Method, apparatus, electronic device, and storage medium for determining a target task

Abstract

An embodiment of the present invention provides a method, an apparatus, an electronic device, and a storage medium for determining a target task. The method includes: for each task to be sent, determining task attribute information of the currently to-be-sent task, and determining a matching degree between the currently to-be-sent task and a target user according to the task attribute information; wherein, the task attribute information includes at least one of the to-be-sent text content corresponding to the currently to-be-sent task, the task creator identifier corresponding to the currently to-be-sent task, and the task item category corresponding to the currently to-be-sent task; determining a target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user; and sending the to-be-sent text content corresponding to the target task to the terminal device of the target user. This technical solution improves the matching degree between the determined target task and the target user, thereby improving the effect of the task conversion rate.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to a method, apparatus, electronic device, and storage medium for determining a target text. Background Art

[0002] With the increasing development of e-commerce, in order to improve the marketing effect, the marketing method of reaching users by sending text messages is mostly adopted.

[0003] Currently, sending text messages to each user mainly involves: operators selecting user groups in different ways and sending corresponding text messages to the selected users. In this way, there is a situation where a certain user has multiple text message tasks to be sent within a certain time period.

[0004] To avoid the technical problem of poor user experience caused by frequently sending text message tasks to target users within a certain time period. Usually, only one text message task can be sent to the target user within a certain time period. At this time, the text message task sent to the target user is particularly important. Currently, the target text message task is mainly determined according to the time sequence of receiving the text message task, that is, the earliest received text message task is used as the target text message task.

[0005] In the process of implementing the present invention, the inventor found that the prior art has the following problems:

[0006] When sending text message tasks to corresponding users based on the sequence of receiving text message tasks, there is a low matching degree between the sent text message tasks and the users, which further leads to the problem that users will not trigger the text message tasks, resulting in a low conversion rate of text message tasks. Summary of the Invention

[0007] The present invention provides a method, apparatus, electronic device, and storage medium for determining a target task, so as to achieve the technical effect of determining the target task with the best matching degree with the target user from all tasks to be sent, thereby improving the conversion rate of the target task.

[0008] In a first aspect, an embodiment of the present invention provides a method for determining a target task, the method including:

[0009] For each task to be sent, determine the task attribute information of the current task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the task creator identifier corresponding to the current task to be sent, and the task item category corresponding to the current task to be sent;

[0010] Determine a target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user;

[0011] Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0012] In a second aspect, an embodiment of the present invention further provides a device for determining a target task, and the device includes:

[0013] A matching degree determination module, configured to determine, for each task to be sent, task attribute information of the current task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the task creator identifier corresponding to the current task to be sent, and the task item category corresponding to the current task to be sent;

[0014] A target task determination module, configured to determine a target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user;

[0015] A target task sending module, configured to send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, and the electronic device includes:

[0017] One or more processors;

[0018] A storage device, configured to store one or more programs,

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining a target task according to any one of the embodiments of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute the method for determining a target task according to any one of the embodiments of the present invention when executed by a computer processor.

[0021] The technical solution of the embodiment of the present invention can determine the matching degree between each task to be sent and the target user by processing the task attribute information of each task to be sent. Furthermore, based on the matching degree, the target task can be determined from each task to be sent, improving the matching degree between the determined target task and the target user. Again, after determining the target task, the target task can be sent to the terminal corresponding to the target user. Since the matching degree between the target task and the target user is relatively high, the probability that the target user triggers the target task can be increased, thereby improving the task conversion rate and achieving the technical effect of the marketing purpose. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solution of the exemplary embodiment of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the introduced drawings are only the drawings of a part of the embodiments to be described by the present invention, rather than all the drawings. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a schematic flowchart of a method for determining a target task provided by Embodiment 1 of the present invention;

[0024] Figure 2 It is a schematic flowchart of a method for determining a target task provided by Embodiment 2 of the present invention;

[0025] Figure 3 It is a schematic flowchart of a method for determining a target task provided by Embodiment 2 of the present invention;

[0026] Figure 4 It is a schematic flowchart of a method for determining a target task provided by Embodiment 3 of the present invention;

[0027] Figure 5 It is a schematic flowchart of a method for determining a target task provided by Embodiment 3 of the present invention;

[0028] Figure 6 It is a schematic flowchart of a method for determining a target task provided by Embodiment 4 of the present invention;

[0029] Figure 7 It is a schematic flowchart of a method for determining a target task provided by Embodiment 5 of the present invention;

[0030] Figure 8 It is a schematic flowchart of a method for determining a target task provided by Embodiment 6 of the present invention;

[0031] Figure 9 It is a schematic structural diagram of a device for determining a target task provided by Embodiment 7 of the present invention;

[0032] Figure 10 A schematic structural diagram of an electronic device provided in the eighth embodiment of the present invention. Specific implementation manners

[0033] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention rather than all structures are shown in the accompanying drawings.

[0034] Embodiment 1

[0035] Figure 1 A schematic flowchart of a method for determining a target task provided in the first embodiment of the present invention. This embodiment is applicable to the situation where there are multiple tasks to be sent for the same target user, and the matching degree between each task to be sent and the target user can be determined respectively, so as to determine the target task from all tasks to be sent according to the matching degree and send the target task to the terminal device to which the target user belongs. This method can be executed by a device for determining the target task, and this device can be implemented in the form of software and / or hardware.

[0036] As Figure 1 described, the method of this embodiment includes:

[0037] S110. For each task to be sent, determine the task attribute information of the current task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information.

[0038] In this embodiment, the task to be sent can be a short message task. That is, the task to be sent refers to a short message task that needs to be sent to the target user. Since only one short message task can be sent to the user within a preset duration, but the actual number of tasks to be sent corresponding to this user includes multiple, in order to improve the task conversion rate to achieve the marketing purpose, the target task with the best matching degree with the target user can be determined from all tasks to be sent and the target task can be sent to the target user. The matching degree between the task to be sent and the target user can be determined based on the task attribute information of the task to be sent. The matching degree is used to represent the degree of fit between the task to be sent and the target user. Optionally, the higher the matching degree, the better the fit between the task to be sent and the user, and correspondingly, the higher the probability that the user triggers the task to be sent, and the higher the conversion rate of this task.

[0039] It should be noted that the matching degree between each task to be sent and the target user can be determined in the same way. This embodiment takes one task to be sent as an example for introduction.

[0040] Among them, the task attribute information includes at least one of the to-be-sent text content corresponding to the to-be-sent task, the task creator identifier corresponding to the to-be-sent task, and the task item category corresponding to the to-be-sent task.

[0041] Among them, the to-be-sent text content may be the content of a short message. The task creator can create a short message task, and the task creator identifier is the user identifier for creating the short message task. When creating a short message task, the item category corresponding to the short message task can be determined or set, and the item category corresponding to the short message task can be used as the task item category. The task attribute information may include at least one of the above information. If the task attribute information includes one, the corresponding task attribute information can be processed to obtain the matching degree between the to-be-sent task and the target user. If the task attribute information includes multiple of the above information, each task attribute information can be processed separately. After obtaining the matching degrees, all the matching degrees can be integrated to obtain the matching degree between the to-be-sent task and the target user.

[0042] Specifically, for each to-be-sent task, the task attribute information of each to-be-sent task can be determined. By processing each task attribute information, the matching degree between the to-be-sent task and the target user can be determined.

[0043] S120. According to the matching degrees between the to-be-sent tasks and the target user, determine the target tasks corresponding to the target user from the to-be-sent tasks.

[0044] Among them, the matching degree is used to represent the degree of fit between the to-be-sent task and the target user. Optionally, the higher the matching degree, the higher the degree of fit between the user and the to-be-sent task, that is, the higher the probability that the user triggers the to-be-sent task corresponding to the matching degree, and correspondingly, the higher the task conversion efficiency of the to-be-sent task. Therefore, the target tasks can be determined based on the matching degrees between each to-be-sent task and the target user.

[0045] Specifically, after determining the matching degree between each to-be-sent task and the target user, the to-be-sent task corresponding to the highest matching degree can be obtained, and this to-be-sent task can be used as the target task.

[0046] It should be noted that after determining the target tasks, if the number of to-be-sent tasks increases, optionally, new to-be-sent tasks are added. The method provided in this embodiment can be used to determine the matching degrees between each newly added to-be-sent task and the user, and then based on the matching degrees of the newly added to-be-sent tasks and the matching degrees of the original to-be-sent tasks, the target tasks can be determined.

[0047] S130. Send the to-be-sent text content corresponding to the target task to the terminal device of the target user.

[0048] Specifically, after determining the target task, the target task can be sent to the terminal device corresponding to the target user. Since the target task is a text message task, mainly the text content to be sent corresponding to the target task is sent to the terminal device corresponding to the target user. The target user can trigger the text message task received by the terminal device, and when the target user triggers the text message task, the conversion rate of the text message task can be increased.

[0049] The technical solution of the embodiment of the present invention can determine the matching degree between each task to be sent and the target user by processing the task attribute information of each task to be sent, and then determine the target task from each task to be sent based on the matching degree, improving the matching degree between the determined target task and the target user. Moreover, after determining the target task, the target task can be sent to the terminal corresponding to the target user. Since the matching degree between the target task and the target user is relatively high, the probability that the target user triggers the target task can be increased, thereby improving the task conversion rate and achieving the technical effect of the marketing purpose.

[0050] Embodiment 2

[0051] Figure 2 It is a schematic flowchart of a method for determining a target task provided in Embodiment 2 of the present invention. On the basis of the foregoing embodiment, if the task attribute information includes the text content to be sent corresponding to the current task to be sent, the specific implementation manner of S110 for determining the matching degree between the current task to be sent and the target user according to the task attribute information can be referred to in this embodiment. The same or corresponding technical terms as those in the above embodiment will not be elaborated herein.

[0052] Before determining the matching degree between the task to be sent and the target user according to the text content to be sent, the associated words included in each task, and the heat value and effective trigger value corresponding to each associated word can be determined according to the task set including multiple tasks obtained in advance, so that when processing the text content of the task to be sent, the matching degree between the task to be sent and the target user can be determined based on the pre-determined heat value and effective trigger value.

[0053] Optionally, obtain the sent tasks and the total number of sent times within a preset duration, the valid tasks clicked on the sent tasks, and the total number of valid clicks; generate a sample set based on the sent tasks, the total number of sent times, the valid tasks, and the total number of valid clicks; for each sent task in the sample set, process the first text content of the current sent task based on a word segmentation tool, preset stop words, and a preset phrase model to determine the associated vocabulary of the current sent task; generate an associated vocabulary set according to the associated vocabulary of each sent task; for each associated vocabulary in the associated vocabulary set, determine the number of times the current associated vocabulary is sent and the number of valid clicks for at least one sent task to which the current associated vocabulary belongs, determine the heat value of the current associated vocabulary according to the number of times the vocabulary is sent and the total number of sent times, and determine the effective trigger value of the current associated vocabulary according to the number of valid clicks and the total number of valid clicks; determine the total trigger value of the current associated vocabulary according to the total number of valid clicks and the total number of sent times; store each associated vocabulary and the corresponding heat value, effective trigger value, and total trigger value in a preset location to determine the matching degree between the task to be sent and the target user based on the stored heat value, effective trigger value, and total trigger value.

[0054] Among them, the preset duration can be three months, one year, etc., and the operation and maintenance personnel can set the specific duration of the preset duration according to actual needs. The tasks sent within the preset duration are used as a task set. The sent tasks refer to the tasks created by the task creator within the preset duration and sent to the corresponding users. The number of times each sent task is sent can be determined, and by accumulating the number of times each task is sent, the total number of sent times of the sent tasks can be obtained. After the task is sent to the user's corresponding terminal, the user can trigger the task, and the task triggered by the user is used as a valid task. Correspondingly, the number of times the task is triggered in the sent tasks can be determined, and the number of times the task is triggered can be used as the total number of valid clicks. A sample set can be generated based on the sent tasks, the total number of sent times, the valid tasks, and the total number of valid clicks. The word segmentation tool can be an open-source word segmentation component, optionally, Jieba word segmentation, etc. The specific word segmentation tool is not limited here, and the user can set it according to actual needs as long as it can achieve word segmentation. The preset stop words can be pre-set stop words. Based on the preset stop words, meaningless words in the text to be sent can be removed. Optionally, "de, le", etc. The preset phrase model is a model that combines two words into a phrase. The associated vocabulary is the word and / or phrase obtained after processing the first text content. Each sent task has its corresponding associated vocabulary, and an associated vocabulary set including all associated vocabularies can be generated according to the associated vocabulary corresponding to each sent task. The heat value can represent the appearance frequency of each associated vocabulary, and the effective trigger value can represent the probability that the text may be clicked when the word appears in the text. The total trigger value is the probability value that the task is clicked within the preset duration.

[0055] In this embodiment, processing the first text content of the currently sent task based on a word segmentation tool, a preset stop word list, and a preset phrase model to determine the associated words of the currently sent task includes: dividing the first text content into at least one word to be processed based on the word segmentation tool; removing words that are the same as the preset stop words from the at least one word to be processed to obtain at least one word to be used; combining the at least one word to be used into at least one phrase to be used based on the preset phrase model and the position information of the at least one word to be used in the first text content; and determining the associated words of the currently to-be-sent task based on the at least one word to be used and the at least one phrase to be used.

[0056] Among them, the word segmentation tool can be any tool capable of performing word segmentation processing on text content. Based on the word segmentation tool, the first text content can be divided into multiple words to be processed. To improve the effectiveness of the words to be processed, words that are the same as the preset stop words can be removed. For example, if the word to be processed includes "de" and the preset word list also includes "de", then "de" can be deleted. The words to be used are the words obtained by processing the words to be processed based on the preset stop words. The preset phrase model can be a model constructed in a similar bigram manner. Based on the preset phrase model, the words to be used can be constructed to obtain at least one phrase to be used. According to the words to be used and the phrases to be used, the associated words corresponding to the currently sent task can be determined, that is, the associated words include the words to be used and the phrases to be used.

[0057] In this embodiment, constructing the phrases to be used based on the preset phrase model can be: based on the preset phrase model, combining two words to be used with adjacent position information into a phrase to be processed; if the phrase to be processed is consistent with part of the content in the first text content, then the phrase to be processed is used as the phrase to be used.

[0058] Among them, the position information can be the position of the word to be used in the first text content. Adjacent position information can also be understood as two words to be used that are adjacent after word segmentation.

[0059] Specifically, based on the preset phrase model, two words to be used with adjacent position information can be combined / concatenated into a phrase to be used. After obtaining the phrase to be used, it can be determined whether there is a word in the first text content that is consistent with the phrase to be used. If so, it is retained; if not, this phrase to be used can be deleted. The reason for this setting is to avoid the situation where non-adjacent word segmentation results are concatenated into phrases due to the filtering of stop words and the like.

[0060] Specifically, within one year, obtain the sent tasks sent by the system to the user and the total number of sent times corresponding to all sent tasks. At the same time, determine the number of times the user triggers all sent tasks, that is, the total number of effective clicks. For each sent task, the first text content corresponding to the current sent task can be obtained, and the first text content is divided into multiple words to be processed by a word segmentation tool; based on the preset stop words, the preset stop words in the multiple words to be processed are deleted, and the remaining words to be processed are used as words to be used. Based on the preset phrase model, two adjacent words to be used are spliced into a phrase to be processed. When there is a phrase in the first text content that is the same as the phrase to be processed, the phrase to be processed is used as the word to be used. Correspondingly, if there is no phrase in the first text content that is the same as the phrase to be processed, the phrase to be processed is deleted. The words to be used and the phrases to be used of each sent task can be used as associated words, and an associated word set can be generated based on the associated words of each sent task. For each associated word in the associated word combination, the popularity value of the associated word can be determined according to the word sending times of the sent task to which the associated word belongs and the total sending times of all tasks; according to the effective click times of the sent task to which the associated word belongs and the total effective click times, the effective trigger value of the current associated word can be determined. The associated words, the popularity values and the effective trigger values corresponding to the associated words can be stored in a preset storage location correspondingly, so that when the task attribute information includes the text content to be sent, the target associated words included in the text content can be determined, and then the popularity values and the effective trigger values corresponding to the target associated words can be retrieved, and then the matching degree between the task to be sent and the target user can be determined.

[0061] That is to say, through preprocessing the sent task information within a preset duration in this embodiment, the popularity value and the effective trigger value of the associated words included in all task information can be determined. Based on the associated value and the effective trigger value, the matching degree between each task to be sent and the target user can be determined, improving the technical effects of the convenience and efficiency of determining the matching degree.

[0062] Based on the above technical solution, after determining the popularity value and the effective trigger value of each associated word, the matching degree between the task to be sent and the target user can be determined according to the pre-determined popularity value and the effective trigger value.

[0063] As Figure 2 shown, the method includes:

[0064] S210. Determine at least one target associated word corresponding to the text content to be sent.

[0065] Among them, since the task to be sent is a text message task, each task to be sent has corresponding text, and this text can be used as the content of the text to be sent. Based on a word segmentation tool, the text to be sent can be divided into multiple words, and the words without actual meaning in the multiple words are deleted. Optionally, words such as "de", "ne" are deleted to obtain the target words to be used. Based on a preset phrase model, adjacent target words to be used are combined into target phrases to be processed. It is detected whether the content of the text to be sent includes the target phrases to be processed. If so, the target phrases to be processed are used as the target words to be used. If not, the target phrases to be processed are deleted. Based on the target words to be used and the target phrases to be used, the target associated words of the content of the text to be sent are determined.

[0066] S220. For each target associated word, retrieve the heat value and effective trigger value corresponding to the current target associated word from the preset positions.

[0067] Among them, the number of target associated words can be one or more. The heat value and effective trigger value of each target associated word can be determined respectively. The preset positions can be understood as the storage positions for storing associated words, the heat values corresponding to the associated words, and the effective trigger values. The heat values and effective trigger values corresponding to the associated words are determined in advance.

[0068] Specifically, for each target associated word, the heat value and effective trigger value corresponding to the current target associated word can be retrieved from the preset positions. That is, the heat values and effective trigger values corresponding to each target word to be used and target phrase to be used are retrieved from the preset positions.

[0069] S230. Determine the matching degree between the current task to be sent and the target user according to the heat values, effective trigger values, and total trigger values of each target associated word.

[0070] Specifically, after determining the heat value and effective trigger value of each target associated word, the matching degree between the current task to be sent and the target user can be determined according to the heat values, effective trigger values, and total trigger values of all target associated words.

[0071] Optionally, according to the effective trigger value of each target associated word and the total trigger value, determine a first intermediate processing value corresponding to the current task to be sent; according to the heat values of each target associated word, determine a second intermediate processing value of the current task to be sent; based on the first intermediate processing value and the second intermediate processing value, determine the matching degree between the current task to be sent and the target user.

[0072] Among them, the first intermediate processing value is determined based on the effective trigger value and the total trigger value of each target associated word. Optionally, the first intermediate processing value is determined according to the product of the effective trigger values of each target associated word and the product of the total trigger values. The second intermediate processing value is determined according to the popularity value of each target associated word. Optionally, the second intermediate processing value is determined based on the product of the popularity values of each target associated word. The matching degree can be determined based on the ratio of the first intermediate processing value to the second intermediate processing value.

[0073] In this embodiment, if the task attribute information includes the text content to be sent corresponding to the current task to be sent, the matching degree between the current task to be sent and the target user can be determined in the above manner. Other tasks to be sent can use the same method to determine their matching degrees with the target user.

[0074] S240. Determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user.

[0075] S250. Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0076] The technical solution of the embodiment of the present invention can determine the fit degree between the task to be sent and the target user by processing the text content to be sent of the task to be sent, so as to send the task to be sent with the highest fit degree to the target user, improve the matching degree between the target user and the target task, and thus improve the probability of the target user triggering the target task and the technical effect of the task conversion rate.

[0077] As an optional embodiment of the above embodiment, Figure 3 It is a schematic flowchart of a method for determining a target task provided in the second embodiment of the present invention. Among them, the same or corresponding technical terms as those in the above embodiment will not be elaborated here.

[0078] As Figure 3 shown, the method further includes:

[0079] S310. Start.

[0080] It can be understood as starting to determine the matching degree between the task to be sent and the target user.

[0081] S320. Use ANSJ to perform word segmentation processing on the short message text.

[0082] Among them, ANJS can be understood as an open-source word segmentation tool. Based on this open-source word segmentation tool and the stop words in the preset stop word library, the short message text can be segmented. The short message text can be understood as the first text content corresponding to the sent task.

[0083] Specifically, based on ANJS to process the SMS text, at least one word to be processed corresponding to the SMS text can be determined. Based on the stop words in the preset stop word library, the stop words in the words to be processed are removed, and the remaining words to be processed are the words to be used, that is, the word segmentation result corresponding to the SMS text is obtained.

[0084] S330. Construct phrases using the bigram method.

[0085] Specifically, according to the word segmentation result, the bigram method similar to the binary model can be used for phrase construction. For example, the first text content is "I like this type of house". Based on the ANJS word segmentation tool and the preset stop words, the word segmentation result includes "like, house type, house". Using the bigram method, two adjacent words can be concatenated together, and the constructed phrases include "like house type, house type house". It can be judged whether the first text content includes the constructed phrases. If so, the phrase can be retained; otherwise, the phrase is deleted. The first text content does not include "like house type" and "house type house", so there are no phrases to be used corresponding to the first text content. The words to be used corresponding to the first text content are "like, house type, house", that is, the associated words are "like, house type, house".

[0086] S340. Statistically calculate the heat value and effective trigger value of each word and phrase.

[0087] Statistically calculating the heat value and effective trigger value of each word and phrase can be to obtain the historical SMS task sending data and click data for one year, and statistically calculate the heat value and effective trigger value of each word to be used and each phrase to be used in each SMS task, that is, the heat value and effective trigger value of the associated words corresponding to each SMS task. Among them, the heat value can be understood as the occurrence frequency of the associated words, and the effective trigger value can be understood as the frequency at which the sent tasks including the effective words are triggered.

[0088] Based on S330, the associated words corresponding to each sent task can be determined. The associated words include the words to be used and the phrases to be used. After determining the associated words corresponding to each sent task, the heat value and effective trigger value corresponding to each associated word can be determined.

[0089] Exemplarily, for each associated term, the number of times A that the current associated term belongs to the sent tasks can be determined. According to the ratio of the number of times A to the total number of times B of all sent tasks, the heat value P(associated term) of the current associated term can be determined. This way can be used to determine the heat values of each associated term. Determine the number of times D that the sent task to which the current associated term belongs is clicked, and the total number of effective clicks E. According to the ratio of the number of times D that the task is clicked to the total number of effective clicks E, the effective trigger value P(associated term / trigger) of the current associated term can be determined. According to the total number of effective clicks and the total number of sent times, the total trigger value P(total) can be determined. The above method is used to determine the heat value and the effective trigger value of each associated term respectively.

[0090] After determining the heat values and the effective trigger values of each associated term, the corresponding relationship among the associated term, the heat value, and the effective trigger value can be established and stored at a preset location. When the task attribute information includes the text content to be sent, based on the corresponding relationship stored at the preset location, the matching degree between the text content to be sent and the target user can be determined, and then the target task corresponding to the target user can be determined.

[0091] S350. For the current task to be sent, according to the heat value and the effective trigger value corresponding to the current task to be sent, determine the matching degree between the current text to be sent and the target user.

[0092] Specifically, the text content to be sent of the current task to be sent can be obtained. Based on the word segmentation tool, it can be determined that the target associated terms included in the text content to be sent are A, B, C, and D respectively. Based on the heat values and the effective trigger values corresponding to each associated term stored at the preset location, the heat values of the target associated terms can be determined respectively, that is, the occurrence probability values are P(A), P(B), P(C), and P(D), and the effective trigger values of the associated terms are P(A\trigger), P(B\trigger), P(C\trigger), and P(D\trigger).

[0093] Based on the formula P = [P(A\trigger) * P(B\trigger) * P(C\trigger) * P(D\trigger) * P(total)] / [P(A) * P(B) * P(C) * P(D)], the matching degree between the current task to be sent and the target user can be determined. S340 can be repeatedly executed to determine the matching degrees between each task to be sent and the target user.

[0094] It should be noted that since the matching degree at this time is determined based on the text content to be sent, the matching degree obtained at this time can be understood as the quality value of the short message text.

[0095] S360. Determine the target task from the tasks to be sent according to the matching degree, and send the target task to the terminal device corresponding to the target user.

[0096] After determining the matching degree between each task to be sent and the target user, the target task can be determined from all tasks to be sent according to the matching degree, and the target task is sent to the terminal device corresponding to the target user.

[0097] It should be noted that if the task attribute information only includes the text content to be sent corresponding to the task to be sent, the target task corresponding to the target user can be directly determined based on the matching degree.

[0098] The technical solution of the embodiment of the present invention can determine the matching degree between the text content to be sent and the target user by processing the text content to be sent of each task to be sent, and then determine the target task from all tasks to be sent based on the matching degree, improving the matching degree between the determined target task and the user, thereby improving the technical effect of the task conversion rate.

[0099] Embodiment III

[0100] Figure 4 It is a schematic flowchart of a method for determining a target task provided by Embodiment III of the present invention. On the basis of the foregoing embodiment, the text content to be sent may further include preferential vocabulary information. If the preset preferential vocabulary information is included, the matching degree can be updated on the basis of determining the matching degree between the task to be sent and the user according to the text content to be sent. Wherein, the same or corresponding technical terms as those in the above embodiments are not described herein again.

[0101] As Figure 4 shown, the method includes:

[0102] S410. For each task to be sent, determine the task attribute information of the current task to be sent.

[0103] S420. According to the text content to be sent included in the task attribute information and each feature vocabulary in the feature vocabulary library, determine the target feature vocabulary included in the text to be sent.

[0104] Wherein, each feature vocabulary in the feature vocabulary library is preset. The feature vocabulary included in the text content to be sent can be determined according to each feature vocabulary included in the feature vocabulary library, and the feature vocabulary included in the text content to be sent is used as the target feature vocabulary.

[0105] S430. According to the corresponding relationship established in advance between the feature vocabulary and the feature vocabulary evaluation value, determine the feature evaluation value of each target feature vocabulary.

[0106] Among them, the characteristic word evaluation value is used to represent the popularity value corresponding to the word. The characteristic word library includes multiple characteristic words and the corresponding characteristic evaluation values for each characteristic word. According to the corresponding relationship, the characteristic word evaluation value corresponding to each characteristic word can be determined. Based on this characteristic word evaluation value, the matching degree between the text content to be sent and the target user can be determined.

[0107] In this embodiment, establishing the corresponding relationship between each characteristic word in the characteristic word library and the characteristic word evaluation value can be as follows: for each valid task, according to a pre-set rule template, extract the characteristic words corresponding to the current valid task from the second text corresponding to the current valid task, and form the characteristic word library according to the characteristic words of each valid task; according to each characteristic word, based on the effective click times and the total effective click times corresponding to the current characteristic word, obtain the characteristic word evaluation value of the current characteristic word; establish the corresponding relationship between each characteristic word and the corresponding characteristic word evaluation value, so as to determine the characteristic evaluation value corresponding to the target characteristic word based on the corresponding relationship.

[0108] Among them, the valid task can be the task that the user clicks. The rule template is pre-set and can be a rule template abstracted from the text content of each completed task. In this embodiment, the abstracted rule template can include the following three categories:

[0109] a. Full reduction type: The rule template for the preferential information with full reduction, such as: "Full * minus *";

[0110] b. Discount type: The rule template for the preferential information with discount strength, such as: "* discount";

[0111] c. Quota type: The preferential information rule module with preferential amount: such as: "* coupon", "* yuan".

[0112] According to the regular expression grammar, the regular expression corresponding to the preferential information rule template can be:

[0113] a. "Full * minus *": "\d+ minus \d+", "\d+ yuan minus \d+", etc.

[0114] b. "* discount": "\d+ discount", "\d+ off", etc.

[0115] c. "* coupon", "* yuan": "\d+ coupon", "\d+ yuan", etc.

[0116] Each preferential word in the above expressions can be used as a characteristic word.

[0117] The second text content may be the text content corresponding to a valid task. The characteristic vocabulary refers to the vocabulary including the above-mentioned preferential vocabulary. A characteristic vocabulary library can be formed according to the characteristic vocabulary of each valid task, that is, the characteristic vocabulary library includes the characteristic vocabulary corresponding to each valid task.

[0118] According to the tasks sent within the preset duration and the valid tasks in the second embodiment, the effective click times of the task to which the characteristic vocabulary belongs and the total effective click times of all sent tasks can be determined. According to the effective click times and the total effective click times, the characteristic vocabulary evaluation value of the characteristic vocabulary can be determined. After determining the characteristic evaluation value corresponding to the characteristic vocabulary, a correspondence relationship is established between the characteristic evaluation value and the corresponding characteristic vocabulary, so that when the text content to be sent includes the text content to be sent in the task attribute information, it can be determined whether the text content to be sent includes the characteristic vocabulary, and the matching degree of the task to be sent to which the text content to be sent belongs is updated according to the characteristic evaluation value corresponding to the characteristic vocabulary.

[0119] S440. Determine the matching degree between the current task to be sent and the target user according to the characteristic evaluation value.

[0120] After determining the characteristic vocabulary included in the text content to be sent and the corresponding characteristic vocabulary evaluation value, the matching degree between the current task to be sent and the target user can be determined according to the characteristic vocabulary evaluation value.

[0121] It should be noted that for other tasks to be sent, S410 to S440 can be repeatedly executed to determine the matching degree between each task to be sent and the target user.

[0122] S450. Determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user.

[0123] S460. Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0124] The technical solution of the embodiment of the present invention, by pre-determining the correspondence relationship between the characteristic vocabulary and the corresponding characteristic vocabulary evaluation value, can determine the characteristic vocabulary included in the text content to be sent and the corresponding characteristic vocabulary evaluation value according to the correspondence relationship, and then determine the matching degree between the task to be sent and the target user based on the characteristic vocabulary evaluation value. When determining the target task based on the matching degree, the matching degree between the target task and the user and the technical effect of the task conversion rate are improved.

[0125] As an optional embodiment of the above embodiment, Figure 5 It is a schematic flowchart of a method for determining a target task provided by the third embodiment of the present invention. As Figure 5 shown, the method includes:

[0126] S510. Start.

[0127] S520. Determine a rule template according to the text content corresponding to the sent task.

[0128] Among them, the rule template can be a preferential information template.

[0129] Specifically, each sent task has corresponding text content, and a preferential template can be determined for the text content. Optionally, full reduction, discount, coupon, yuan, etc.

[0130] S530. Extract corresponding feature words based on the rule template.

[0131] Specifically, based on the determined preferential information template, a regular expression corresponding to the preferential information template can be determined. Optionally, "full reduction": "\d+ reduction", "\d+ yuan reduction \d+", "discount": "\d+ discount", "\d+ percent off", "coupon", "yuan": "\d+ coupon", "\d+ yuan". Each word in the above expressions can be used as a feature word. For example, "full reduction" can be used as a feature word.

[0132] S540. Determine the feature evaluation value corresponding to the feature word, and establish a correspondence between the feature word and the feature word evaluation value.

[0133] After determining the feature word, according to the total number of valid clicks corresponding to the sent task and the number of clicks corresponding to each sent task to which the feature word belongs, the feature word evaluation value of each feature word can be determined. Optionally, the ratio of the number of clicks A corresponding to the sent task to which the feature word M belongs to the total number of valid clicks B is the feature word evaluation value corresponding to the feature word M.

[0134] After determining the feature word and the feature word evaluation value, a correspondence between each feature word and the feature word evaluation value can be established, so that when determining the target task, the feature word evaluation value can be retrieved based on the correspondence, and then the matching degree between the task to be sent and the target user can be determined based on the feature word evaluation value, so as to determine the target task according to the matching degree.

[0135] S550. Determine the feature words included in the text content to be sent of the current task to be sent, and determine the feature word evaluation value of the feature word according to the correspondence.

[0136] Specifically, determine the feature words included in the text content to be sent, and retrieve the feature word evaluation value corresponding to the current feature word according to the pre-established correspondence.

[0137] S560. Determine the matching degree between the current task to be sent and the target user according to the characteristic word evaluation value of each characteristic word.

[0138] Exemplarily, if the text content to be sent includes five characteristic words A, B, C, D, and E, the characteristic word evaluation values T(A), T(B), T(C), T(D), and T(E) of the five characteristic words can be determined respectively based on the corresponding relationship. According to T(A), T(B), T(C), T(D), and T(E), the matching degree between the current task to be sent and the target user can be determined.

[0139] It should be noted that S510 to S560 can be repeatedly executed to determine the matching degree between each task to be sent and the target user.

[0140] S570. Determine the target task according to the matching degree and send the target task to the target terminal.

[0141] Exemplarily, the task corresponding to the highest matching degree can be used as the target task, and the target task can be sent to the target terminal corresponding to the target user.

[0142] Embodiment 4

[0143] Figure 6 It is a schematic flowchart of a method for determining a target task provided by Embodiment 4 of the present invention. On the basis of the foregoing embodiments, the task attribute information further includes the task creator identifier corresponding to the current task to be sent. For the specific implementation manner of determining the matching degree between the current task to be sent and the target user according to the task attribute information, reference can be made to the detailed introduction of the technology of this embodiment. Among them, the same or corresponding technical terms as those in the above embodiments will not be described herein again.

[0144] As Figure 6 shown, the method includes:

[0145] S610. For each task to be sent, determine the task attribute information of the current task to be sent.

[0146] Among them, the task attribute information may be the task creator identifier corresponding to the current task to be sent. Each task has a task creator. In order to distinguish different task creators, the task creator can be marked, and this mark can be used as the task creator identifier.

[0147] S620. According to the mapping relationship established in advance between the task creator identifier and the creator task conversion value, determine the creator task conversion value corresponding to the task creator identifier, and determine the matching degree between the current task to be sent and the target user based on the creator task conversion value.

[0148] Among them, after the task creator finishes creating a task, the created task can be sent to the corresponding user. The creator task conversion value can be understood as whether the user clicks after the task is sent to the user. The conversion value of the task is determined according to the click-through rate of the user, and the creator task conversion value is determined according to the conversion value of the task. The mapping relationship includes the corresponding relationship between the task creator identifier and the creator task conversion value.

[0149] Specifically, the creator identifier corresponding to the task to be sent can be determined, and the corresponding creator task conversion value can be retrieved from the mapping relationship according to the creator identifier. The matching degree between the current task to be sent and the target user is determined according to the creator task conversion value.

[0150] Correspondingly, other tasks to be sent can also use the above method to determine the matching degree with the target user.

[0151] Based on the above technical solution, a mapping relationship between the task creator identifier and the creator task conversion value can be established. Optionally, for each creator identifier, the created tasks and the number of created tasks corresponding to the current creator identifier are determined from the tasks sent within the preset time period; for each created task, the task click-through rate of the current created task is determined according to the task click volume corresponding to the current created task and the number of times the current created task is sent; according to the task click-through rate and the number of created tasks of each created task, the creator task conversion value of the current creator identifier is determined; a mapping relationship between the creator identifier and the creator task conversion value is established to obtain the creator task conversion value corresponding to the creator identifier from the mapping relationship according to the creator identifier to which the current task to be sent belongs.

[0152] Among them, the number of created tasks is the number of tasks established within the preset time period. Optionally, according to the tasks sent within the preset time period, the number of tasks created by each task creator is determined. The task click volume can be the number of times triggered after the task is sent to the user. The task click-through rate can be determined according to the total number of times a certain task is sent and the number of times the task is clicked.

[0153] Specifically, for each creator identifier, the number of tasks corresponding to the preset duration and the current creator identifier, as well as the sent tasks, can be obtained. For each sent task, determine the number of times the current sent task has been sent and the number of times it has been clicked. Based on the number of times it has been clicked and the number of times it has been sent, determine the click-through rate of the task. Based on the click-through rates and the number of tasks of all sent tasks, the task conversion value of the creator can be determined. After determining the creator task conversion value corresponding to each creator identifier, a mapping relationship can be established between the creator identifier and the creator task conversion value, so that when the creator identifier is included in the task attribute information of the task to be sent, based on the mapping relationship, the creator task conversion value corresponding to the creator identifier can be determined, and then based on the creator task conversion value, the matching degree between the target task and the target user can be determined.

[0154] S630. Determine a target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user.

[0155] S640. Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0156] As an optional embodiment of the above embodiment, the creator task conversion value corresponding to each task creator can be determined first, and a corresponding relationship between the creator task conversion value and the creator identifier can be established. So that when the creator identifier is included in the task attribute information, the matching degree between the task to be sent and the target user can be determined based on the corresponding relationship.

[0157] Specifically, for each task creator, the number of tasks created and sent by the task creator within the preset duration, the task click volume of the sent tasks, and the task sending times of each task can be determined. Based on the task click volume of each task and the task sending times of the task, the task click-through rate of the task can be determined. Based on the task click-through rate of each task and the total number of created tasks corresponding to the creator identifier, the creator task conversion value corresponding to the creator identifier can be determined.

[0158] Exemplarily, the number of tasks created by the creator with the creator identifier A within one year is 5, and the sending times of each task are A1, A2, A3, A4, A5 respectively. The number of times each task is clicked, B1, B2, B3, B4, B5, can be determined. Based on the number of times each task is clicked and the corresponding sending times, the task click-through rate of each task can be determined. Based on the ratio between the task click-through rate of each task and the total number of tasks, the creator task conversion value S corresponding to the creator identifier A is determined. Optionally, the formula S = (the click-through rate of each created task corresponding to the creator identifier) / the number of created tasks is used.

[0159] In the technical solution of the embodiment of the present invention, by processing the attribute information of the task to be sent, the creator identifier to which the task to be sent belongs can be determined, and the creator task conversion value corresponding to the creator identifier can be determined. According to the creator task conversion value, the matching degree between the task to be sent and the target user is determined, and based on the matching degree, the target task that fits the target user is determined, which improves the matching degree between the target task and the target user, thereby improving the technical effect of the user experience.

[0160] Embodiment 5

[0161] Figure 7 It is a schematic flowchart of a method for determining a target task provided by Embodiment 5 of the present invention. On the basis of the foregoing embodiments, the task attribute information may further include: the task item category corresponding to the current task to be sent. For the specific implementation manner of determining the matching degree between the current task to be sent and the target user according to the task attribute information, reference may be made to the technical solution of this embodiment. Among them, the same or corresponding technical terms as those in the above embodiments will not be described in detail herein.

[0162] As Figure 7 shown, the method includes:

[0163] S710. For each task to be sent, determine the task attribute information of the current task to be sent.

[0164] It should be noted that when the task creator creates a task, the item category corresponding to the task can be set in advance, and the item category corresponding to the task can be called the task item category.

[0165] S720. According to the task item category corresponding to the current task to be sent, determine the matching degree between the current task to be sent and the target user.

[0166] Among them, the task item category refers to the item category set when creating the current task to be sent and corresponding to the current task to be sent.

[0167] In this embodiment, determining the matching degree between the current task to be sent and the target user according to the task item category may be: obtaining the target item category associated with the target user, and determining the category association matching value according to the target item category and the task item category; determining the category association coefficient value according to the number of task categories of the task item category and the number of target categories including the target item category in the task item category; and determining the matching degree between the current task to be sent and the target user according to the category association matching value and the category association coefficient value.

[0168] Among them, when creating a task, the third-level category involved in the task can be determined, and the involved third-level category can be used as the task item category. At the same time, the target item category corresponding to the target user can be obtained, that is, the item category preferred by the target user. The association matching value refers to the matching degree between the task item category and the target item category. According to the task item category, the corresponding number of task categories can be determined, and according to the target item category, the corresponding number of target categories can be determined. Determine the number of target categories included in the number of task categories, and determine the category association value according to the included quantitative relationship. According to the category association value and the category association matching value, the matching degree between the currently to-be-sent task and the target user can be determined.

[0169] In this embodiment, determining the category association matching value according to the target item category and the task item category includes: determining the task third-level categories included in the task item category and the target third-level categories corresponding to the target item category; determining the target third-level categories included in the task third-level categories to obtain the matching third-level categories; respectively determining the matching values corresponding to each matching third-level category, and taking the largest matching value as the category association matching value.

[0170] Specifically, to determine the category association matching value, the third-level categories of the task item category and the target item category can be matched, and the largest value among all the hit category preferences is taken, and the determined value is used as the category association matching value.

[0171] It should be noted that the smaller the number corresponding to the task item category, the higher the matching association value. The category association value can be determined according to the number of target item categories included in the task item category. Optionally, the formula category association value = 1 / log2(1 + the number of third-level categories corresponding to the task item category / the number of target item categories included in the task item category) is used. In this embodiment, the matching degree between the currently to-be-sent task and the target user can be determined according to the product of the category association matching value and the category association value.

[0172] S730. Determine the target task corresponding to the target user from each to-be-sent task according to the matching degree between each to-be-sent task and the target user.

[0173] S740. Send the to-be-sent text content corresponding to the target task to the terminal device of the target user.

[0174] The technical solution of the embodiment of the present invention can determine the matching degree between the to-be-sent task and the target user by determining the relationship between the task item category and the target item category, and then determine the target task corresponding to the target user based on the matching degree, improving the probability of the target task being triggered, thereby achieving the technical effect of the marketing purpose.

[0175] Embodiment Six

[0176] Figure 8 FIG. is a schematic flowchart of a method for determining a target task provided in Embodiment Six of the present invention. On the basis of the foregoing embodiments, the task attribute information may include multiple items such as the text content to be sent corresponding to the current task to be sent, the identifier of the task creator corresponding to the current task to be sent, and the category of task items corresponding to the current task to be sent. When the number of items in the task attribute information is multiple, the specific implementation manner of determining the matching degree between the current task to be sent and the target user according to the task attribute information can refer to the technical solution of this embodiment. Among them, the same or corresponding technical terms as those in the above embodiments will not be described in detail herein.

[0177] As Figure 8 shown, the method includes:

[0178] S810. For each task to be sent, determine the task attribute information of the current task to be sent.

[0179] Among them, the task attribute information may include multiple items such as the text content to be sent corresponding to the current task to be sent, the identifier of the task creator corresponding to the current task to be sent, and the category of task items corresponding to the current task to be sent.

[0180] S820. Determine the matching degree between the current task to be sent and the target user according to the matching degree corresponding to at least one task attribute information.

[0181] When the number of task attribute information items is multiple, each task attribute information can be processed separately, and the matching degree corresponding to each task attribute information can be obtained separately. According to the matching degrees corresponding to each task attribute information, the matching degree between the current task to be sent and the target user can be obtained.

[0182] In this embodiment, determining the matching degree between the current task to be sent and the target user according to the matching degree corresponding to at least one task attribute information includes: determining the matching degree between the current task to be sent and the target user according to the weight value and the matching degree corresponding to each task attribute information.

[0183] Among them, the weight value corresponding to each task attribute information can be set in advance. Optionally, set the weight value corresponding to the text content to be sent as A, the weight value corresponding to the identifier of the task creator corresponding to the current task to be sent as B, and the weight value corresponding to the category of task items corresponding to the current task to be sent as C. According to the matching degree corresponding to each task attribute information and the weight value corresponding to each task attribute information, the matching degree between the current task to be sent and the target user can be determined.

[0184] Exemplarily, the weight value corresponding to the text content to be sent is A, and the corresponding matching degree is P(A). The weight value corresponding to the creator identifier is B, and the corresponding matching value is T(B). The weight value corresponding to the task item category is C, and the corresponding matching value is S(C). Based on the above values, the matching degree corresponding to the current task to be sent is determined as: A * P(A) + B * T(B) + C * S(C).

[0185] S830. Determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user.

[0186] Specifically, by repeatedly executing the above steps, the matching degree of each task to be sent can be determined. According to the matching degree between each task to be sent and the target user, the target task corresponding to the target user can be determined from each task to be sent.

[0187] In this embodiment, determining the target task corresponding to the target user according to the matching degree may be: determining the task to be sent corresponding to the highest matching degree according to the matching degree between each task to be sent and the target user, and using the task to be sent as the target task corresponding to the target user.

[0188] Specifically, according to the matching degree of each task to be sent, the task to be sent with the highest matching degree can be used as the target task corresponding to the target user.

[0189] The advantage of determining the target task in this way is that the task with the highest fit with the target user can be screened out from all tasks to be sent. When this task is sent to the corresponding target user, the probability of the target user triggering the target task can be increased, thereby improving the task conversion rate and achieving the technical effect of the marketing purpose.

[0190] S840. Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0191] The technical solution of the embodiment of the present invention can determine the matching degree between the task to be sent and the target user by processing multiple task attribute information corresponding to each task to be sent, and then send the task to be sent with the highest matching degree to the target user, improving the fit between the determined target task and the user, thereby improving the task trigger probability and further improving the technical effect of the task conversion rate.

[0192] Embodiment Seven

[0193] Figure 9 FIG. 9 is a schematic structural diagram of a device for determining a target task provided in Embodiment Seven of the present invention. The device includes: a matching degree determination module 910, a target task determination module 920, and a target task sending module 930.

[0194] Among them, the matching degree determination module 910 is used to determine the task attribute information of each task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the task creator identifier corresponding to the current task to be sent, and the task item category corresponding to the current task to be sent; the target task determination module 920 is used to determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user; the target task sending module 930 is used to send the text content to be sent corresponding to the target task to the terminal device of the target user. On the basis of the above, the device further includes:

[0195] The sample set generation module is used to obtain the sent tasks and the total number of sendings within a preset time period, the effective tasks clicked on the sent tasks and the total number of effective clicks; generate a sample set based on the sent tasks, the total number of sendings, the effective tasks, and the total number of effective clicks; the associated vocabulary set generation module is used to process the first text content of the current sent task for each sent task in the sample set based on a word segmentation tool, a preset stop word list, and a preset phrase model to determine the associated vocabulary of the current sent task; generate an associated vocabulary set according to the associated vocabulary of each sent task; the associated value determination module is used to determine the number of times a current associated vocabulary is sent and the number of effective clicks of at least one sent task to which the current associated vocabulary belongs for each associated vocabulary in the associated vocabulary set, determine the heat value of the current associated vocabulary according to the number of times the vocabulary is sent and the total number of sendings, determine the effective trigger value of the current associated vocabulary according to the number of effective clicks and the total number of effective clicks; determine the total trigger value of the current associated vocabulary according to the total number of effective clicks and the total number of sendings; the storage module is used to store each associated vocabulary and the corresponding heat value, effective trigger value, and total trigger value at a preset position to determine the matching degree between the task to be sent and the target user according to the stored heat value, effective trigger value, and total trigger value.

[0196] On the basis of the above technical solutions, the associated vocabulary set generation module further includes:

[0197] A vocabulary-to-be-used determination unit, configured to divide the first text content into at least one vocabulary to be processed based on a word segmentation tool; remove the vocabulary that is the same as the preset stop vocabulary from the at least one vocabulary to be processed, so as to obtain at least one vocabulary to be used; a phrase-to-be-used determination unit, configured to combine the at least one vocabulary to be used into at least one phrase to be used based on the preset phrase model and the position information of the at least one vocabulary to be used in the first text content; an associated vocabulary determination unit, configured to determine the associated vocabulary of the current task to be sent based on the at least one vocabulary to be used and the at least one phrase to be used.

[0198] Based on the above technical solutions, the phrase-to-be-used determination unit includes a to-be-processed phrase determination subunit, configured to combine two adjacent vocabulary to be used into a to-be-processed phrase based on a preset phrase model; the to-be-used phrase determination subunit is configured to, if the to-be-processed phrase is consistent with a part of the first text content, use the to-be-processed phrase as the phrase to be used.

[0199] Based on the above technical solutions, the matching degree determination module is further configured to: determine at least one target associated vocabulary corresponding to the text content to be sent; for each target associated vocabulary, retrieve the heat value and the effective trigger value corresponding to the current target associated vocabulary from the preset positions; determine the matching degree between the current task to be sent and the target user according to the heat values, the effective trigger values, and the total trigger value of the respective target associated vocabulary.

[0200] Based on the above technical solutions, the matching degree determination module is further configured to: determine a first intermediate processing value corresponding to the current task to be sent according to the effective trigger value and the total trigger value of each target associated vocabulary; determine a second intermediate processing value of the current task to be sent according to the heat values of the respective target associated vocabulary; determine the matching degree between the current task to be sent and the target user based on the first intermediate processing value and the second intermediate processing value.

[0201] Based on the above technical solutions, the matching degree determination module is further configured to: determine the target feature vocabulary included in the text to be sent according to each feature vocabulary in the feature vocabulary library;

[0202] Determine the feature evaluation value of each target feature vocabulary according to the corresponding relationship established in advance between the feature vocabulary and the feature vocabulary evaluation value;

[0203] Determine the matching degree between the current task to be sent and the target user according to the feature evaluation value.

[0204] Based on the above technical solutions, the device further includes a correspondence establishing module, configured to: establish a correspondence between feature words and feature word evaluation values;

[0205] The establishing of the correspondence between feature words and feature word evaluation values includes:

[0206] For each valid task, according to a pre-set rule template, extract the feature words corresponding to the current valid task from the second text corresponding to the current valid task, and form the feature word library according to the feature words of each valid task; for each feature word, based on the effective click times and the total number of effective clicks corresponding to the current feature word, obtain the feature word evaluation value of the current feature word; establish the correspondence between each feature word and the corresponding feature word evaluation value, so as to determine the feature evaluation value corresponding to the target feature word based on the correspondence.

[0207] Based on the above technical solutions, the matching degree determining module is further configured to: determine the creator task conversion value corresponding to the task creator identifier according to the pre-established mapping relationship between the task creator identifier and the creator task conversion value, and determine the matching degree between the current task to be sent and the target user based on the creator task conversion value.

[0208] Based on the above technical solutions, the device further includes a mapping relationship establishing module, configured to: establish a mapping relationship between a task creator identifier and a creator task conversion value;

[0209] The establishing of the mapping relationship between the task creator identifier and the creator task conversion value includes:

[0210] For each creator identifier, determine the created tasks and the number of created tasks corresponding to the current creator identifier from the tasks that have been sent within a preset time period; for each created task, determine the task click-through rate of the current created task according to the task click volume corresponding to the current created task and the number of times the current created task has been sent; according to the task click-through rate of each created task and the number of created tasks, determine the creator task conversion value of the current creator identifier;

[0211] Establish a mapping relationship between the creator identifier and the creator task conversion value, so as to obtain the creator task conversion value corresponding to the creator identifier from the mapping relationship according to the creator identifier to which the current task to be sent belongs.

[0212] Based on the above technical solutions, the task attribute information includes the task item category corresponding to the currently to-be-sent task. The matching degree determination module is further configured to: obtain the target item category associated with the target user, and determine a category association matching value according to the target item category and the task item category;

[0213] Determine a category association coefficient value according to the number of task categories of the task item category and the number of target categories including the target item category in the task item category;

[0214] Determine the matching degree between the currently to-be-sent task and the target user according to the category association matching value and the category association coefficient value.

[0215] Based on the above technical solutions, the matching degree determination module is further configured to: determine the task third-level categories included in the task item category and the target third-level category corresponding to the target item category; determine the target third-level categories included in the task third-level categories to obtain matching third-level categories; respectively determine the matching values corresponding to each matching third-level category, and use the largest matching value as the category association matching value.

[0216] Based on the above technical solutions, the matching degree determination module is further configured to: determine the matching degree between the currently to-be-sent task and the target user according to the matching degrees corresponding to at least one task attribute information.

[0217] Based on the above technical solutions, the matching degree determination module is further configured to: determine the matching degree between the currently to-be-sent task and the target user according to the weight value and the matching degree corresponding to each task attribute information.

[0218] Based on the above technical solutions, the target task determination module is further configured to determine the to-be-sent task corresponding to the highest matching degree according to the matching degrees between each to-be-sent task and the target user, and use the to-be-sent task as the target task corresponding to the target user.

[0219] The technical solution of the embodiment of the present invention can determine the matching degrees between each to-be-sent task and the target user by processing the task attribute information of each to-be-sent task, and then determine the target task from each to-be-sent task based on the matching degree, which improves the matching degree between the determined target task and the target user. Furthermore, after the target task is determined, the target task can be sent to the terminal corresponding to the target user. Since the matching degree between the target task and the target user is relatively high, the probability that the target user triggers the target task can be increased, thereby improving the task conversion rate and achieving the technical effect of the marketing purpose.

[0220] The apparatus for determining a target task provided by an embodiment of the present invention can execute the method for determining a target task provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution of the method.

[0221] It should be noted that the various units and modules included in the above apparatus are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the embodiments of the present invention.

[0222] Embodiment VIII

[0223] Figure 10 It is a schematic structural diagram of a device provided for Embodiment VIII of the present invention. Figure 10 It shows a block diagram of an exemplary device 100 suitable for implementing the embodiments of the present invention. Figure 10 The shown device 100 is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present invention.

[0224] As Figure 10 shown, the device 100 is presented in the form of a general-purpose computing device. The components of the device 100 may include but are not limited to: one or more processors or processing units 1001, a system memory 1002, and a bus 1003 connecting different system components (including the system memory 1002 and the processing unit 1001).

[0225] The bus 1003 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0226] The device 100 typically includes a variety of computer system-readable media. These media can be any available media accessible by the device 100, including volatile and non-volatile media, removable and non-removable media.

[0227] The system memory 1002 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 1004 and / or cache memory 1005. The device 100 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1006 can be used to read and write non-removable, non-volatile magnetic media ( Figure 10not shown, commonly referred to as a "hard disk drive"). Although Figure 10 not shown in Figure 10 , a disk drive for reading and writing a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 1003 through one or more data medium interfaces. The memory 1002 may include at least one program product having a set (such as at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0228] A program / utility 1008 having a set (at least one) of program modules 1007 may be stored in, for example, the memory 1002. Such program modules 1007 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 1007 generally perform the functions and / or methods in the embodiments described in the present invention.

[0229] The device 100 may also communicate with one or more external devices 1009 (such as a keyboard, a pointing device, a display 1010, etc.), and may also communicate with one or more devices that enable a user to interact with the device 100, and / or communicate with any device that enables the device 100 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 1011. Also, the device 100 may communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1012. As shown, the network adapter 1012 communicates with other modules of the device 100 through the bus 1003. It should be understood that although Figure 10 not shown in Figure 10 , other hardware and / or software modules may be used in combination with the device 100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0230] The processing unit 1001 executes various functional applications and data processing by running programs stored in the system memory 1002, such as implementing the method for determining a target task provided by the embodiments of the present invention.

[0231] Embodiment Nine

[0232] Embodiment Nine of the present invention also provides a storage medium containing computer-executable instructions that are used to execute the method for determining a target task when executed by a computer processor.

[0233] The method includes:

[0234] For each task to be sent, determine the task attribute information of the current task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the identifier of the task creator corresponding to the current task to be sent, and the category of task items corresponding to the current task to be sent;

[0235] Determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user;

[0236] Send the text content to be sent corresponding to the target task to the terminal device of the target user.

[0237] The computer storage medium of the embodiments of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0238] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0239] The program code contained on the computer-readable medium can be transmitted by any suitable medium, including - but not limited to - wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0240] Computer program code for performing the operations of the embodiments of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., connected through the Internet using an Internet service provider).

[0241] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments may be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a target task, characterized in that, Including: For each task to be sent, determine the task attribute information of the current task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the task creator identifier corresponding to the current task to be sent, and the task item category corresponding to the current task to be sent; Determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user; Send the text content to be sent corresponding to the target task to the terminal device of the target user; Wherein, the task attribute information includes the text content to be sent, and the determining the matching degree between the current task to be sent and the target user according to the task attribute information includes: Determine at least one target associated word corresponding to the text content to be sent; For each target associated word, retrieve the heat value and effective trigger value corresponding to the current target associated word from a preset location; wherein, the preset location also includes the total trigger value corresponding to each associated word, the heat value represents the occurrence frequency of the associated word, the effective trigger value represents the probability that the text is clicked when the associated word appears in the text, and the total trigger value represents the probability that all sent tasks are clicked within a preset duration; Determine the matching degree between the current task to be sent and the target user according to the heat value, effective trigger value and total trigger value of each target associated word.

2. The method according to claim 1, wherein Before determining the matching degree between the current task to be sent and the target user according to the task attribute information, it further includes: Obtain the sent tasks and total send times within a preset duration, the effective tasks and total effective click times of the sent tasks clicked; generate a sample set based on the sent tasks, total send times, effective tasks and total effective click times; For each sent task in the sample set, process the first text content of the current sent task based on a word segmentation tool, preset stop words and a preset phrase model to determine the associated words of the current sent task; generate an associated word set according to the associated words of each sent task; For each associated word in the associated word set, determine the word send times and effective click times of the at least one sent task to which the current associated word belongs, determine the heat value of the current associated word according to the word send times and total send times, and determine the effective trigger value of the current associated word according to the effective click times and total effective click times; determine the total trigger value of the tasks triggered within the preset duration to which the current associated word belongs according to the total effective click times and the total send times; Correspondingly store each associated word, and the heat value, effective trigger value and total trigger value corresponding to the associated word in a preset location, so as to determine the matching degree between the task to be sent and the target user according to the heat value, effective trigger value and total trigger value of each word in the text content to be sent.

3. The method according to claim 2, wherein Processing the first text content of the currently sent task based on a word segmentation tool, a preset stop word list, and a preset phrase model to determine the associated vocabulary of the currently sent task, including: Dividing the first text content into at least one word to be processed based on the word segmentation tool; removing the words that are the same as the preset stop words from the at least one word to be processed to obtain at least one word to be used; Combining the at least one word to be used into at least one phrase to be used based on the preset phrase model and the position information of the at least one word to be used in the first text content; Determining the associated vocabulary of the currently to-be-sent task based on the at least one word to be used and the at least one phrase to be used.

4. The method according to claim 3, wherein The combining the at least one word to be used into at least one phrase to be used based on the preset phrase model and the position information of the at least one word to be used in the first text content includes: Combining two words to be used with adjacent position information into a phrase to be processed based on the preset phrase model; If the phrase to be processed is consistent with a part of the first text content, then taking the phrase to be processed as a phrase to be used.

5. The method according to claim 1, characterized in that The determining the matching degree between the currently to-be-sent task and the target user according to the heat value, effective trigger value, and total trigger value of each target associated vocabulary includes: Determining a first intermediate processing value corresponding to the currently to-be-sent task according to the effective trigger value and total trigger value of each target associated vocabulary; determining a second intermediate processing value of the currently to-be-sent task according to the heat value of each target associated vocabulary; Determining the matching degree between the currently to-be-sent task and the target user based on the first intermediate processing value and the second intermediate processing value.

6. The method according to claim 2, characterized in that, The task attribute information includes the to-be-sent text content. The determining the matching degree between the currently to-be-sent task and the target user according to the task attribute information includes: Determining the target feature vocabulary included in the to-be-sent text according to each feature vocabulary in the feature vocabulary library; Determining the feature evaluation value of each target feature vocabulary according to the corresponding relationship established in advance between the feature vocabulary and the feature vocabulary evaluation value; Determining the matching degree between the currently to-be-sent task and the target user according to the feature evaluation value.

7. The method according to claim 6, wherein Further including: establishing the corresponding relationship between the feature vocabulary and the feature vocabulary evaluation value; The establishing the corresponding relationship between the feature vocabulary and the feature vocabulary evaluation value includes: For each valid task, extracting the feature vocabulary corresponding to the current valid task from the second text corresponding to the current valid task according to the preset rule template, and forming the feature vocabulary library according to the feature vocabulary of each valid task; Obtaining the feature vocabulary evaluation value of the current feature vocabulary according to each feature vocabulary based on the effective click times and the total effective click times corresponding to the current feature vocabulary; Establishing the corresponding relationship between each feature vocabulary and the corresponding feature vocabulary evaluation value to determine the feature evaluation value corresponding to the target feature vocabulary based on the corresponding relationship.

8. The method according to claim 1, characterized in that The task attribute information includes the identifier of the task creator corresponding to the current task to be sent. Determining the matching degree between the current task to be sent and the target user according to the task attribute information includes: Determining the creator task conversion value corresponding to the task creator identifier according to the pre-established mapping relationship between the task creator identifier and the creator task conversion value, and determining the matching degree between the current task to be sent and the target user based on the creator task conversion value.

9. The method according to claim 8, characterized in that It also includes: Establishing a mapping relationship between the task creator identifier and the creator task conversion value; The establishment of the mapping relationship between the task creator identifier and the creator task conversion value includes: For each creator identifier, determining the creation task and the number of creation tasks corresponding to the current creator identifier from the tasks that have been sent within a preset time period; For each creation task, determining the task click-through rate of the current creation task according to the task click-through volume corresponding to the current creation task and the number of times the current creation task has been sent; Determining the creator task conversion value of the current creator identifier according to the task click-through rate of each creation task and the number of creation tasks; Establishing a mapping relationship between the creator identifier and the creator task conversion value, so as to obtain the creator task conversion value corresponding to the creator identifier from the mapping relationship according to the creator identifier to which the current task to be sent belongs.

10. The method according to claim 1, wherein The task attribute information includes the task item category corresponding to the current task to be sent. Determining the matching degree between the current task to be sent and the target user according to the task attribute information includes: Obtaining the target item category associated with the target user, and determining the category association matching value according to the target item category and the task item category; Determining the category association coefficient value according to the number of task categories of the task item category and the number of target categories including the target item category in the task item category; Determining the matching degree between the current task to be sent and the target user according to the category association matching value and the category association coefficient value.

11. The method according to claim 10, wherein The determination of the category association matching value according to the target item category and the task item category includes: Determining the task tertiary category included in the task item category and the target tertiary category corresponding to the target item category; Determining the target tertiary category included in the task tertiary category to obtain the matching tertiary category; Respectively determining the matching value corresponding to each matching tertiary category, and taking the largest matching value as the category association matching value.

12. The method according to claim 1, wherein Determining the matching degree between the current task to be sent and the target user according to the task attribute information includes: Determining the matching degree between the current task to be sent and the target user according to the matching degrees corresponding to at least one task attribute information.

13. The method according to claim 12, wherein The determination of the matching degree between the current task to be sent and the target user according to the matching degrees corresponding to at least one task attribute information includes: Determine the matching degree between the current task to be sent and the target user according to the weight value and matching degree corresponding to each task attribute information.

14. The method according to claim 1, characterized in that The determining of the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user includes: According to the matching degree between each task to be sent and the target user, determine the task to be sent corresponding to the highest matching degree, and use the task to be sent as the target task corresponding to the target user.

15. A device for determining a target task, characterized in that, It includes: A matching degree determination module, configured to determine the task attribute information of the current task to be sent for each task to be sent, and determine the matching degree between the current task to be sent and the target user according to the task attribute information; wherein, the task attribute information includes at least one of the text content to be sent corresponding to the current task to be sent, the task creator identifier corresponding to the current task to be sent, and the task item category corresponding to the current task to be sent. A target task determination module, configured to determine the target task corresponding to the target user from each task to be sent according to the matching degree between each task to be sent and the target user. A target task sending module, configured to send the text content to be sent corresponding to the target task to the terminal device of the target user. Wherein, the task attribute information includes the text content to be sent, and the matching degree determination module is further configured to determine at least one target associated word corresponding to the text content to be sent; for each target associated word, retrieve the heat value and effective trigger value corresponding to the current target associated word from a preset location; wherein, the preset location further includes the total trigger value corresponding to each associated word, the heat value represents the occurrence frequency of the associated word, the effective trigger value represents the probability that the text is clicked when the associated word appears in the text, and the total trigger value represents the probability that all sent tasks are clicked within a preset duration; according to the heat value, effective trigger value, and total trigger value of each target associated word, determine the matching degree between the current task to be sent and the target user.

16. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining a target task as described in any one of claims 1-14.

17. A storage medium containing computer-executable instructions, the computer-executable instructions being used to execute the method for determining a target task as described in any one of claims 1-14 when executed by a computer processor.

Images