, from the various information push quantities, the minimum number of information pushes is determined. For any information push quantity, the ratio between the information push quantity and the minimum number of information pushes is obtained. Based on the ratio, the push parameters corresponding to the request initiator for the information push quantity are determined, wherein the push parameters are obtained by rounding up the ratio.

[0094] In this embodiment of the disclosure, for any push time period, the number of information pushes that each request initiator needs to send on the server can be compared and sorted to determine the minimum number of information pushes. In this scenario, an algorithm can be used to process the ratio between the number of information pushes by each request initiator and the minimum number of information pushes to obtain the ratio between the number of information pushes by each request initiator and the minimum number of information pushes.

[0095] In this case, the ratio of the number of each demand initiator obtained by the above method may not be an integer. In this scenario, the ratio of the number of each demand initiator can be rounded down, and the integer value obtained after rounding can be determined as the push parameter corresponding to each demand initiator.

[0096] As an example, let the minimum number of information pushes be represented as MinNum_1, and the number of information pushes by any request initiator be represented as Num_1. Then, we can obtain the ratio M between Num_1 and MinNum_1, and round up the ratio M. The resulting integer can be represented as Ceil(M). Ceil(M) can be used to determine the push parameter corresponding to any request initiator mentioned in this example.

[0097] Here, Num_1 can be used as the denominator and MinNum_1 as the numerator to obtain the corresponding ratio M.

[0098] Optionally, the request initiators are divided into multiple sets based on the push parameters, wherein the absolute value of the difference between the sum of the push parameters of each initiator included in initiator set i and the sum of the push parameters of each initiator included in initiator set j is less than or equal to a set threshold.

[0099] In this embodiment of the disclosure, a set partitioning strategy can be used to partition the request initiators that send information on the same server within any push time period based on push parameters. For the two partitioned initiator sets i and j, the sum of the push parameters of each initiator in set i can be denoted as SUM(Ceil(M))_i, and the sum of the push parameters of each initiator in set j can be denoted as SUM(Ceil(M))_j. In this scenario, the absolute value of the difference between SUM(Ceil(M))_i and SUM(Ceil(M))_j needs to be less than or equal to a set threshold.

[0100] In other words, after dividing the demand initiators into sets, any two sets among the multiple sets of demand initiators obtained from the division must satisfy the relationship between the initiator set i and the initiator set j mentioned above.

[0101] In this scenario, any set that satisfies the relationship between any two sets i and j can be identified as the multiple sets of initiators after partitioning.

[0102] Optionally, the service level parameters of each of the multiple initiator sets are determined, and the service level order of the multiple initiator sets is determined according to the service level parameters. The push order of each target information is determined according to the service level order.

[0103] In this embodiment of the disclosure, the service level of the initiators included in each of the multiple initiator sets can be obtained from the service level record information pre-stored on the server. For any initiator set, the corresponding parameters of the service level of each service initiator included in the set can be summed to obtain the service level parameters and values ​​of the initiators included in each of the multiple initiator sets.

[0104] In this scenario, the variance of each service level parameter and value can be calculated separately to obtain the variance of the service level parameters and values ​​of multiple initiator sets, and this variance can be determined as the set service level parameter of each of the multiple initiator sets.

[0105] In this embodiment of the disclosure, the service level parameters of each set can be sorted in descending order of numerical value to sort the initiator sets corresponding to each service level parameter of the set, thereby obtaining multiple sorted initiator sets, and the sorting of multiple initiator sets in the current scenario is determined as the service level sorting of multiple initiator sets.

[0106] In this embodiment of the disclosure, after determining the service order of multiple initiator sets, the target information subsets of each of the multiple initiator sets can be sorted based on the order, thereby obtaining the order of target information that needs to be sent within the push time period. This order can then be determined as the push order of each target information.

[0107] In this embodiment of the disclosure, for any target information, the number to be pushed to the target information can be determined from the list of push numbers based on the information push requirements corresponding to the target information, and thus determined as the target push number of the target information.

[0108] Optionally, each target message can be pushed to its corresponding target push number in the order of push.

[0109] In this embodiment of the disclosure, after determining the push order of each target information, each target information can be pushed to its corresponding target push number in sequence within the push time period to which its target push time belongs.

[0110] It should be noted that during the daily operation of enterprises and the daily lives of users, the relevant data of enterprises, users, and servers will change to some extent. In this scenario, the first resource deployment data of each enterprise in the enterprise cluster, the load data of each server cluster, and the first communication data of each user in the user cluster can be updated at set time intervals to push information based on the new first resource deployment data, the new load data, and the new first communication data.

[0111] In this embodiment of the disclosure, relevant data of enterprises, users and servers can be obtained based on a set time interval, and the data required by enterprises, users and servers when pushing information can be updated based on the obtained relevant data.

[0112] Specifically, it can update the enterprise's first resource deployment data, update the load data of each server in the server cluster, and update the first communication data of each user in the user cluster. Then, based on the updated first resource deployment data, updated load data, and updated first communication data, it can calculate relevant data for subsequent information push tasks and execute subsequent information push tasks.

[0113] It should be noted that the push evaluation model for obtaining push evaluation values ​​proposed in this embodiment may require model optimization. Specifically, the corresponding information delivery reward can be obtained based on the second communication data of users included in multiple user clusters and the second resource delivery data of enterprises included in multiple enterprise clusters. The evaluation model for obtaining push evaluation values ​​can be optimized based on the information delivery reward to obtain a new optimized evaluation model, and information push can be performed based on the new evaluation model.

[0114] In other words, based on a set time interval, relevant data such as the monthly average percentage of marketing SMS messages received by users in each user cluster, the monthly average percentage of non-marketing SMS messages sent by natural persons, the monthly average number of marketing SMS messages unsubscribed, and the percentage of marketing SMS messages unsubscribed within a set time period can be obtained as the user's second communication data. The set time period can be 5 minutes or other durations, and there is no specific limitation here.

[0115] Additionally, data such as the average monthly SMS volume, average daily SMS volume, average monthly unsubscription volume of marketing SMS messages, and the proportion of marketing SMS messages unsubscribed by users within a set time after receipt are used as secondary resource delivery data for each enterprise cluster. The set time can be 5 minutes or other durations, and no specific limitation is made here.

[0116] In this scenario, the reward acquisition algorithm corresponding to the push evaluation model can be used to process the second communication data of users in multiple user clusters and the second resource delivery data of enterprises in multiple enterprise clusters. Then, the reward value required for optimizing the push evaluation model can be obtained based on the result of the algorithm processing. This reward value can be determined as the information delivery reward.

[0117] As an example, the acquisition of information delivery rewards can be understood using the following formula:

[0118] In the above formula, Com is the communication score before the SMS is sent, Com' is the communication score after the SMS is sent, Mar is the marketing score before the SMS is sent, Mar' is the marketing score after the SMS is sent, and α, β, and γ are all constants. That is to say, the second communication data and the second resource delivery data can be processed by the algorithm based on the preset algorithm corresponding to the push evaluation model to obtain the communication scores and marketing scores required in the above algorithm formula, and then the information delivery reward required for the model optimization of the push evaluation model can be obtained based on the above algorithm formula.

[0119] In this embodiment of the disclosure, the model parameters of the push evaluation model can be iterated and optimized based on the obtained information delivery reward by using the model parameter optimization method in the related technology, and the optimized model that meets the model optimization termination condition is determined as the optimized new push evaluation model.

[0120] In this scenario, subsequent information push tasks can be executed based on the new push evaluation model.

[0121] In this embodiment of the disclosure, the acquisition of the multiple enterprise clusters mentioned above can be understood in conjunction with the following: Optionally, based on the resource deployment behavior data of each enterprise in the enterprise cluster, the first resource deployment data and the second resource deployment data of each enterprise are determined. The first resource deployment data includes at least the business data, business volume level data, monthly average resource deployment cost, and total unsubscription ratio of resource deployment SMS included in the resource deployment behavior data. The second resource deployment data includes at least the monthly average number of SMS pushed, the daily average number of SMS pushed, the monthly average number of unsubscriptions of resource deployment SMS, and the immediate unsubscription ratio of resource deployment SMS included in the resource deployment behavior data.

[0122] Optionally, the enterprise clusters can be clustered based on the first resource allocation data to obtain multiple group clusters.

[0123] In this embodiment of the disclosure, the first resource deployment data of each enterprise in the enterprise cluster can be obtained, and the enterprises in the enterprise cluster can be clustered based on the first resource deployment data using a clustering algorithm in related technologies to obtain multiple clusters, which can be identified as multiple group clusters.

[0124] Optionally, the enterprises included in multiple group clusters can be clustered based on the second resource allocation data to obtain multiple enterprise clusters included in each of the multiple group clusters.

[0125] In this embodiment of the disclosure, for any group cluster, the second resource deployment data of each enterprise in the group cluster can be obtained. Through the clustering algorithm in the related technology, the second resource deployment data of each enterprise is used to process the clustering algorithm for each enterprise included in the group cluster, and multiple clusters included in the group cluster are obtained. These multiple clusters can be determined as multiple enterprise clusters included in the group cluster.

[0126] It should be noted that the clustering methods used in the acquisition process of the above-mentioned group clusters, enterprise clusters and user clusters can be based on the K-means clustering algorithm in related technologies, or on the Partitioning Around Medoids (PAM) algorithm in related technologies, or on other clustering algorithms. No specific limitation is made here.

[0127] The information push method proposed in this disclosure determines a list of candidate information push numbers based on the information push requirements provided by the enterprise, and transforms the candidate information based on the information style of each push number in the list to obtain the target information. This improves the fit between information style and user preferences. Based on the target information's target push time, the target information is pushed to its corresponding push number, improving the fit between the information push time and the user's available reading time, increasing the likelihood of the user reading the information, improving the accuracy of pushing the target information to the user's terminal with the push number, improving the effectiveness of information transmission using the target information as a carrier, optimizing the user's information reading experience, and optimizing the user's information push experience on mobile devices.

[0128] Corresponding to the information push methods provided in the above embodiments, an embodiment of this disclosure also provides an information push device. Since the information push device provided in this disclosure corresponds to the information push methods provided in the above embodiments, the implementation methods of the above information push methods are also applicable to the information push device provided in this disclosure, and will not be described in detail in the following embodiments.

[0129] Figure 3 This is a schematic diagram of the structure of an information push device according to an embodiment of the present disclosure, as shown below. Figure 3 As shown, the information push device 300 includes a determining module 31, an acquiring module 32, and a pushing module 33, wherein: The determination module 31 is used to determine the candidate information to be pushed and the list of push numbers from the information push requirements; The acquisition module 32 is used to acquire the information style of each push number in the push number list, so as to obtain the target information of each push number based on the candidate information; The push module 33 is used to obtain the target push time of each of the multiple target information, so as to push the multiple target information.

[0130] In this embodiment of the disclosure, the acquisition module 32 is further configured to: acquire the target user cluster to which each push number belongs in the push number list; determine the information style of each push number according to the user cluster style of the target user cluster; and for any push number, perform style conversion on the candidate information according to the information style corresponding to the push number to obtain the target information of the push number, wherein the target information is obtained by editing the style and content of the candidate information based on the information style of the push number and the SMS editing conditions carried in the information push requirements through the model capabilities of the large language model.

[0131] In this embodiment of the disclosure, the acquisition module 32 is further configured to: determine the first communication data and the second communication data of each user based on the communication behavior data of each user in the user cluster, wherein the first communication data includes at least the monthly average call cost, monthly average SMS cost, monthly average SMS reception volume, and monthly SMS sending volume included in the communication behavior data, and the second communication data includes at least the monthly average reception ratio of resource delivery SMS, monthly SMS sending ratio of personal SMS, monthly average unsubscription volume of resource delivery SMS, and the proportion of resource delivery SMS that can be unsubscribed from the communication behavior data; cluster the user cluster based on the first communication data to obtain multiple group clusters; cluster the users included in each of the multiple group clusters based on the second communication data to obtain multiple user clusters included in each of the multiple group clusters; and determine the target user cluster of each push number from the multiple user clusters.

[0132] In this embodiment of the disclosure, the push module 33 is further configured to: for any target information, obtain multiple push information groups obtained by combining the information style corresponding to the target information with each of the preset multiple candidate push times; obtain the push evaluation value of each push information in the multiple push information groups, and determine the target push time of the target information from the multiple candidate push times based on the push evaluation value; and push the target information at the target push time.

[0133] In this embodiment of the disclosure, the push module 33 is further configured to: for any target information, based on the first resource deployment data of the target enterprise cluster to which the information push request initiator belongs, the first communication data of the target user cluster to which the target information belongs, and the load data of each server cluster, obtain push evaluation values ​​for each of the multiple push information groups corresponding to the target information, wherein the first resource deployment data is obtained based on the resource deployment behavior data of the target enterprise cluster, and the push evaluation value is obtained based on the evaluation model; in response to any push evaluation value satisfying the set conditions, determine the candidate push time in any push evaluation value as the target push time of the target information.

[0134] In this embodiment of the disclosure, the push module 33 is further configured to: determine the push time period to which each target information belongs, and the set of target information to be pushed within each push time period; for any push time period, determine the push order of each target information in the target information set corresponding to the push time period, and the target push number corresponding to each target information in the push number list; and push each target information to its corresponding target push number according to the push order.

[0135] In this embodiment of the disclosure, the push module 33 is further configured to: for any push time period, determine the demand initiator corresponding to each target information in the target information set to be pushed within the push time period; determine the push level of each demand initiator, and determine the push order of each target information according to the push level.

[0136] In this embodiment of the disclosure, the push module 33 is further configured to: for any push time period, determine the subset of target information to be pushed by each request initiator from the target information set corresponding to the push time period, so as to obtain the number of information pushed by each request initiator within the push time period; divide each request initiator into multiple initiator sets based on the number of information pushed; determine the set service level parameters of each of the multiple initiator sets, and determine the set service order of the multiple initiator sets according to the set service level parameters; and determine the push order of each target information according to the set service order.

[0137] In this embodiment of the disclosure, the push module 33 is further configured to: determine the minimum number of information pushes from the various information push quantities; for any information push quantity, obtain the ratio between the information push quantity and the minimum information push quantity, and determine the push parameters corresponding to the request initiator corresponding to the information push quantity based on the ratio, wherein the push parameters are obtained by rounding up the ratio; divide each request initiator into multiple initiator sets based on the push parameters, wherein the absolute value of the difference between the sum of the push parameters of each initiator included in the initiator set i and the sum of the push parameters of each initiator included in the initiator set j is less than or equal to a set threshold.

[0138] In this embodiment of the disclosure, the push module 33 is further configured to: update the first resource deployment data of each enterprise in the enterprise cluster, the load data of each server cluster, and the first communication data of each user in the user cluster based on a set time interval, so as to push information based on the new first resource deployment data, the new load data, and the new first communication data.

[0139] In this embodiment of the present disclosure, the device further includes an optimization module, configured to: obtain corresponding information delivery rewards based on the second communication data of users included in each of the multiple user clusters and the second resource delivery data of enterprises included in each of the multiple enterprise clusters; optimize the evaluation model for obtaining the push evaluation value based on the information delivery rewards to obtain an optimized new evaluation model, and push information based on the new evaluation model.

[0140] In this embodiment of the disclosure, the optimization module is further configured to: determine the first resource deployment data and the second resource deployment data for each enterprise based on the resource deployment behavior data of each enterprise in the enterprise cluster, wherein the first resource deployment data includes at least the business data, business volume level data, monthly average resource deployment cost, and total unsubscription ratio of resource deployment SMS included in the resource deployment behavior data, and the second resource deployment data includes at least the monthly average SMS push volume, daily average SMS push volume, monthly average unsubscription volume of resource deployment SMS, and immediate unsubscription ratio of resource deployment SMS included in the resource deployment behavior data; cluster the enterprise cluster based on the first resource deployment data to obtain multiple group clusters; and cluster the enterprises included in the multiple group clusters based on the second resource deployment data to obtain multiple enterprise clusters included in each of the multiple group clusters.

[0141] The information push device disclosed herein determines a list of candidate information push numbers based on the information push requirements provided by the enterprise, and transforms the candidate information based on the information style of each push number in the list to obtain the target information. This improves the fit between information style and user preferences. Based on the target information's target push time, the target information is pushed to its corresponding push number, improving the fit between the information push time and the user's available reading time, increasing the likelihood of the user reading the information, improving the accuracy of pushing the target information to the user's terminal with the push number, improving the effectiveness of information transmission using the target information as a carrier, optimizing the user's information reading experience, and optimizing the user's information push experience on mobile devices.

[0142] To achieve the above embodiments, this disclosure also provides an electronic device, a computer-readable storage medium, and a computer program product.

[0143] Figure 4 This is a block diagram of an electronic device according to an embodiment of the present disclosure, such as... Figure 4 As shown, device 400 includes processor 401 and memory 402 communicatively connected to the processor. Memory 402 stores instructions executable by at least one processor. The instructions are executed by at least one processor 401. The processor 401 runs a program corresponding to the executable program code by reading the executable program code stored in memory 402, thereby implementing the functions described in this disclosure. Figures 1 to 2 The information push method of the embodiment.

[0144] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the present disclosure. Figures 1 to 2 The information push method of the embodiment.

[0145] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program, which, when executed by a processor, implements the features of this disclosure. Figures 1 to 2 The information push method of the embodiment.

[0146] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0147] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0148] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0149] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0150] It should be understood that various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0151] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0152] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0153] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. An information push method, characterized in that, The method includes: From the information push request, determine the candidate information to be pushed and the list of push numbers; Obtain the information style of each push number in the list of push numbers, so as to obtain the target information of each push number based on the candidate information; Obtain the target push time for each of the multiple target information items, and then push the multiple target information items.

2. The method according to claim 1, characterized in that, The step of obtaining the information style of each push number in the push number list, so as to obtain the target information of each push number based on the candidate information, includes: Obtain the target user cluster to which each push number in the push number list belongs; Based on the user cluster style of the target user cluster, determine the information style of each push number; For any given push number, the candidate information is style-transformed according to the information style corresponding to the push number to obtain the target information of the push number. The target information is obtained by editing the style and content of the candidate information based on the information style of the push number and the SMS editing conditions carried in the information push requirements through the modeling capabilities of a large language model.

3. The method according to claim 2, characterized in that, The step of obtaining the target user cluster to which each push number in the push number list belongs includes: Based on the communication behavior data of each user in the user cluster, the first communication data and the second communication data of each user are determined. The first communication data includes at least the monthly average call cost, monthly average SMS cost, monthly average SMS received volume, and monthly SMS sent volume included in the communication behavior data. The second communication data includes at least the monthly average received ratio of resource-distributed SMS, the monthly sent ratio of personal SMS, the monthly unsubscribed volume of resource-distributed SMS, and the unsubscribed ratio of resource-distributed SMS. The user clusters are clustered based on the first communication data to obtain multiple group clusters; Based on the second communication data, the users included in each of the multiple group clusters are clustered to obtain multiple user clusters included in each of the multiple group clusters; From the multiple user clusters, determine the target user cluster for each push number.

4. The method according to claim 1, characterized in that, The step of obtaining the target push time for each of the multiple target information items, and then pushing the multiple target information items, includes: For any target information, obtain multiple push information groups by combining the information style corresponding to the target information with each of the preset multiple candidate push times; Obtain the push evaluation value of each push message in the plurality of push message groups, and determine the target push time of the target message from the plurality of candidate push times based on the push evaluation value; The target information is pushed at the target push time.

5. The method according to claim 4, characterized in that, The step of obtaining the push evaluation value of each push message in the plurality of push message groups, and determining the target push time of the target message from the plurality of candidate push times based on the push evaluation value, includes: For any target information, based on the first resource deployment data of the target enterprise cluster to which the information push request originates, the first communication data of the target user cluster to which the target information belongs, and the load data of each server cluster, the push evaluation value of each of the multiple push information groups corresponding to the target information is obtained, wherein the first resource deployment data is obtained based on the resource deployment behavior data of the target enterprise cluster, and the push evaluation value is obtained based on the evaluation model. In response to any push evaluation value satisfying a set condition, the candidate push time in the any push evaluation value is determined as the target push time of the target information.

6. The method according to claim 4, characterized in that, The step of pushing the target information at the target push time includes: Determine the target push time period for each target information, and the set of target information to be pushed within each push time period; For any given push time period, determine the push order of each target information in the target information set corresponding to the push time period, and the target push number corresponding to each target information in the push number list; According to the push order, each target message is pushed to its corresponding target push number.

7. The method according to claim 6, characterized in that, For any given push time period, determining the push order of each target information in the target information set corresponding to that push time period includes: For any given push time period, determine the request initiator corresponding to each target information in the set of target information to be pushed within the push time period; Determine the push level of each request initiator, and determine the push order of each target information based on the push level.

8. The method according to claim 7, characterized in that, The step of determining the push level of each request initiator and determining the push order of each target information according to the push level includes: For any given push time period, a subset of target information to be pushed by each request initiator is determined from the target information set corresponding to the push time period, so as to obtain the number of information pushed by each request initiator within the push time period. Based on the number of information pushes, the initiators of each request are divided into multiple initiator sets. Determine the collection service level parameters for each of the multiple initiator sets, and determine the collection service order of the multiple initiator sets based on the collection service level parameters; The order in which each target message is pushed is determined based on the sorting of the collection services.

9. The method according to claim 8, characterized in that, The process involves dividing the request initiators into multiple sets based on the number of information pushes, including: Determine the minimum number of messages to push from among all the message pushes; For any number of information pushes, obtain the ratio between the number of information pushes and the minimum number of information pushes, and determine the push parameters corresponding to the request initiator for the number of information pushes based on the ratio, wherein the push parameters are obtained by rounding up the ratio. Based on the push parameters, each request initiator is divided into multiple sets of initiators. In each set of initiators, the absolute value of the difference between the sum of the push parameters of each initiator in initiator set i and the sum of the push parameters of each initiator in initiator set j is less than or equal to a set threshold.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Based on the set time interval, update the first resource deployment data of each enterprise in the enterprise cluster, the load data of each server cluster, and the first communication data of each user in the user cluster, so as to push information based on the new first resource deployment data, the new load data, and the new first communication data.

11. The method according to any one of claims 1-9, characterized in that, The method further includes: Based on the second communication data of users included in multiple user clusters and the second resource deployment data of enterprises included in multiple enterprise clusters, the corresponding information deployment reward is obtained. The evaluation model for obtaining the push evaluation value is optimized based on the information delivery reward, resulting in a new optimized evaluation model. Information is then pushed based on the new evaluation model.

12. The method according to claim 11, characterized in that, Obtain the multiple enterprise clusters, including: Based on the resource deployment behavior data of each enterprise in the enterprise cluster, the first resource deployment data and the second resource deployment data of each enterprise are determined. The first resource deployment data includes at least the business data, business volume level data, monthly average resource deployment cost and total unsubscription ratio of resource deployment SMS included in the resource deployment behavior data. The second resource deployment data includes at least the monthly average SMS push volume, daily average SMS push volume, monthly average unsubscription volume of resource deployment SMS and immediate unsubscription ratio of resource deployment SMS included in the resource deployment behavior data. Based on the first resource allocation data, the enterprise clusters are clustered to obtain multiple group clusters; Based on the second resource allocation data, the enterprises included in the multiple group clusters are clustered to obtain multiple enterprise clusters included in each of the multiple group clusters.

13. An information push device, characterized in that, The device includes: The determination module is used to determine the candidate information to be pushed and the list of push numbers from the information push request; The acquisition module is used to acquire the information style of each push number in the push number list, so as to obtain the target information of each push number based on the candidate information; The push module is used to obtain the target push time for each of the multiple target information items, so as to push the multiple target information items.

14. An electronic device, characterized in that, Including memory and processor; The processor runs a program corresponding to the executable program code stored in the memory to implement the method as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-12.

Images