Information screening method and device

Abstract

The invention discloses an information screening method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring an information packet, and grouping each piece of information in the information packet according to a specified dimension to obtain information groups; judging whether the information quantity in the information group exceeds a preset quantity threshold value or not; in response to the fact that the information quantity in the information group exceeds a preset quantity threshold value, screening each piece of information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determining the screened information as to-be-sent information; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of the historical information and the grouping characteristics of the information grouping. According to the embodiment, preferential screening of the information is realized, the value of subsequent information sending is improved, and valuable information sending resources are fully utilized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an information screening method and device. Background Art

[0002] In today's digital age, information promotion services for mobile terminals have become an effective means for businesses to reach users. In order to prevent various businesses from frequently sending promotional information to users, information sending platforms will manage the frequency of promotional information. For example, only one promotional message can be sent to a designated user per day to reduce disturbance to users.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] The existing frequency control management method adopts a first-come, first-served mechanism. In order to seize frequency control resources, merchants will concentrate their efforts in the morning. This not only brings higher instantaneous traffic pressure to the platform, but also this first-come, first-served mechanism cannot maximize value. Each user has different needs for different products. The existing frequency control management method cannot filter promotional information. Sending unnecessary information to users wastes resources and is not conducive to maintaining user experience. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides an information screening method and device, which realizes the preferential screening of information, and utilizes the similarity between the sending characteristics of historical information that has been sent and the grouping characteristics of the current information grouping to establish an information element evaluation table for the current information grouping, and then uses the information element evaluation table to preferentially screen out the information to be sent, which not only improves the value of subsequent information sending and makes full use of precious information sending resources, but also can terminate other information in the information grouping with low expected conversion in advance, saving the promotion cost of the merchant.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, there is provided an information screening method, comprising:

[0007] Acquire an information package, and group each information in the information package according to a specified dimension to obtain an information group;

[0008] Determining whether the amount of information in the information group exceeds a preset amount threshold;

[0009] In response to the number of information in the information group exceeding a preset quantity threshold, each information in the information group is screened according to a pre-constructed information element evaluation table corresponding to the information group, and the screened information is determined as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

[0010] Optionally, in response to the information grouping, each of the information is grouped and constructed according to the user dimension; the information element evaluation table is constructed in the following manner: for each historical information, a set of responding users who respond to the sending of the historical information is found, and the similarity between the grouped users corresponding to the information grouping and each responding user in the responding user set is calculated, and based on the similarity calculation result, the acceptance of the historical information by the grouped users is determined; and then the acceptance of each of the historical information by the grouped users is obtained; information elements are extracted for each of the historical information, and an information element evaluation table corresponding to the grouped users is generated based on the acceptance of each of the historical information by the grouped users.

[0011] Optionally, the similarity between the grouped users corresponding to the information group and each responding user in the responding user set is calculated, and based on the similarity calculation result, the acceptance of the historical information by the grouped users is determined, including: searching for the first consumer item corresponding to the grouped users and the second consumer item corresponding to each responding user in the responding user set; calculating the similarity between the first consumer item and each of the second consumer items; and using the maximum similarity value in the similarity calculation result as the acceptance of the historical information by the grouped users.

[0012] Optionally, in response to the historical information including text information; information elements are extracted from each piece of historical information, and an information element evaluation table corresponding to the grouped users is generated according to the acceptance of each piece of historical information by the grouped users, including: word segmentation of each piece of historical information, extracting a keyword set corresponding to each piece of historical information; determining the acceptance of a keyword set corresponding to each piece of historical information according to the acceptance of each piece of historical information by the grouped users, summarizing and collating the acceptance of each keyword set, and generating an information element evaluation table corresponding to the grouped users.

[0013] Optionally, the acceptance degrees of each of the keyword sets are summarized and organized to generate an information element evaluation table corresponding to the grouped users, including: summarizing the acceptance degrees of each of the keyword sets, and determining whether there are identical keywords in the summarized keywords; in response to the existence of identical keywords in the keywords, averaging the acceptance degrees corresponding to the identical keywords, and taking the average acceptance degree after averaging as the acceptance degree of the identical keywords.

[0014] Optionally, the information element evaluation table contains the acceptance degree of each information element; according to the pre-constructed information element evaluation table corresponding to the information grouping, each information in the information grouping is screened, and the screened information is determined as the information to be sent, including: extracting information elements from each information in the information grouping to obtain a set of information elements corresponding to each information; searching the information element evaluation table for the acceptance degree of the information elements in the information element set corresponding to each information, and summing up the acceptance degrees of each information belonging to an information element set to obtain the information acceptance degree corresponding to each information in the information grouping; according to the quantity threshold and the acceptance degree of each information, the information to be sent is screened out from each information in the information grouping.

[0015] Optionally, after determining the filtered information as information to be sent, the method further includes: acquiring a belonging party corresponding to other information in the information group except the information to be sent, and sending an information screening failure notification to the belonging party.

[0016] According to a second aspect of an embodiment of the present invention, there is provided an information screening device, comprising:

[0017] An information grouping module, used to obtain an information packet, and group each information in the information packet according to a specified dimension to obtain an information group;

[0018] A quantity determination module is used to determine whether the quantity of information in the information group exceeds a preset quantity threshold;

[0019] An information screening module is used to respond to the number of information in the information group exceeding a preset number threshold, and screen the individual information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determine the screened information as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

[0020] According to a third aspect of an embodiment of the present invention, there is provided an information screening electronic device, comprising:

[0021] one or more processors;

[0022] a storage device for storing one or more programs,

[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0024] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0025] According to a fifth aspect of an embodiment of the present invention, there is provided a computer program product, including a computer program, wherein when the computer program is executed by a processor, the method provided in the first aspect of the embodiment of the present invention is implemented.

[0026] An embodiment of the invention has the following advantages or beneficial effects: by acquiring an information package, each information in the information package is grouped according to a specified dimension to obtain an information group; judging whether the amount of information in the information group exceeds a preset quantity threshold; in response to the amount of information in the information group exceeding the preset quantity threshold, according to a pre-constructed information element evaluation table corresponding to the information group, each information in the information group is screened, and the screened information is determined as the information to be sent; wherein the information element evaluation table is a technical solution constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group, thereby realizing preferential screening of information, and utilizing the similarity between the sending characteristics of the historical information that has been sent and the grouping characteristics of the current information group to establish an information element evaluation table for the current information group, and then using the information element evaluation table to preferentially screen out the information to be sent, which not only improves the value of subsequent information sending and makes full use of precious information sending resources, but also can terminate other information in the information group with low expected conversion in advance, saving the promotion cost of the merchant. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0028] Figure 1 is a schematic diagram of the main process of the information screening method according to an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of a specific form of information grouping according to an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of information screening according to an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of a method for constructing an information element evaluation table according to an embodiment of the present invention;

[0032] Figure 5 is a schematic diagram of the process of constructing an information element evaluation table according to an embodiment of the present invention;

[0033] Figure 6 It is a schematic diagram of the overall principle of information screening in an embodiment of the present invention;

[0034] Figure 7 is a schematic diagram of main modules of an information screening device according to an embodiment of the present invention;

[0035] Figure 8 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0036] Fig. 9 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that in the technical solution of the present invention, the collection / collection, updating, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, disclosed or sold outside of these legal uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken for user personal information to selectively block the use or access to personal information data to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. In addition, once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0038] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0039] The existing frequency control management method adopts a first-come, first-served mechanism. In order to seize frequency control resources, merchants will concentrate on placing orders in the morning, which not only brings higher instantaneous traffic pressure to the platform, but also this first-come, first-served mechanism cannot maximize the value. Each user has different needs for different products. The existing frequency control management method cannot filter the promotion information. Sending unnecessary information to users not only wastes resources but also is not conducive to maintaining the user experience, and cannot meet practical applications well.

[0040] In order to solve the above-mentioned problems existing in the prior art, the present invention proposes an information screening method, which realizes the preferential screening of information. The similarity between the sending characteristics of historical information that has been sent and the grouping characteristics of the current information group is used to establish an information element evaluation table for the current information group, and then the information element evaluation table is used to preferentially screen out the information to be sent. This not only improves the value of subsequent information sending and makes full use of precious information sending resources, but also can terminate other information in the information group with low expected conversion in advance, saving the promotion cost of the merchant.

[0041] Figure 1 is a schematic diagram of the main process of the information screening method according to an embodiment of the present invention, such as Figure 1 As shown, the information screening method of the embodiment of the present invention includes the following steps S101 to S103.

[0042] Step S101: obtain an information package, and group each information in the information package according to a specified dimension to obtain an information group.

[0043] Specifically, when each merchant launches a new product or conducts a promotion, it is necessary to prepare the information content for promotion in advance, and specify the type of each information (new product promotion, promotion, promotion to increase new users, etc.), the user to whom it is sent, the date of sending, and other related information, and form an information package with the information containing these related information. It can be understood that the information in the information package of the embodiment of the present invention can be a text message, or it can be information that meets the format requirements of other instant messaging software, or it can be an email, etc.

[0044] Furthermore, each information in the information package is grouped according to a specified dimension. The specific dimension can be grouping according to the type of information, for example, the information is divided into three information groups according to new product promotion, sales promotion and new customer promotion; the information can also be grouped according to the user dimension to obtain the information group corresponding to each user; the information can also be grouped according to the date of sending to obtain the information group corresponding to each day, which is not specifically limited in the embodiment of the present invention.

[0045] Step S102: determine whether the amount of information in the information group exceeds a preset amount threshold.

[0046] Specifically, in view of the fact that the present invention is mainly used to control the frequency of information sending, the quantity threshold corresponding to the group information of the specified dimension obtained above is determined according to the preset frequency requirement. For example, for the information type dimension, the corresponding frequency is that the number of new product promotions shall not exceed 500 per day, the number of promotional promotions shall not exceed 2000 per day, and the number of new customer promotions shall not exceed 1000 per day. The quantity threshold of the group information of new product promotions on the same day is determined to be 500, the quantity threshold of the group information of promotional promotions on the same day is 2000, and the quantity threshold of the group information of new customer promotions on the same day is 1000. Of course, for the user dimension, if the corresponding frequency requirement is that the number of group information of a specified user shall not exceed 1 per day, then the quantity threshold of the group information of each user is 1.

[0047] Exemplarily, the frequency requirement is flexibly configurable. According to different scenario requirements, it can be configured as a one-day frequency control with a time window of 1 day, for example, the sending frequency of each user in 1 day is 1 message, a two-day frequency control with a time window of 2 days, for example, the sending frequency of each user in 2 days is 3 messages, and a three-day frequency control with a time window of 3 days, for example, the sending frequency of each user in 3 days is 5 messages.

[0048] Figure 2 It is a schematic diagram of the specific existence form of the information grouping of the embodiment of the present invention. There are three information groups (Plan1, Plan2, Plan3) in the figure, each of which corresponds to a user group. The group package in the figure stores the account of the user group receiving information (such as mobile phone number, email address, or instant messaging software account, etc.), and the information set stores the information set expected to be sent to the user. The time window of the three information groups in the figure is 1 day, and the planned sending dates are t1, t1 and t2 respectively, so it can be seen that Plan1 and Plan2 are allocated in the t1 date window, and Plan3 is allocated in the t2 date window.

[0049] Further, according to the quantity threshold, it is determined whether the quantity of information in the information group exceeds the quantity threshold, that is, it is determined whether the information in the current information group needs to be frequency controlled and whether the information in the information group needs to be screened.

[0050] Step S103: In response to the number of information in the information group exceeding the number threshold, the information in the information group is screened according to a pre-constructed information element evaluation table corresponding to the information group, and the screened information is determined as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

[0051] Specifically, if the number of information in the current information group, that is, the number of information items, exceeds the quantity threshold, it indicates that the information in the information group needs to be screened. The embodiment of the present invention pre-establishes a corresponding information element evaluation table for the information group. The information element evaluation table records the information elements in the information and the screening scores corresponding to the information elements. This screening score is used for information screening and is a standard for information screening. By querying the information element evaluation table, the screening scores of each information in the information group are obtained, and the information with high screening scores that meet the above quantity threshold is selected as the information to be sent, and other unselected information is no longer included in the sending plan.

[0052] It can be understood that, in view of the fact that the information element evaluation table pre-constructed in the embodiment of the present invention needs to construct a query table with a sufficiently high coverage rate based on a certain scale of information materials, the embodiment of the present invention uses the historical information that has been sent, calls the historical information sending record, and extracts the sending features related to the dimension of the information grouping from the sending record, such as the information type feature corresponding to the information generating the conversion rate in the historical information related to the information type, or the user feature that generates a response to it in the historical information related to the user. Then, the grouping feature of the current information grouping, that is, the similarity between the dimension feature and the sending feature of each selected historical information is compared and calculated, and the calculated similarity is used as the acceptance of the current information grouping to the historical information, and the acceptance is used as the screening score of each component element in the historical information to obtain the information element evaluation table generated based on the historical information, and then the information element evaluation table of all historical information corresponding to the current information grouping is obtained. It can be understood that after the number of historical information reaches a certain scale, an information element evaluation table with a high coverage rate for the current information grouping can be obtained, and the information element evaluation table contains the screening scores corresponding to each information component element.

[0053] According to one embodiment of the present invention, the information element evaluation table contains the acceptance degree of each information element; according to the pre-constructed information element evaluation table corresponding to the information grouping, each information in the information grouping is screened, and the screened information is determined as the information to be sent, including: extracting information elements from each information in the information grouping to obtain a set of information elements corresponding to each information; searching the information element evaluation table for the acceptance degree of the information elements in the information element set corresponding to each information, and summing up the acceptance degrees of each information belonging to an information element set to obtain the information acceptance degree corresponding to each information in the information grouping; according to the quantity threshold and the acceptance degree of each information, the information to be sent is screened out from each information in the information grouping.

[0054] Specifically, considering that the information in the information group contains various components, such as a text message, in which the various components are each word segment in the text message, if the information element evaluation table is queried one by one according to all the components in the information to obtain the corresponding acceptance, the efficiency is not high, and it is inevitable that some of the components are not necessary for the semantics of the entire information. Therefore, in order to improve efficiency, in the embodiment of the present invention, preferably, the information element evaluation table only records the acceptance corresponding to the key components in the historical information. Correspondingly, in the screening, the information elements of each information in the information group are also extracted to extract the key components and obtain the information element set corresponding to each information. It can be understood that in order to ensure consistency, when constructing the information element evaluation table, the same information element extraction tool or algorithm is used for the information element extraction of the historical information and the information element extraction of each information in the information group.

[0055] Furthermore, the acceptance of the information elements in the information element set of each information in the information group is searched from the information element evaluation table. Specifically, multi-threaded parallel query can be performed with each information element set as a unit, and the information elements recorded in the information element evaluation table can also be partitioned and stored according to the characteristics of the information elements, so as to improve the efficiency of table query. Then, the acceptance corresponding to the information elements belonging to the same information element set is summed to obtain the information acceptance corresponding to the information of the information element set. According to the information acceptance, high acceptance information that meets the quantity threshold is screened from the information group as the information to be sent.

[0056] Figure 3 Schematic diagram of information screening of an embodiment of the present invention. Information 1 and information 2 are in the same information group. It is necessary to screen out one to-be-sent information from information 1 and information 2, extract key information elements from information 1 and information 2, and extract key components, such as Figure 1 The "super-sensing image", "brand A" and "operating system OS" of information 1, and the "brand B", "20 off for purchases over 1000" and "get coupons" of information 2 form the information element set of information 1 and the information element set of information 2. Then, the acceptance of the information elements in each information element set is found in the information element evaluation table, and the acceptance of "super-sensing image", "brand A" and "operating system OS" is 5, 9, and 4 respectively; the acceptance of "brand B", "20 off for purchases over 1000" and "get coupons" is 1, 4, and 7 respectively. Then, the information acceptance corresponding to information 1 is 18, and the information acceptance corresponding to information 2 is 12, that is, information 1 corresponding to the high score of 18 is selected as the information to be sent.

[0057] According to another embodiment of the present invention, after determining the filtered information as information to be sent, the method further includes: obtaining the belonging party corresponding to other information in the information group except the information to be sent, and sending an information screening failure notification to the belonging party.

[0058] Specifically, after filtering out the information to be sent from the information group, in order to save the merchant's promotion costs, it is necessary to immediately count the corresponding parties of the other information remaining in the information group, that is, the merchants, and notify the parties of the information that failed to be filtered out, so that the merchants who received the information that failed to be filtered out can adjust their promotion strategies in time and choose other methods or channels to promote the information.

[0059] Finally, the selected information to be sent is added to the information sending plan. When the information sending time arrives, the selected information to be sent is sent to the designated user, completing the selective screening and sending of the information.

[0060] The embodiment of the present invention performs grouping based on information packets before information is sent to obtain information groups, and determines whether screening is required by judging the amount of information in the information group. When it is determined that screening is required, a corresponding information element evaluation table is constructed for the information group by comparing the similarity between the sending characteristics of historical information that has been sent and the grouping characteristics of the information group. Then, information screening is performed based on the information element evaluation table, thereby ensuring that the screened information to be sent is high-value information, improving the information sending effect, and also terminating other information in the information group with low expected conversion in advance, saving the merchant's promotion costs.

[0061] Through the above analysis, it can be seen that the construction of the information element evaluation table plays an important role in the accuracy of information screening. The embodiment of the present invention takes the information grouping constructed by user dimension grouping as an example to provide a detailed method for constructing the information element evaluation table. Figure 4 Schematic diagram of a method for constructing an information element evaluation table according to an embodiment of the present invention. Figure 4 The method for constructing the information element evaluation table includes:

[0062] Step S401: for each historical information, find a set of responding users who have responded to the sending of the historical information, calculate the similarity between the grouped users corresponding to the information group and each responding user in the responding user set, and determine the acceptance of the historical information by the grouped users based on the similarity calculation result; and then obtain the acceptance of each historical information by the grouped users.

[0063] Specifically, the embodiment of the present invention takes the information grouping constructed by user dimension grouping as an example to explain the information screening method in detail. Based on dividing each information in the information package into information groups corresponding to different users according to the user dimension, that is, the information in an information group is pre-planned to be sent to the same user, all corresponding historical information is selected for each information group, and the selection of specific historical information can be random or selected from each type of historical information. For each historical information, the responding users who have responded to the historical information are retrieved to form a responding user set. The response of the embodiment of the present invention is determined according to the content of the specific historical information. For example, for historical information of the reply type, a user replying to renew is considered a response, and for historical information of the click link type, a user clicking a link is considered a response. In addition, when the number of responding users exceeds the preset number threshold, the responding user set can be formed according to the number threshold, and the users exceeding the number can be deleted to avoid too much pressure on the system calculation due to too many responding users.

[0064] Furthermore, the user similarity between the grouped users of the current information group and each responding user in the responding user set is calculated. Specifically, with the help of the user portraits of each user in the background, the similarity between the user portraits of the grouped users and the user portraits of each responding user can be compared and calculated, and the maximum similarity in the similarity calculation result is used as the acceptance of the grouped users to the historical information.

[0065] Finally, the response user set corresponding to each historical information is traversed according to the similarity comparison method mentioned above to obtain the acceptance of each historical information by the grouped users.

[0066] According to one embodiment of the present invention, the similarity between the grouped users corresponding to the information group and each responding user in the responding user set is calculated, and based on the similarity calculation result, the acceptance of the historical information by the grouped users is determined, including: searching for the first consumer item corresponding to the grouped users and the second consumer item corresponding to each responding user in the responding user set; calculating the similarity between the first consumer item and each of the second consumer items; and using the maximum similarity value in the similarity calculation result as the acceptance of the historical information by the grouped users.

[0067] Specifically, in order to further improve the universal applicability of the construction of the information element evaluation table, the embodiment of the present invention uses the user's consumption history as basic data to calculate the similarity between the grouped users and each responding user. The consumption history of the grouped users is searched, and the preferred consumer items of the grouped users are selected from the consumption history. Specifically, the user preference can be determined by setting a purchase number threshold. If there is no consumption history, the user preference can be determined from the browsing number threshold. The preferred consumer items of the grouped users are searched to form the first consumer items, and the preferred consumer items corresponding to each responding user in the responding user set of the historical information are searched to form the second consumer items. The item similarity between the first consumer item and the second consumer item corresponding to each responding user is calculated from the item dimension, and the maximum similarity value in the item similarity calculation result is selected as the acceptance of the grouped user to this historical information.

[0068] For example, a certain consumer item sku1, sku2, sku3...sku is selected in response to a user's preference. n , which constitutes the corresponding second consumer item , accordingly, the second set of consumer items composed of m responding users is M= . Set the current group user Preferred consumer goods sku1, sku2, sku3…sku n , which constitutes the corresponding first consumer item The similarity between the first consumer item and each second consumer item is measured by using the Jaccard coefficient of similarity between sets. Denote by P, the second consumption good Expressed in Q, we can get the similarity calculation formula:

[0069] Accordingly, Calculate the similarity with the second consumer item set M, and get the similarity calculation result S= Finally, the largest similarity value in S is taken as the acceptance of historical information by the grouped users ,Right now:

[0070] Step S402: extract information elements from each piece of historical information, and generate an information element evaluation table corresponding to each group of users according to the acceptance degree of each piece of historical information by each group of users.

[0071] Specifically, based on the acceptance of historical information by the grouped users determined above, the historical information is split and the key information elements therein are extracted. The acceptance of historical information by the grouped users is granularized to the acceptance of the key information elements therein, and the acceptance of the key information elements in the historical information by the grouped users is obtained. These information elements and the corresponding acceptance of the information elements are combined into an information element evaluation table for the grouped users.

[0072] According to one embodiment of the present invention, in response to the historical information including text information; information elements are extracted from each of the historical information, and an information element evaluation table corresponding to the grouped users is generated according to the acceptance of each of the historical information by the grouped users, including: word segmentation of each of the historical information, extracting a keyword set corresponding to each of the historical information; determining the acceptance of the keyword set corresponding to each of the historical information according to the acceptance of each of the historical information by the grouped users, summarizing and collating the acceptance of each of the keyword sets, and generating an information element evaluation table corresponding to the grouped users.

[0073] Specifically, when the historical information is in text form, use a word segmentation tool, such as Let, to segment the historical information, and then use text mining TF-IDF technology to identify keyword tokens in the segmentation results. i , forming a keyword set Finally, the acceptance of historical information by the grouped users is converted into the acceptance of each keyword in the keyword set by the grouped users, and the keyword sets of each historical information are summarized and sorted to generate an information element evaluation table corresponding to the grouped users.

[0074] It can be understood that the information element evaluation table of the embodiment of the present invention can be constructed offline in advance or online in real time, and can be flexibly configured according to different business needs.

[0075] According to another embodiment of the present invention, the acceptance degrees of each of the keyword sets are summarized and sorted to generate an information element evaluation table corresponding to the grouped users, including: summarizing the acceptance degrees of each of the keyword sets, and determining whether there are identical keywords in the summarized keywords; in response to the existence of identical keywords in the keywords, averaging the acceptance degrees corresponding to the identical keywords, and using the average acceptance degree after averaging as the acceptance degree of the identical keywords.

[0076] Specifically, in the final process of summarizing the acceptance of keyword sets, it is inevitable that different keyword sets will have the same keywords. For example, the keyword "minus 20 for purchases over 1000" usually appears in multiple historical information, so it is necessary to check and determine whether there are identical keywords in the summarized keywords. If there are identical keywords, then the average acceptance is calculated based on the number of identical keywords and the acceptance of these identical keywords. The average acceptance is used as the acceptance corresponding to the identical keywords, and then an information element evaluation table is generated in which the identical keywords do not exist.

[0077] Figure 5 : It is a schematic diagram of the construction process of the information element evaluation table of the embodiment of the present invention. For the historical information "Brand A series L rear 50 million super perception imaging operating system OS mobile phone, reply ST to cancel the subscription", the corresponding responding user 1, responding user 2 and responding user 3 are found to form a responding user set. Then the second consumer items corresponding to responding user 1, responding user 2 and responding user 3 are searched respectively, and the second consumer items of responding user 1 include items 2, 3, 4 and 7; the second consumer items of responding user 2 include items 3, 8, 9 and 15; the second consumer items of responding user 3 include items 1, 4, 8 and 15. At the same time, the first consumer items of the grouped users are searched, and the first consumer items include items 1, 2, 3 and 4. Then the Jaccard coefficient is used to calculate the similarity between the first consumer item and each second consumer item, and the similarities between the grouped user and responding user 1, responding user 2 and responding user 3 are 0.6, 0.1428 and 0.3333 respectively, and the maximum value 0.6 is used as the acceptance of the historical information by the grouped user.

[0078] Furthermore, by segmenting the historical information and using the TF-IDF technology, we identify the keywords (information elements) of the historical information as “super-sensing imaging”, “operating system OS” and “brand A”. We can then determine that the grouped users’ acceptance of “super-sensing imaging”, “operating system OS” and “brand A” is also 0.6.

[0079] Finally, we summarize and count the situations where the same keywords exist in the keyword sets corresponding to each historical information. We set the number of the same keywords to x, and add 0.6 to the sum of the acceptance of the same keywords. We get the acceptance of “super-sensing imaging”, “operating system OS” and “brand A” by grouped users as the average acceptance of each same keyword, avg (x, 0.6+…), thus obtaining the summarized information element evaluation table.

[0080] It can be understood that, for the convenience of calculation, the numerical value of the acceptance degree between 0 and 1 of each keyword in the summarized information element evaluation table can be converted into an integer in equal proportion.

[0081] The information element evaluation table constructed based on the similarity calculated by using the user's preferred consumption items can better ensure the accuracy of the information element evaluation table and provide reliable screening support for information screening.

[0082] Figure 6 It is a schematic diagram of the overall principle of information screening in an embodiment of the present invention. The information sending platform first groups the information in the information package planned to be sent according to the user dimension, and distributes the information belonging to the same user to the user pool to form an information group. One unit in the user pool represents one user. It can be seen that the information group corresponding to PinA contains 2 pre-planned messages (txt1 and txt2), the information group corresponding to PinB contains 1 pre-planned message (txt1), and the information group corresponding to PinD also contains 2 pre-planned messages (txt2 and txt3). It is determined whether the number of messages in these three information groups exceeds the preset number threshold 1. The information group of PinA and the information group of PinD exceed the number threshold and need to be screened. There is no need to screen PinB. By default, one of the messages is the message to be sent, which is represented by dark filling in the figure.

[0083] Furthermore, based on the first consumer item consisting of the preferred consumer items of the grouped users PinA and PinD, and the extraction of information elements of each information in the information grouping, combined with the responding user set corresponding to the historical information, an information element evaluation table is constructed, and information preferential screening is performed on txt1 and txt2 in PinA's information grouping, and txt2 and txt3 in PinD's information grouping, to obtain the information acceptance of grouped user PinA to txt1 and txt2, and the information acceptance of grouped user PinD to each information txt2 and txt3, and sort them according to the value of the information acceptance, and select txt2 at the head of the sorting as the information to be sent by PinA, and txt3 as the information to be sent by PinD.

[0084] Finally, the determined txt2 corresponding to PinA, txt1 corresponding to PinB, and txt3 corresponding to PinD are used as the filtered information to be sent, and the remaining information is used as the filtering failure information. The filtering failure notification broadcast of txt1 in PinA and txt2 in PinD is sent to the information sending platform.

[0085] The embodiment of the present invention utilizes historical information and constructs an information element evaluation table through similarity comparison between users, thereby providing accurate and reliable data support for information screening, and realizing the screening of information that is truly valuable to users from information grouping. Under the premise of avoiding excessively disturbing users, the required information is sent to users, thereby improving the promotion effect and avoiding the loss caused by blindly sending information.

[0086] Figure 7 Schematic diagram of the main modules of the information screening device according to an embodiment of the present invention. Figure 7 As shown, the information screening device 700 mainly includes an information grouping module 701 , a quantity determination module 702 and an information screening module 703 .

[0087] The information grouping module 701 is used to obtain an information package, and group each information in the information package according to a specified dimension to obtain an information group;

[0088] The quantity determination module 702 is used to determine whether the quantity of information in the information group exceeds a preset quantity threshold;

[0089] The information screening module 703 is used to respond to the number of information in the information group exceeding a preset number threshold, and screen the individual information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determine the screened information as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

[0090] According to one embodiment of the present invention, in response to the information grouping, each of the information is grouped and constructed according to the user dimension; the information screening device 700 also includes an information element evaluation table construction module (not shown in the figure) for: for each historical information, finding a set of responding users who respond to the sending of the historical information, calculating the similarity between the grouped users corresponding to the information grouping and each responding user in the responding user set, and determining the acceptance of the historical information by the grouped users based on the similarity calculation result; and then obtaining the acceptance of each of the historical information by the grouped users; extracting information elements from each of the historical information, and generating an information element evaluation table corresponding to the grouped users based on the acceptance of each of the historical information by the grouped users.

[0091] According to another embodiment of the present invention, the information element evaluation table construction module (not shown in the figure) is also used to: find the first consumer item corresponding to the grouped users, and the second consumer item corresponding to each responding user in the responding user set; calculate the similarity between the first consumer item and each of the second consumer items; and use the maximum similarity value in the similarity calculation result as the acceptance of the grouped users to the historical information.

[0092] According to another embodiment of the present invention, in response to the historical information including text information, the information element evaluation table construction module (not shown in the figure) is also used to: segment each historical information, and extract the keyword set corresponding to each historical information; determine the acceptance of the keyword set corresponding to each historical information according to the acceptance of each historical information by the grouped users, summarize and organize the acceptance of each keyword set, and generate an information element evaluation table corresponding to the grouped users.

[0093] According to another embodiment of the present invention, the information element evaluation table construction module (not shown in the figure) is also used to: summarize the acceptance of each of the keyword sets, and determine whether there are identical keywords in the summarized keywords; in response to the existence of identical keywords in the keywords, average the acceptance corresponding to the identical keywords, and use the average acceptance after averaging as the acceptance of the identical keywords.

[0094] According to another embodiment of the present invention, the information element evaluation table includes the acceptance degree of each information element; the information screening module 703 is further used to: extract information elements from each information in the information group to obtain an information element set corresponding to each information; search the information element acceptance degree of the information element in the information element set corresponding to each information from the information element evaluation table, and sum up each acceptance degree in an information element set to obtain the information acceptance degree corresponding to each information in the information group; and screen out the information to be sent from each information in the information group according to the quantity threshold and the acceptance degree of each information.

[0095] According to another embodiment of the present invention, the information screening device 700 also includes a notification module (not shown in the figure), which is used to: after determining the screened information as information to be sent, obtain the belonging party corresponding to other information in the information group except the information to be sent, and send an information screening failure notification to the belonging party.

[0096] Figure 8 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0097] like Figure 8As shown, system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. Network 804 is used to provide a medium for communication links between terminal devices 801, 802, 803 and server 805. Network 804 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0098] Users can use terminal devices 801, 802, 803 to interact with server 805 through network 804 to receive or send messages, etc. Various communication client applications, such as information screening applications, etc., can be installed on terminal devices 801, 802, 803 (only as an example).

[0099] The terminal devices 801 , 802 , and 803 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0100] The server 805 may be a server that provides various services, such as a background management server that supports information screening performed by users using terminal devices 801, 802, and 803 (for example only). The background management server may obtain an information package, group each piece of information in the information package according to a specified dimension, and obtain an information group; determine whether the amount of information in the information group exceeds a preset amount threshold; in response to the amount of information in the information group exceeding the preset amount threshold, screen each piece of information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determine the screened information as information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group, and feeds back the processing result (such as information to be sent, etc. - for example only) to the terminal device.

[0101] It should be noted that the information screening method provided in the embodiment of the present invention is generally executed by the server 805 , and accordingly, the information screening device is generally disposed in the server 805 .

[0102] It should be understood that Figure 8 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0103] Reference below Fig. 9 , Fig. 9 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. Fig. 9 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0104] like Fig. 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the system 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0105] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0106] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the above-mentioned functions defined in the system of the present invention are executed.

[0107] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: 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 the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0108] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes: an information grouping module, a quantity determination module and an information screening module.

[0110] Among them, the names of these modules do not constitute a limitation on the modules themselves in certain cases. For example, the information grouping module can also be described as "a module used to obtain information packets, group the information in the information packets according to specified dimensions, and obtain information groups."

[0111] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or may exist independently without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: obtaining an information packet, grouping each information in the information packet according to a specified dimension to obtain an information group; judging whether the number of information in the information group exceeds a preset number threshold; in response to the number of information in the information group exceeding the preset number threshold, screening each information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determining the screened information as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of the historical information and the grouping characteristics of the information group.

[0112] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by acquiring an information package, each information in the information package is grouped according to a specified dimension to obtain an information group; judging whether the amount of information in the information group exceeds a preset quantity threshold; in response to the amount of information in the information group exceeding the preset quantity threshold, the information in the information group is screened according to an information element evaluation table corresponding to the pre-constructed information group, and the screened information is determined as the information to be sent; wherein the information element evaluation table is a technical solution constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group, thereby realizing the preferential screening of information, and using the pixels between the sending characteristics of the historical information that has been sent and the grouping characteristics of the current information group to establish an information element evaluation table for the current information group, and then using the information element evaluation table to preferentially screen out the information to be sent, which not only improves the value of subsequent information sending and makes full use of precious information sending resources, but also can terminate other information in the information group with low expected conversion in advance, saving the promotion cost of the merchant.

[0113] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. An information screening method, characterized in that: include: Acquire an information package, and group each information in the information package according to a specified dimension to obtain an information group; Determining whether the amount of information in the information group exceeds a preset amount threshold; In response to the number of information in the information group exceeding the quantity threshold, each information in the information group is screened according to a pre-constructed information element evaluation table corresponding to the information group, and the screened information is determined as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

2. The method according to claim 1, characterized in that In response to the information grouping, each of the information is grouped and constructed according to the user dimension; The information element evaluation table is constructed in the following manner: For each historical information, find a response user set that responds to the sending of the historical information, calculate the similarity between the grouped users corresponding to the information group and each response user in the response user set, and determine the acceptance of the historical information by the grouped users according to the similarity calculation result; and then obtain the acceptance of each historical information by the grouped users; Information elements are extracted from each of the historical information, and an information element evaluation table corresponding to the grouped users is generated according to the acceptance of each of the historical information by the grouped users.

3. The method according to claim 2, characterized in that Calculating the similarity between the grouped users corresponding to the information group and each responding user in the responding user set, and determining the acceptance of the grouped users to the historical information according to the similarity calculation result, including: Finding the first consumption item corresponding to the grouped users and the second consumption item corresponding to each responding user in the responding user set; calculating the similarity between the first consumer item and each of the second consumer items; The maximum similarity value in the similarity calculation result is used as the acceptance degree of the grouped users to the historical information.

4. The method according to claim 2, characterized in that: In response to the historical information including text information; Extracting information elements from each of the historical information, and generating an information element evaluation table corresponding to the grouped users according to the acceptance of each of the historical information by the grouped users, including: Segmenting each piece of historical information to extract a keyword set corresponding to each piece of historical information; According to the acceptance of each historical information by the grouped users, the acceptance of the keyword set corresponding to each historical information is determined, and the acceptance of each keyword set is summarized and sorted to generate an information element evaluation table corresponding to the grouped users.

5. The method according to claim 4, characterized in that Summarize and organize the acceptance of each keyword set to generate an information element evaluation table corresponding to the grouped users, including: Summarizing the acceptance of each of the keyword sets, and determining whether there are identical keywords among the summarized keywords; In response to the existence of identical keywords among the keywords, the acceptance degrees corresponding to the identical keywords are averaged, and the average acceptance degree after the average is taken as the acceptance degree of the identical keyword.

6. The method according to claim 1, characterized in that The information element evaluation table includes the acceptance level of each information element; Screening each piece of information in the information group according to the pre-constructed information element evaluation table corresponding to the information group, and determining the screened information as the information to be sent, including: Extracting information elements from each information in the information group to obtain an information element set corresponding to each information; Searching the information element acceptance degree of the information element in the information element set corresponding to each of the information from the information element evaluation table, and summing up the acceptance degrees of each of the information elements in one information element set to obtain the information acceptance degree corresponding to each of the information in the information group; The information to be sent is screened out from each information in the information group according to the quantity threshold and the acceptance degree of each information.

7. The method according to claim 1, characterized in that After determining the filtered information as information to be sent, the method further includes: Acquire the attribution party corresponding to other information in the information group except the to-be-sent information, and send an information screening failure notification to the attribution party.

8. An information screening device, characterized in that: include: An information grouping module, used to obtain an information packet, and group each information in the information packet according to a specified dimension to obtain an information group; A quantity determination module is used to determine whether the quantity of information in the information group exceeds a preset quantity threshold; An information screening module is used to respond to the number of information in the information group exceeding a preset number threshold, and screen the individual information in the information group according to a pre-constructed information element evaluation table corresponding to the information group, and determine the screened information as the information to be sent; wherein the information element evaluation table is constructed by comparing the similarity between the sending characteristics of historical information and the grouping characteristics of the information group.

9. A mobile electronic device terminal, characterized in that: include: 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 according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images