CN112104989B

CN112104989B - Short message sending method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN112104989B
Application number: CN202011275625.0A
Authority: CN
Inventors: 林聪�
Original assignee: Shenzhen Zhenaiyun Information Technology Co ltd
Current assignee: Shenzhen Aiteyun Information Technology Co ltd
Priority date: 2020-11-16
Filing date: 2020-11-16
Publication date: 2021-02-19
Anticipated expiration: 2040-11-16
Also published as: CN112104989A

Abstract

The application relates to a short message sending method, a short message sending device, electronic equipment and a computer readable storage medium, which are applied to the electronic equipment, wherein the method comprises the following steps: acquiring a short message set to be sent and a short message channel set, and classifying the short message set to be sent based on preset short message categories to obtain a plurality of short message subsets to be sent; calculating a short message channel weight set corresponding to the short message channel set; determining a plurality of target short message channel sets in the short message channel set based on the short message subsets to be sent, and performing channel probability calculation on the target short message channel sets based on the short message channel weight sets to obtain a plurality of channel probability matrixes; and sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets. The embodiment of the application has the advantage of high user experience.

Description

Short message sending method and device, electronic equipment and computer readable storage medium

Technical Field

The present application relates to the field of electronic communications technologies, and in particular, to a short message sending method, an apparatus, an electronic device, and a computer-readable storage medium.

Background

Short Message Service (SMS) is a text or digital Message that a user directly sends or receives through a mobile phone or other electronic devices, and a Short Message group sending platform is generated along with the rapid development of the electronic devices.

The conventional short message platform is mainly used for selecting one short message channel from a plurality of short message channels provided by an external short message gateway to realize a short message group sending function, but under the condition of a single short message channel, when an unstable event occurs in the short message channel, the short message channel cannot work or the short message cannot reach the unstable event, so that the short message platform is low in efficiency and the user experience degree is low.

Disclosure of Invention

The embodiment of the application provides a short message sending method, a short message sending device, electronic equipment and a computer readable storage medium, and aims to improve the working efficiency and the user experience of a short message platform.

In a first aspect, an embodiment of the present application provides a short message sending method, which is applied to an electronic device, and the method includes:

acquiring a short message set to be sent and a short message channel set, and classifying the short message set to be sent based on preset short message categories to obtain a plurality of short message subsets to be sent;

calculating a short message channel weight set corresponding to the short message channel set;

determining a plurality of target short message channel sets in the short message channel set based on the short message subsets to be sent, and performing channel probability calculation on the target short message channel sets based on the short message channel weight sets to obtain a plurality of channel probability matrixes;

and sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets.

In a possible example, the calculating a short message channel weight set corresponding to the short message channel set includes: acquiring a plurality of manual weights and a plurality of statistical weights corresponding to a plurality of short message channels in the short message channel set; executing channel health weight calculation operation aiming at the short message channels to obtain a plurality of channel health weights; substituting the artificial weights, the statistical weights and the channel health weights into a preset channel weight calculation formula to obtain a plurality of channel weights corresponding to the short message channels; and generating the short message channel weight set based on the plurality of channel weights.

In a possible example, the performing channel health weight calculation operations for the plurality of short message channels includes: acquiring a touch window value of the short message channel aiming at each short message channel in the short message channel set; determining a historical touch window period corresponding to the short message channel based on the current time and the touch window value; extracting a plurality of sampling periods contained in the historical touch window period and a plurality of groups of historical short message data corresponding to the sampling periods; receiving a plurality of actual reach rates and a plurality of expected reach rates of the plurality of groups of historical short message data; performing difference calculation based on the actual reach rates and the expected reach rates to obtain a plurality of reach rate deviations, and combining the reach rate deviations to obtain a window deviation vector WD; obtaining a preset influence coefficient vector WRP aiming at the multiple sampling periods, and substituting a preset artificial weight threshold LIMIT, the WRP and the WD into a preset channel health weight calculation formula to obtain a channel health weight WH of the short message channel, wherein the channel health weight calculation formula comprises：

。

In a possible example, the determining, in the short message channel set, a plurality of target channel sets based on the plurality of short message subsets to be sent includes: determining a plurality of short message types corresponding to the plurality of short message subsets to be sent; and performing a screening operation for each of the plurality of short message types to obtain the plurality of target short message channel sets, wherein the screening operation comprises: aiming at any one of the short message types, a plurality of short message channels to be selected corresponding to the any one short message type are selected from the short message channel set; and acquiring at least one target short message channel in an idle state in the plurality of short message channels to be selected to generate a target short message channel set corresponding to any one short message type.

In a possible example, the performing a channel probability calculation on the plurality of target short message channel sets based on the short message channel weight set includes: acquiring a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set aiming at each target short message channel set in the plurality of target short message channel sets, wherein the target short message channel set comprises k target short message channels, the target short message channel weight set comprises k target short message channel weights, and k is greater than 0; generating a target short message channel weight vector based on the k target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector NW, wherein,

；

substituting the target weight vector NW into a cumulative distribution function formula to obtain the target distribution cumulative function vector CDF,

(ii) a Computing a channel probability matrix based on the CDFCDFR, wherein,

。

in a possible example, after obtaining the target weight vector NW, the method further includes: acquiring a comprehensive calculation vector R of the target short message channel set at the current moment; substituting the comprehensive calculation vector R and the target weight vector NW into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, wherein the comprehensive calculation formula is as follows:

(ii) a Judging whether the target comprehensive value RO is larger than a preset comprehensive value threshold value or not

If the sum of the obtained target short message channel set and the obtained target short message channel set is greater than the preset threshold, obtaining an optimized vector corresponding to the target short message channel set, calculating a channel mathematical expectation CE based on the optimized vector and the target weight vector NW, adjusting the target weight vector NW to enable the mathematical expectation CE to reach the minimum value

Determining the minimum value

Corresponding weight vector

Based on the weight vector

The target weight vector NW is updated.

In a possible example, the sending the multiple subsets of short messages to be sent based on the multiple channel probability matrices and the multiple target short message channel sets includes: determining a target short message channel set and a channel probability matrix corresponding to any short message in the plurality of short message subsets to be sent; acquiring a random number of the any short message; substituting the channel probability matrix and the random number into a preset judgment range function to obtain a selection vector of any one short message; and controlling a target short message channel corresponding to the component with the component value of 1 in the selection vector to send the arbitrary short message.

In a second aspect, an embodiment of the present application provides a short message sending apparatus, where the apparatus includes:

the device comprises an acquisition unit, a sending unit and a receiving unit, wherein the acquisition unit is used for acquiring a short message set to be sent and a short message channel set, and classifying the short message set to be sent based on a preset short message category to obtain a plurality of short message subsets to be sent;

the calculation unit is used for calculating a short message channel weight set corresponding to the short message channel set;

a determining unit, configured to determine multiple target short message channel sets in the short message channel set based on the multiple short message subsets to be sent, and perform channel probability calculation on the multiple target short message channel sets based on the short message channel weight sets to obtain multiple channel probability matrices;

and the sending unit is used for sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets.

In a third aspect, embodiments of the present application provide an electronic device, which includes a processor, a memory, a communication interface, and one or more programs, stored in the memory and configured to be executed by the processor, the programs including instructions for performing some or all of the steps described in the method according to the first aspect of the embodiments of the present application.

In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, where the computer program is executed by a processor to implement part or all of the steps described in the method according to the first aspect of the present application.

It can be seen that, in the embodiment of the application, the electronic device acquires a short message set to be sent and a short message channel set, and classifies the short message set to be sent based on a preset short message category to obtain a plurality of short message subsets to be sent; calculating a short message channel weight set corresponding to the short message channel set; determining a plurality of target short message channel sets in the short message channel set based on the short message subsets to be sent, and performing channel probability calculation on the target short message channel sets based on the short message channel weight sets to obtain a plurality of channel probability matrixes; and sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets. Therefore, a target short message channel set can be screened out through the short message categories, a channel probability matrix is calculated based on the target short message channel, namely, the optimal solution of channel combination is realized by calculating the channel probability matrix of the target short message channel set, the short message set is sent through the channel probability matrix, the multi-short message channel work is realized, the short message channel stability is improved, and the channel probability matrix is recalculated for each batch of short messages to be sent, so that the short message channel fault can be found in time, the working efficiency of a short message platform is improved, and the user experience is favorably improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is an application environment diagram of a short message sending method according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a short message sending method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a window offset calculation according to an embodiment of the present disclosure;

fig. 4 is a schematic flowchart of another short message sending method according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device 500 according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a short message sending apparatus according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of the invention and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

Hereinafter, some terms in the present application are explained to facilitate understanding by those skilled in the art.

Electronic devices may include a variety of handheld devices, vehicle-mounted devices, wearable devices (e.g., smartwatches, smartbands, pedometers, etc.), computing devices or other processing devices communicatively connected to wireless modems, as well as various forms of User Equipment (UE), Mobile Stations (MS), terminal Equipment (terminal device), and so forth having wireless communication capabilities. For convenience of description, the above-mentioned devices are collectively referred to as electronic devices.

Referring to fig. 1, fig. 1 is an application environment diagram of a short message sending method according to an embodiment of the present application, in which a terminal 120 receives a short message to be sent from a short message sending device (e.g., a short message sending device 111 and a short message sending device 112), an electronic device 120 divides the short message to be sent into a plurality of short message subsets to be sent according to short message categories, a plurality of target short message channel sets corresponding to the plurality of short message subsets to be sent are determined in short message channels provided by preset gateway devices (e.g., a gateway 131 and a gateway 132), the gateway devices send short messages in the short message subsets to be sent to operator devices (e.g., an operator device 141, an operator device 142, and an operator device 143) through corresponding short message channel sets after receiving the short message subsets to be sent, the operator devices send the short messages in the short message subsets to be sent to user devices (e.g., user equipment 161, user equipment 162, and user equipment 163).

The short message sending device 111, the short message sending device 112, the electronic device 120, the operator device 141, the operator device 142, the operator device 143, the user device 161, the user device 162, and the user device 163 may be, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the

gateways

131 and 132 may be implemented by independent servers or a server cluster formed by a plurality of servers.

Referring to fig. 2, an embodiment of the present application provides a short message sending method, which is described by taking the application of the method to the terminal in fig. 1 as an example, and includes the following steps:

step 201, acquiring a short message set to be sent and a short message channel set, and classifying the short message set to be sent based on a preset short message category to obtain a plurality of short message subsets to be sent.

Optionally, a short message set to be sent is obtained, where the short message set to be sent includes at least one short message to be sent, and a short message channel set is obtained, where the short message channel set includes at least one short message channel.

Step 202, calculating a short message channel weight set corresponding to the short message channel set.

Optionally, a preset short message channel weight calculation rule is obtained, each short message channel in the short message channel weight set is calculated based on the short message channel weight calculation rule, and the short message channel weights corresponding to each short message channel are combined to obtain a short message channel weight set.

Step 203, determining a plurality of target short message channel sets in the short message channel set based on the plurality of short message subsets to be sent, and performing channel probability calculation on the plurality of target short message channel sets based on the short message channel weight sets to obtain a plurality of channel probability matrices.

And step 204, sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets.

The channel probability matrixes correspond to the target short message channel sets one by one, and the target short message channel sets correspond to the short message subsets to be sent one by one.

Optionally, for each short message subset to be sent in the multiple short message subsets to be sent, a random number matrix corresponding to each short message subset to be sent and a channel probability vector of the target short message channel set are obtained, and a channel selection matrix is calculated based on the random number matrix and the channel probability vector, wherein a column vector in the channel selection matrix is a channel selection vector of each short message to be sent in the short message subsets to be sent.

Optionally, a preset artificial weight vector is obtained, where the artificial weight vector includes a plurality of artificial weight components, and the artificial weight components are in one-to-one correspondence with the plurality of short message channels, where the artificial weight vector has an artificial weight threshold LIMIT, that is, a value range of any one of the plurality of components is (-LIMIT, LIMIT); acquiring a preset statistical weight vector, where the statistical weight vector includes a plurality of statistical weight components corresponding to the plurality of short message channels one to one, where the statistical weight has a statistical weight range, for example, the statistical weight range may include (-1000, 1000), which is not limited herein, and in a possible case, the statistical weight range is default to a constant value of 0.

Optionally, when obtaining the statistical weight of any one short message channel, first obtaining m quantity statistics devices of the short message channel

Obtaining the m number statistics device

Determining the calculation mode of statistical weight according to the current statistical value and m data statistics devices

The statistical weight of any one short message channel is determined, it should be noted that any one short message channel can be provided with any number of quantity statistics devices, and the quantity of the quantity statistics devices corresponding to different short message channels can be different.

In the specific implementation process, it is assumed that the calculation mode of the statistical weight is a minimum weight, that is, for any short message channel j, at a certain time t, the statistical value component of the short message channel j is the minimum weight of the m number of corresponding statistical devices, and it is assumed that the statistical weight range is (-1000, 1000), that is, the statistical weight range is (-1000, 1000)

。

The statistical weight is a group of weights which impose limitation according to the time interval statistical value, and the influence of the overload degree of the current load of the short message channel is reflected.

In a possible example, the performing channel health weight calculation operations for the plurality of short message channels includes: acquiring a touch window value of the short message channel aiming at each short message channel in the short message channel set; determining a historical touch window period corresponding to the short message channel based on the current time and the touch window value; extracting a plurality of sampling periods contained in the historical touch window period and a plurality of groups of historical short message data corresponding to the sampling periods; receiving a plurality of actual reach rates and a plurality of expected reach rates of the plurality of groups of historical short message data; performing difference calculation based on the actual reach rates and the expected reach rates to obtain a plurality of reach rate deviations, and combining the reach rate deviations to obtain a window deviation vector WD; acquiring a preset influence coefficient vector WRP aiming at the multiple sampling periods, and substituting a preset artificial weight threshold LIMIT, the WRP and the WD into a preset channel health weight calculation formula to obtain a channel health weight WH of the short message channel, wherein the channel health weight calculation formula comprises:

。

the channel health weight is used for reflecting the health state of the short message channel at the current moment, the health state is calculated according to the channel operation feedback condition, the health state of the short message channel is related to the short message touch condition of the channel, namely, if a short message can be sent within the preset time, the short message channel is considered to be in the health state, and if a short message is not sent within the preset time, the short message channel is considered to be in the non-health state.

The touch window is the maximum time length that a certain type of short message can touch and tolerate under normal conditions, and for any type of short message, if the short message is not touched within the touch window time of the corresponding short message channel, the short message channel is determined to be in a fault state, and the touch windows of the different types of short message channels are not all the same.

In the specific implementation process, the historical touch window period corresponding to the short message channel is determined based on the current time and the touch window value, namely, the current time is assumed to be t, and the touch window value is assumed to be t

Then determine the historical touchdown window period as

(ii) a The history window period comprises a plurality of sampling periods s, i.e.

Wherein

extracting multiple groups of historical short message data corresponding to multiple sampling periods for the length of a short message sending window, wherein each group of historical short message data comprises: an actual reach rate and a desired reach rate; or, assuming that win batches of short messages are sent in the historical reach window period, extracting the expected reach rate vector corresponding to the historical reach window period

And the actual reach rate vector

The components in the actual reach rate vector correspond to the components in the expected reach rate vector one to one; calculating a reach rate deviation based on an actual reach rate and an expected reach rate

Merging multiple reach rate biasesDifferencing to obtain a window deviation vector

As shown in fig. 3, fig. 3 is a schematic diagram of window deviation calculation according to an embodiment of the present application, and it can be known from the diagram that the calculation is performed

Window offset vector of time, selecting

Within the past SRW time of the touch window value at the moment, win batches of short messages are sent out, and the first batch of short messages sent out initially

Corresponding time is

And at the present time

The first batch of short messages can be known to have the deviation of the touch rate of the first batch of short messages at any moment

(ii) a Similarly, the second batch of short messages

Corresponding time is

And at the present time

The touch rate deviation of the second batch of short messages can be known at any moment

And so on until the last batch

Corresponding time is

And is at present

The deviation of the touch rate of the last batch of short messages can be known at the moment

Thus, combining the multiple reach rate deviations to obtain a window deviation vector

。

Optionally, a weight coefficient vector WRP is obtained, where each component in the weight coefficient vector WRP corresponds to a time point, and is used to reflect an influence weight of sending a short message at the time point, that is, the weight coefficient vector WRP is obtained

。

For the above embodiment, an example is described below, and it is assumed that for a certain sampling period s =3, a certain type of short message of the short message batch win =5 is sent through the short message channel j, and the expected reach proportion distribution thereof

That is, on the short message channel k, 5% of the short messages are received within the first 3 seconds, 90% of the short messages are received within the second 3 seconds, 95% of the short messages are received within the third 3 seconds, 98% of the short messages are received within the fourth 3 seconds, and 100% of the short messages are received within the fifth 3 seconds; at the current moment

In the last 15 seconds, 5 batches of short messages are sent, and for each batch of short messages, the true gas touch rate is as follows:

the first batch of short messages are sent for the time of

At a

，

) At the moment, the real touch rate of the first batch of short messages is

；

The second batch of short messages are sent for time

At a

，

) At the moment, the real touch rate of the first batch of short messages is

；

The third batch of short messages are sent for time

At a

，

) At the moment, the real touch rate of the first batch of short messages is

；

The fourth batch of short messages are sent for time

At a

，

) At the moment, the real touch rate of the first batch of short messages is

；

The fifth batch of short messages are sent for time

At a

，

) At the moment, the real touch rate of the first batch of short messages is

；

Therefore, the formula is calculated according to the deviation of the touch rate

The window deviation vector can be calculated

Then, then

I.e. by

；

Obtaining a weight coefficient vector WRP, assuming

Calculating the current deviation

I.e. by

，

Thereby, the reliability of the current channel is obtained

Comprises the following steps: when CD<At the time of 0, the number of the first,

(ii) a When CD>At the time of 0, the number of the first,

(ii) a When 0 is present<CD<When the pressure of the mixture is 1, the pressure is lower,

(ii) a Substituting a preset artificial weight threshold LIMIT =1000, WRP and WD into a preset channel health weight calculation formula to obtain a channel health weight WH, namely

，

That is, the health weight of channel k is-121.

In a specific implementation process, a target subset is determined in a plurality of short message subsets to be sent, a short message type corresponding to the target subset is obtained, the short message type is screened in a target channel set, wherein each short message channel in the target channel set corresponds to one short message type, a plurality of short message channels matched with the short message type are extracted in the target channel set, a set formed by the plurality of short message channels is determined as a channel set to be selected, and whether the short message channel to be selected is in an idle state, namely a non-use state, is judged for each short message channel to be selected in the channel set to be selected, wherein the judgment of whether the short message channel is in the idle state may include: acquiring the utilization rate of a short message channel at the current moment, if the utilization rate is greater than a preset utilization rate threshold value, determining that the short message channel is in a non-idle state, and if the utilization rate is less than the utilization rate threshold value, determining that the short message channel is in an idle state; and extracting the short message channels in the idle state in the channel set to be selected to generate a target short message channel set.

(ii) a Substituting the target weight vector NW into a cumulative distribution function formula to obtain the target distribution cumulative function vector CDF,

(ii) a Computing a channel probability matrix, CDFR, based on the CDF, wherein,

。

optionally, generating a target short message channel weight vector based on the k target short message channel weights, and performing a normalization operation on the target short message channel weight vector, including: determining k target short message channel weights

Wherein, 0<i<k, generating a target short message channel weight vector

For the target short message channel weight vector

Performing normalization operation to obtain target weight vector

Namely:

，

。

optionally, the selection range vector CDFR cuts the length between [0,1] into k segments according to the probability density of k short message channels, and for any short message, there is a random number with a size between [0,1], and the random number falls in an area corresponding to any one of the k short message channels, that is, it indicates that the short message channel is selected, and sends the short message.

In a possible example, after obtaining the target weight vector NW, the method further includes: acquiring the current target short message channel setComprehensively calculating a vector R of the moment; substituting the comprehensive calculation vector R and the target weight vector NW into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, wherein the comprehensive calculation formula is as follows:

Determining the minimum value

Corresponding weight vector

Based on the weight vector

The target weight vector NW is updated.

Optionally, a comprehensive calculation vector R of the target short message channel set at the current time is obtained, where the comprehensive calculation vector R includes the reliability of each short message channel at the current time, that is, the comprehensive calculation vector at time t is:

，

wherein,

the reliability of the first channel at time t.

Optionally, the comprehensive calculation vector R and the target weight vector NW are substituted into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, for example, at time t, the target comprehensive value RO is calculated

。

Optionally, before obtaining the optimized vector corresponding to the target short message channel set, the method further includes: acquiring unit cost of k short message channels in a target short message channel set at the current moment, and generating the optimized vector based on the k unit cost, wherein the optimized vector is as follows:

。

optionally based on an optimisation vector

And the target weight vector NW calculates the channel mathematical expectation CE, i.e. at time t the mathematical expectation is:

the mathematical expectation CE represents the unit cost for sending the short message based on the target short message channel set at the current moment; adjusting the target weight vector NW minimizes the mathematical expectation CE

When the mathematical expectation CE reaches a minimum value

When the minimum value is determined

Corresponding weight vector

Based on weight vectors

The target weight vector NW is updated.

Optionally, any short message subset to be sent is selected from the multiple short message subsets to be sent as a target subset, a channel probability matrix CDFR of a target short message channel set corresponding to the target subset is determined, a random number corresponding to each short message in the target subset is obtained, and a preset judgment range function is obtained, where the judgment range function may include:

；

substituting the channel probability matrix CDFR and the random number into a judgment range function, and assuming that a target short message channel set has k short message channels, obtaining a selection vector of the short message

，

Wherein:

，

namely, the selection vector CSV is a vector composed of components with k dimensions and values of (0,1), and at least one component has a value of 1, and the other components are 0, and the target short message channel corresponding to the component with the value of 1 in the selection vector is controlled to send the short message.

In the specific implementation process, a random number vector exists for a batch of short messages in a short message subset to be sent

Substituting the random number vector and the channel probability matrix CDFR into a judgment range function to obtain a matrix with a matrix column vector as a selection vector, namely:

，

the matrix is a channel selection matrix of the subset to be transmitted.

Referring to fig. 4, fig. 4 is a schematic flow chart of another short message sending method according to an embodiment of the present application, and as shown in the figure, the method includes the following steps:

step 401, acquiring a short message set to be sent and a short message channel set, and classifying the short message set to be sent based on a preset short message category to obtain a plurality of short message subsets to be sent;

step 402, acquiring a plurality of manual weights and a plurality of statistical weights corresponding to a plurality of short message channels in the short message channel set;

step 403, substituting the artificial weights, the statistical weights and the channel health weights into a preset channel weight calculation formula to obtain channel weights corresponding to the short message channels, and generating a short message channel weight set based on the channel weights;

step 404, determining a plurality of target short message channel sets in the short message channel set based on the plurality of short message subsets to be sent;

step 405, for each target short message channel set in the plurality of target short message channel sets, obtaining a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set, wherein the target short message channel set comprises k target short message channels, and the target short message channel weight set comprises target short message channel weights;

step 406, generating a target short message channel weight vector based on the target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector;

step 407, substituting the target weight vector into a cumulative distribution function formula to obtain the target distribution cumulative function vector;

step 408, calculating a channel probability matrix based on the target distribution cumulative function vector to obtain a plurality of channel probability matrices;

step 409, sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets.

The detailed description of the steps 401 to 409 may refer to the corresponding steps of the short message sending method described in fig. 2, and are not repeated herein.

It should be understood that, although the steps in the flowchart of fig. 4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device 500 according to an embodiment of the present application, and as shown in the figure, the server 500 includes an application processor 510, a memory 520, a communication interface 530, and one or more programs 521, where the one or more programs 521 are stored in the memory 520 and configured to be executed by the application processor 510, and the one or more programs 521 include instructions for:

In a possible example, in the aspect of calculating the short message channel weight set corresponding to the short message channel set, the instructions in the program are specifically configured to perform the following operations: acquiring a plurality of manual weights and a plurality of statistical weights corresponding to a plurality of short message channels in the short message channel set; executing channel health weight calculation operation aiming at the short message channels to obtain a plurality of channel health weights; substituting the artificial weights, the statistical weights and the channel health weights into a preset channel weight calculation formula to obtain a plurality of channel weights corresponding to the short message channels; and generating the short message channel weight set based on the plurality of channel weights.

In one possible example, in the performing channel health weight calculation operations for the plurality of short message channels, the instructions in the program are specifically configured to perform the following operations: acquiring a touch window value of the short message channel aiming at each short message channel in the short message channel set; determining a calendar corresponding to the short message channel based on the current time and the reach window valueStandad window period; extracting a plurality of sampling periods contained in the historical touch window period and a plurality of groups of historical short message data corresponding to the sampling periods; receiving a plurality of actual reach rates and a plurality of expected reach rates of the plurality of groups of historical short message data; performing difference calculation based on the actual reach rates and the expected reach rates to obtain a plurality of reach rate deviations, and combining the reach rate deviations to obtain a window deviation vector WD; acquiring a preset influence coefficient vector WRP aiming at the multiple sampling periods, and substituting a preset artificial weight threshold LIMIT, the WRP and the WD into a preset channel health weight calculation formula to obtain a channel health weight WH of the short message channel, wherein the channel health weight calculation formula comprises:

。

in a possible example, in the aspect that a plurality of target channel sets are determined in the short message channel set based on the plurality of short message subsets to be sent, the instructions in the program are specifically configured to perform the following operations: determining a plurality of short message types corresponding to the plurality of short message subsets to be sent; and performing a screening operation for each of the plurality of short message types to obtain the plurality of target short message channel sets, wherein the screening operation comprises: aiming at any one of the short message types, a plurality of short message channels to be selected corresponding to the any one short message type are selected from the short message channel set; and acquiring at least one target short message channel in an idle state in the plurality of short message channels to be selected to generate a target short message channel set corresponding to any one short message type.

In a possible example, in terms of performing channel probability calculation on the plurality of target short message channel sets based on the short message channel weight set, the instructions in the program are specifically configured to perform the following operations: aiming at each target short message channel set in the plurality of target short message channel sets, acquiring a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set, wherein the target short message channel set comprises k targetsThe target short message channel weight set comprises k target short message channel weights, and k is greater than 0; generating a target short message channel weight vector based on the k target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector NW, wherein,

；

computing a channel probability matrix, CDFR, based on the CDF, wherein,

。

in a possible example, in terms of after said deriving the target weight vector NW, the instructions in the program are further configured to: acquiring a comprehensive calculation vector R of the target short message channel set at the current moment; substituting the comprehensive calculation vector R and the target weight vector NW into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, wherein the comprehensive calculation formula is as follows:

Determining the minimum value

Corresponding weight vector

Based on the weight vector

The target weight vector NW is updated.

In a possible example, in the aspect of sending the multiple to-be-sent short message subsets based on the multiple channel probability matrices and the multiple target short message channel sets, the instructions in the program are specifically configured to perform the following operations: determining a target short message channel set and a channel probability matrix corresponding to any short message in the plurality of short message subsets to be sent; acquiring a random number of the any short message; substituting the channel probability matrix and the random number into a preset judgment range function to obtain a selection vector of any one short message; and controlling a target short message channel corresponding to the component with the component value of 1 in the selection vector to send the arbitrary short message.

The above description has introduced the solution of the embodiment of the present application mainly from the perspective of the method-side implementation process. It is understood that the electronic device comprises corresponding hardware structures and/or software modules for performing the respective functions in order to realize the above-mentioned functions. Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the electronic device may be divided into the functional units according to the method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one control unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Referring to fig. 6, fig. 6 is a schematic structural diagram of a short message sending apparatus according to an embodiment of the present application, including: an acquisition unit 601, a calculation unit 602, a determination unit 603, and a transmission unit 604, wherein:

an obtaining unit 601, configured to obtain a short message set to be sent and a short message channel set, and classify the short message set to be sent based on a preset short message category to obtain a plurality of short message subsets to be sent;

a calculating unit 602, configured to calculate a short message channel weight set corresponding to the short message channel set;

a determining unit 603, configured to determine multiple target short message channel sets in the short message channel set based on the multiple short message subsets to be sent, and perform channel probability calculation on the multiple target short message channel sets based on the short message channel weight sets to obtain multiple channel probability matrices;

a sending unit 604, configured to send the multiple to-be-sent short message subsets based on the multiple channel probability matrices and the multiple target short message channel sets.

In a possible example, in the aspect of calculating the short message channel weight set corresponding to the short message channel set, the calculating unit 602 is specifically configured to: acquiring a plurality of manual weights and a plurality of statistical weights corresponding to a plurality of short message channels in the short message channel set; executing channel health weight calculation operation aiming at the short message channels to obtain a plurality of channel health weights; substituting the artificial weights, the statistical weights and the channel health weights into a preset channel weight calculation formula to obtain a plurality of channel weights corresponding to the short message channels; and generating the short message channel weight set based on the plurality of channel weights.

In a possible example, in terms of performing a channel health weight calculation operation on the plurality of short message channels, the calculating unit 602 is specifically configured to: acquiring a touch window value of the short message channel aiming at each short message channel in the short message channel set; determining a historical touch window period corresponding to the short message channel based on the current time and the touch window value; extracting a plurality of sampling periods contained in the historical touch window period and a plurality of groups of historical short message data corresponding to the sampling periods; receiving a plurality of actual reach rates and a plurality of expected reach rates of the plurality of groups of historical short message data; performing difference calculation based on the actual reach rates and the expected reach rates to obtain a plurality of reach rate deviations, and combining the reach rate deviations to obtain a window deviation vector WD; obtaining a preset needleSubstituting a preset artificial weight threshold LIMIT, the WRP and the WD into a preset channel health weight calculation formula to obtain a channel health weight WH of the short message channel for the influence coefficient vector WRP of the plurality of sampling periods, wherein the channel health weight calculation formula comprises:

。

in a possible example, in the aspect of determining multiple target channel sets in the short message channel set based on the multiple short message subsets to be sent, the determining unit 603 is specifically configured to: determining a plurality of short message types corresponding to the plurality of short message subsets to be sent; and performing a screening operation for each of the plurality of short message types to obtain the plurality of target short message channel sets, wherein the screening operation comprises: aiming at any one of the short message types, a plurality of short message channels to be selected corresponding to the any one short message type are selected from the short message channel set; and acquiring at least one target short message channel in an idle state in the plurality of short message channels to be selected to generate a target short message channel set corresponding to any one short message type.

In a possible example, in terms of performing channel probability calculation on the multiple target short message channel sets based on the short message channel weight set, the determining unit 603 is specifically configured to: acquiring a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set aiming at each target short message channel set in the plurality of target short message channel sets, wherein the target short message channel set comprises k target short message channels, the target short message channel weight set comprises k target short message channel weights, and k is greater than 0; generating a target short message channel weight vector based on the k target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector NW, wherein,

(ii) a Substituting the target weight vector NW into an accumulation scoreA function distribution formula is used for obtaining the target distribution cumulative function vector CDF, wherein,

；

computing a channel probability matrix, CDFR, based on the CDF, wherein,

。

in a possible example, after obtaining the target weight vector NW, the determining unit 603 is specifically configured to: acquiring a comprehensive calculation vector R of the target short message channel set at the current moment; substituting the comprehensive calculation vector R and the target weight vector NW into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, wherein the comprehensive calculation formula is as follows:

Determining the minimum value

Corresponding weight vector

Based on the weight vector

The target weight vector NW is updated.

In a possible example, in the aspect of sending the multiple to-be-sent short message subsets based on the multiple channel probability matrices and the multiple target short message channel sets, the sending unit 604 is specifically configured to: determining a target short message channel set and a channel probability matrix corresponding to any short message in the plurality of short message subsets to be sent; acquiring a random number of the any short message; substituting the channel probability matrix and the random number into a preset judgment range function to obtain a selection vector of any one short message; and controlling a target short message channel corresponding to the component with the component value of 1 in the selection vector to send the arbitrary short message.

For specific limitations of the short message sending apparatus, reference may be made to the above limitations on the short message sending method, which is not described herein again. All modules in the short message sending device can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

Embodiments of the present application also provide a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, the computer program enabling a computer to execute part or all of the steps of any one of the methods described in the above method embodiments, and the computer includes an electronic device.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package, the computer comprising an electronic device.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-mentioned method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A short message sending method is applied to electronic equipment, and comprises the following steps:

sending the plurality of short message subsets to be sent based on the plurality of channel probability matrixes and the plurality of target short message channel sets;

the performing channel probability calculation on the plurality of target short message channel sets based on the short message channel weight set comprises:

acquiring a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set aiming at each target short message channel set in the plurality of target short message channel sets, wherein the target short message channel set comprises k target short message channels, the target short message channel weight set comprises k target short message channel weights, and k is greater than 0;

generating a target short message channel weight vector based on the k target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector NW, wherein,

；

；

computing a channel probability matrix, CDFR, based on the CDF, wherein,

。

2. the method for sending short messages according to claim 1, wherein the calculating of the short message channel weight set corresponding to the short message channel set includes:

acquiring a plurality of manual weights and a plurality of statistical weights corresponding to a plurality of short message channels in the short message channel set;

executing channel health weight calculation operation aiming at the short message channels to obtain a plurality of channel health weights;

substituting the artificial weights, the statistical weights and the channel health weights into a preset channel weight calculation formula to obtain a plurality of channel weights corresponding to the short message channels;

and generating the short message channel weight set based on the plurality of channel weights.

3. The method of claim 2, wherein the performing channel health weight calculation operations for the plurality of short message channels comprises:

acquiring a touch window value of the short message channel aiming at each short message channel in the short message channel set;

determining a historical touch window period corresponding to the short message channel based on the current time and the touch window value;

extracting a plurality of sampling periods contained in the historical touch window period and a plurality of groups of historical short message data corresponding to the sampling periods;

receiving a plurality of actual reach rates and a plurality of expected reach rates of the plurality of groups of historical short message data;

performing difference calculation based on the actual reach rates and the expected reach rates to obtain a plurality of reach rate deviations, and combining the reach rate deviations to obtain a window deviation vector WD;

obtaining a preset influence coefficient vector WRP aiming at the multiple sampling periods, and substituting a preset artificial weight threshold LIMIT, the WRP and the WD into a preset channel health weight calculation formula to obtain the influence coefficient vector WRPThe channel health weight WH of the short message channel comprises the following calculation formula:

。

4. the method for sending short messages according to claim 1, wherein the determining a plurality of target channel sets in the short message channel set based on the plurality of short message subsets to be sent comprises:

determining a plurality of short message types corresponding to the plurality of short message subsets to be sent;

and performing a screening operation for each of the plurality of short message types to obtain the plurality of target short message channel sets, wherein the screening operation comprises: aiming at any one of the short message types, a plurality of short message channels to be selected corresponding to the any one short message type are selected from the short message channel set; and acquiring at least one target short message channel in an idle state in the plurality of short message channels to be selected to generate a target short message channel set corresponding to any one short message type.

5. The short message sending method of claim 1, wherein after obtaining the target weight vector NW, the method further comprises:

acquiring a comprehensive calculation vector R of the target short message channel set at the current moment;

substituting the comprehensive calculation vector R and the target weight vector NW into a preset comprehensive calculation formula to obtain a target comprehensive value RO corresponding to the target short message channel set, wherein the comprehensive calculation formula is as follows:

；

judging whether the target comprehensive value RO is larger than a preset comprehensive value threshold value or not

Determining the minimum value

Corresponding weight vector

Based on the weight vector

The target weight vector NW is updated.

6. The method of claim 1, wherein the sending the plurality of subsets of short messages to be sent based on the plurality of channel probability matrices and the plurality of target short message channel sets comprises:

determining a target short message channel set and a channel probability matrix corresponding to any short message in the plurality of short message subsets to be sent;

acquiring a random number of the any short message;

substituting the channel probability matrix and the random number into a preset judgment range function to obtain a selection vector of any one short message;

and controlling a target short message channel corresponding to the component with the component value of 1 in the selection vector to send the arbitrary short message.

7. A short message sending device, characterized in that the device comprises:

a sending unit, configured to send the multiple to-be-sent short message subsets based on the multiple channel probability matrices and the multiple target short message channel sets;

in the aspect that the channel probability calculation is performed on the plurality of target short message channel sets based on the short message channel weight set, the determining unit is specifically configured to: acquiring a target short message channel weight set corresponding to the target short message channel set from the short message channel weight set aiming at each target short message channel set in the plurality of target short message channel sets, wherein the target short message channel set comprises k target short message channels, the target short message channel weight set comprises k target short message channel weights, and k is greater than 0; generating a target short message channel weight vector based on the k target short message channel weights, and performing normalization operation aiming at the target short message channel weight vector to obtain a target weight vector NW, wherein,

；

computing a channel probability matrix, CDFR, based on the CDF, wherein,

。

8. an electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the method of sending short messages according to any one of claims 1-6.

9. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the short message sending method according to any one of claims 1 to 6.