Information push method and push system

Abstract

The embodiment of the present invention provides an information push method and a push system, including: receiving question information from a first client for a target product; obtaining a weighting factor for the current period, the weighting factor being a characteristic variable that increases with the period; calculating the current push amount of the target product in the current period according to the weighting factor and the average push amount of the target product, the average push amount being the average pushable number of historical question information for the target product; and pushing the question information to multiple second clients according to the current push amount, the multiple second clients being clients of the target product purchasers. The present invention solves the technical problem that the traditional information push method has a poor answering situation for question information due to a fixed push amount.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to an information push method and a push system in e-commerce question and answer. Background Art

[0002] E-commerce Q&A is an emerging product form in the e-commerce industry in recent years. During the e-commerce Q&A process, potential buyers of goods raise questions that they care about, and after existing buyers see the questions, they answer the potential buyers based on their own usage experience.

[0003] An important prerequisite for the e-commerce Q&A process is that after a potential buyer asks a question, existing buyers can see the question and give an answer. Therefore, how to ensure that all questions from potential buyers are answered has become a key focus of e-commerce Q&A. Currently, the mainstream method for pushing question information in the industry is to push each question from a potential buyer to a fixed number of existing buyers through an application (APP).

[0004] Since questions asked earlier in a day will occupy the purchasers' attention first, and the probability of purchasers answering questions received later in a day is lower than that of purchasers answering questions received earlier, too much push of earlier questions will affect the purchasers' answers to later questions. However, the push amount of question information in the above information push method is fixed for all time periods, which will often lead to inappropriate push amount, resulting in poor answers to question information within a day. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide an information push method and a push system to solve the technical problem that the traditional information push method has a fixed push amount, resulting in poor answering of question information.

[0006] According to a first aspect of the present invention, there is provided an information push method, comprising:

[0007] Receiving question information from a first client regarding a target product;

[0008] Obtaining a weighting factor for the current period, wherein the weighting factor is a characteristic variable that increases with the period;

[0009] Calculating the current push amount of the target product in the current time period according to the weighted factor and the average push amount of the target product, the average push amount being the average pushable quantity of historical question information for the target product; and

[0010] The question information is pushed to a plurality of second clients according to the current push amount, and the plurality of second clients are clients of the purchasers of the target product.

[0011] Optionally, calculating the current push amount of the target product in the current time period according to the weighted factor and the average push amount of the target product includes:

[0012] Comparing the minimum push amount of the target product with a weighted value, where the weighted value is equal to the product of the weighted factor and the average push amount of the target product, and the minimum push amount is the minimum push amount of the question information to obtain an answer;

[0013] The larger value between the minimum push amount and the weighted value is used as the current push amount of the target product in the current time period.

[0014] Optionally, the minimum push amount is determined by click probability and answer rate, wherein the click probability is the probability of historical question information about the product being clicked after being sent, and the answer rate is the probability of historical question information about the product being answered after being clicked by a purchaser.

[0015] Optionally, the weighting factor, the average push amount, the minimum push amount and the purchaser sequence are calculated offline in the early morning every day.

[0016] Optionally, the average push volume is the ratio of the daily average number of historical question information about the target product to the number of purchasers of the target product.

[0017] Optionally, pushing the question information to multiple second clients according to the current push amount includes:

[0018] Obtain the quantity of the target product that has been purchased by each purchaser;

[0019] Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence;

[0020] The question information is pushed to the second clients of the purchasers in the purchaser sequence, and each of the second clients receives one question information.

[0021] According to a second aspect of the present invention, there is provided an information push system, comprising:

[0022] A receiving module, used for receiving question information from a first client regarding a target product;

[0023] An acquisition module, used to acquire a weighting factor of the current period, wherein the weighting factor is a characteristic variable that increases with the period;

[0024] a calculation module, configured to calculate the current push amount of the target product in the current time period according to the weighted factor and the average push amount of the target product, wherein the average push amount is the average pushable quantity of historical question information for the target product; and

[0025] A push module is used to push the question information to multiple second clients according to the current push amount, and the multiple second clients are clients of the purchasers of the target product.

[0026] Optionally, the calculation module is used to:

[0027] Comparing the minimum push amount of the target product with a weighted value, where the weighted value is equal to the product of the weighted factor and the average push amount of the target product, and the minimum push amount is the minimum push amount of the question information to obtain an answer;

[0028] The larger value between the minimum push amount and the weighted value is used as the current push amount of the target product in the current time period.

[0029] Optionally, the minimum push amount is determined by click probability and answer rate, wherein the click probability is the probability of historical question information about the product being clicked after being sent, and the answer rate is the probability of historical question information about the product being answered after being clicked by a purchaser.

[0030] Optionally, the weighting factor, the average push amount, the minimum push amount and the purchaser sequence are calculated offline in the early morning every day.

[0031] Optionally, the average push volume is the ratio of the daily average number of historical question information about the target product to the number of purchasers of the target product.

[0032] Optionally, the push module is used to:

[0033] Obtain the quantity of the target product that has been purchased by each purchaser;

[0034] Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence;

[0035] The question information is pushed to the second clients of the purchasers in the purchaser sequence, and each of the second clients receives one question information.

[0036] According to a third aspect of the present invention, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed, the information push method as described in any embodiment of the first aspect is implemented.

[0037] According to a fourth aspect of the present invention, there is provided an information push device, comprising:

[0038] Memory, for storing computer instructions;

[0039] A processor is coupled to the memory, and the processor is configured to execute the information push method as described in any embodiment of the first aspect based on computer instructions stored in the memory.

[0040] The embodiments of the present invention have the following advantages or beneficial effects:

[0041] The embodiment of the present invention determines the current push amount through a weighting factor and an average push amount, wherein the average push amount is the average number of historical question information that can be pushed for the target product, serves as a basic reference for the current push amount, and helps to avoid setting the current push amount too large or too small; the weighting factor is a characteristic variable that increases with time period, and plays a modulating role with time period on the current push amount, which helps to obtain a larger push amount for later information in a day. The combination of the weighting factor and the average push amount makes the current push amount more reasonable, and solves the technical problem of poor answering of question information due to the fixed push amount in traditional information push methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and other objects, features and advantages of the present invention will become more apparent through the description of the embodiments of the present invention with reference to the following drawings, in which:

[0043] Figure 1 is a flow chart of an information push method according to an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of an implementation method of information push according to an embodiment of the present invention;

[0045] Figure 3 It is a display interface of question information on the second client;

[0046] Figure 4 is a structural block diagram of an information push system according to an embodiment of the present invention;

[0047] Figure 5 It is a structural block diagram of an information pushing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The present invention is described below based on embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present invention without the description of these details. In order to avoid confusing the essence of the present invention, known methods, processes, and procedures are not described in detail. In addition, the drawings are not necessarily drawn to scale.

[0049] Before introducing the embodiments provided by the present invention, the parameters and corresponding marks involved in the embodiments of the present invention are described as follows:

[0050] (1) The number of products purchased by buyer k is CPk;

[0051] (2) The set of buyers of product i is Ui;

[0052] (3) The sequence of buyers Uip for product i;

[0053] (4) The number of purchasers in Ui is CUi;

[0054] (5) The daily average number of historical question information about product i, CQi;

[0055] (6) The average push volume of product i is Ki;

[0056] (7) Click probability is CTR;

[0057] (8) Response rate ASR;

[0058] (9) The minimum push amount is Kmin;

[0059] (10) The mean of the first number of questions is CQh;

[0060] (11) The average number of the second questions is CQavg;

[0061] (12) The weighting factor corresponding to the sub-period h is Wh;

[0062] (13) The current user to be pushed is Up;

[0063] (14) Current push amount Khij.

[0064] It should be emphasized that the above-mentioned marks are only for a clearer description of the present invention and do not limit the technical solution of the present invention.

[0065] Figure 1 FIG. 1 is a flow chart of an information push method according to an embodiment of the present invention. Figure 1 , information push methods include:

[0066] Step S101: receiving a question from a first client regarding a target product.

[0067] Step S102, obtaining the weighting factor of the current time period, the weighting factor is a characteristic variable that increases with time period. It should be noted that the weighting factor increases with time period, that is, the weighting factor of the later time period in a day is larger.

[0068] Step S103, the current push amount of the target product in the current period is calculated according to the weighted factor and the average push amount of the target product, where the average push amount is the average pushable quantity of historical question information for the target product.

[0069] And, step S104, pushing the question information to multiple second clients according to the current push amount, the multiple second clients are clients that have purchased the target product.

[0070] Compared with the second client, the first client is the client of the potential buyer of the target product. The potential buyer sends question information about the target product through the first client, and the buyer of the target product answers after receiving the question information through the second client, thus realizing the current e-commerce question and answer process.

[0071] In the embodiment of the present invention, the current push amount is determined by a weighting factor and an average push amount, wherein the average push amount is the average number of historical question information that can be pushed for the target product, and serves as a basic reference for the current push amount, which helps to avoid setting the current push amount too large or too small; the weighting factor is a characteristic variable that increases with time period, and plays a modulating role with time period on the current push amount, which helps to obtain a larger push amount for later information in a day. The combination of the weighting factor and the average push amount makes the current push amount more reasonable, which solves the technical problem of poor answering of question information due to the fixed push amount in traditional information push methods.

[0072] In an optional embodiment, step S103, calculating the current push volume of the target product in the current period according to the weighted factor and the average push volume of the target product, includes:

[0073] Compare the minimum push volume and weighted value of the target product. The weighted value is equal to the product of the weighted factor and the average push volume of the target product. The minimum push volume is the minimum push volume for answering the question information.

[0074] The larger value between the minimum push quantity and the weighted value is used as the current push quantity of the target product in the current period.

[0075] In an embodiment of the present invention, the larger value between the minimum push amount and the weighted value is used as the current push amount of the target product in the current time period, wherein the minimum push amount is the minimum push amount for the question information to obtain an answer. Therefore, the current push amount can ensure that the question information obtains a larger reasonable push amount on the basis of ensuring that the question information obtains a response, which is beneficial for the question information to obtain richer answer content without affecting later question information.

[0076] In an optional embodiment, step S104, pushing the question information to multiple second clients according to the current push amount, includes:

[0077] Get the number of products that each buyer of the target product has purchased;

[0078] Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence;

[0079] The question information is pushed to the second clients of the current pushed quantity purchased users (hereinafter also referred to as the current users to be pushed) in the purchased user sequence, and one second client receives one question information.

[0080] In an embodiment of the present invention, question information is pushed to the second client of the purchaser before the current push number in the sequence of purchasers of the target product, that is, the question information is pushed to the purchaser who has purchased fewer products as much as possible. Since the larger the number of products purchased, the greater the probability of the purchaser being asked questions (including being asked questions by potential purchasers of the same product or different products), for the purchaser of the target product, the fewer products purchased, the smaller the probability of being asked questions, which is conducive to a higher probability of the question information being answered.

[0081] The following is a detailed introduction to the information push method using product i as the target product. However, it should be emphasized that product i is only a synonym for a certain product and does not limit the product. Figure 2 FIG. 4 is a schematic diagram showing an implementation of an information push method according to an embodiment of the present invention.

[0082] Reference Figure 2 The purchaser sequence Uip of commodity i is determined by the purchaser set Ui of commodity i and the quantity CPk of commodities purchased by purchaser k (k represents any purchaser in the purchaser set Ui).

[0083] Reference Figure 2The average push amount Ki, as the average number of historical question information about product i that can be pushed, can be determined by the average daily number CQi of historical question information about product i and the number CUi of users who have purchased product i. Specifically, the average push amount Ki = CUi / CQi, and the average daily number CQi can be the average daily number of question information about product i in the past N days (N in this application refers to an integer greater than 1).

[0084] Reference Figure 2 The minimum push amount Kmin is the minimum push amount for answering the question information, which can be determined by the click probability CTR and the answer rate ASR. The minimum push amount for answering the question information is calculated by fully considering the funnel effect of the process of receiving the question information-the purchaser clicks the question information-the purchaser answers the question information. Among them, the click probability CTR is the probability that the historical question information of the product is clicked after being sent, and the answer rate ASR is the probability that the historical question information of the product is answered after being clicked by the purchaser. Specifically, the click probability CTR can be the click probability of the question information in the past N days, and the click probability CTR = the number of clicks on the question information in the past N days / the number of questions sent in the past N days; the answer rate ASR can be the probability of answering the question information in the past N days after being clicked by the purchaser, and the answer rate ASR = the number of questions answered in the past N days / the number of questions clicked in the past N days.

[0085] Reference Figure 2 The weighting factor Wh is a characteristic variable that increases with time period and can be determined by the first question number average CQh and the second question number average CQavg. Specifically, the weighting factor of the current time period h' can be Among them, the first average number of questions CQh is the average daily number of product question information in the hour segment h in the past N days, and the second average number of questions CQavg is the average daily total number of product question information in the past N days.

[0086] In an optional embodiment, the above average push amount Ki, minimum push amount Kmin, weighting factor Wh and purchaser sequence Uip are calculated offline in the early morning every day.

[0087] Reference Figure 2The average push amount Ki, the minimum push amount Kmin, the weighting factor Wh and the purchaser sequence Uip can be calculated by the offline calculation module 1 in the early morning every day. At this time, the purchase situation of the target product involved in the calculation process adopts the purchase situation calculated in the early morning, such as the number of purchasers of the target product and the number of purchased products by each purchaser. Offline calculation is conducive to the use of a unified purchase situation for all products; if a question information about the target product is received from the first client at a certain moment, the current push amount Khij of the target product at that moment can be calculated by the real-time calculation module 2, and the current user Up to be pushed is selected from the purchaser sequence Uip of the target product, so as to push the question information about the target product to the second client of each purchaser in the current user Up to be pushed. Figure 3 The following is a display interface of the question information on the second client. For each buyer of the product, the question information received by the second client can be displayed through Figure 3 The interface shown is displayed on the display screen of an electronic device, that is, a reminder is given through the title "There is a question I need your help".

[0088] In the embodiment of the present invention, offline calculation and real-time calculation are combined, wherein offline calculation calculates the common parameters such as the average push amount Ki, the minimum push amount Kmin, the weighting factor Wh and the purchaser sequence Uip in advance at dawn every day, and real-time calculation performs targeted calculation on the question information of the target product at a certain moment. Offline calculation is conducive to quickly obtaining the current push amount Khij, and real-time calculation eliminates the need to calculate the push amount of question information that has not been received, which is concise, efficient, and saves computing resources.

[0089] Figure 4 FIG. 1 is a block diagram of the information push system according to an embodiment of the present invention. Figure 4 , the information push system includes:

[0090] The receiving module 100 is used to receive question information about the target product from the first client;

[0091] An acquisition module 200 is used to acquire a weighting factor of the current period, where the weighting factor is a characteristic variable that increases with the period;

[0092] A calculation module 300 is used to calculate the current push amount of the target product in the current period according to the weighted factor and the average push amount of the target product, wherein the average push amount is the average pushable number of historical question information about the target product; and

[0093] The push module 400 is used to push the question information to multiple second clients according to the current push amount, and the multiple second clients are clients of the purchasers of the target product.

[0094] In the embodiment of the present invention, the information push system determines the current push amount through weighted factors and average push amounts, wherein the average push amount is the average number of historical question information that can be pushed for the target product, and serves as a basic reference for the current push amount, which helps to avoid setting the current push amount too large or too small; the weighted factor is a characteristic variable that increases with time period, and plays a modulating role with time period on the current push amount, which helps to make the information later in the day obtain a larger push amount. The combination of weighted factors and average push amount makes the current push amount more reasonable, and solves the technical problem of poor answering of question information due to fixed push amount in traditional information push methods.

[0095] In an optional embodiment, the computing module is used to:

[0096] Compare the minimum push volume and weighted value of the target product. The weighted value is equal to the product of the weighted factor and the average push volume of the target product. The minimum push volume is the minimum push volume for answering the question information.

[0097] The larger value between the minimum push quantity and the weighted value is used as the current push quantity of the target product in the current period.

[0098] In an optional embodiment, the minimum push amount is determined by the click probability and the answer rate, wherein the click probability is the probability that the historical question information about the product is clicked after being sent, and the answer rate is the probability that the historical question information about the product is answered after being clicked by the purchaser.

[0099] In an optional implementation, the weighting factor, average push amount, minimum push amount and purchaser sequence are calculated offline in the early morning every day.

[0100] In an optional implementation manner, the average push volume is the ratio of the daily average number of historical question information about the target product to the number of purchasers of the target product.

[0101] In an optional implementation, the push module is used to:

[0102] Get the number of products that each buyer of the target product has purchased;

[0103] Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence;

[0104] The question information is pushed to the second clients of the current push quantity who have purchased in the purchaser sequence, and each second client receives one question information.

[0105] An information push device according to an embodiment of the present invention includes:

[0106] Memory, for storing computer instructions;

[0107] The processor is coupled to the memory, and the processor is configured to execute the above-mentioned information pushing method based on the computer instructions stored in the memory.

[0108] Figure 5 The device shown is only an example of an information push device and should not constitute any limitation on the functions and scope of use of the embodiments of the present invention. Figure 5 The information push device includes a processor 501, a memory 502, and an input-output device 503 connected via a bus. The memory 502 includes a read-only memory (ROM) and a random access memory (RAM). The memory 502 stores various computer instructions and data required to execute system functions. The processor 501 reads various computer instructions from the memory 502 to execute various appropriate actions and processes. The input-output device 503 includes an input part such as a keyboard and a mouse; an output part such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage part such as a hard disk; and a communication part such as a network interface card such as a LAN card and a modem. The memory 502 also stores the following computer instructions to complete the operations specified in the information push method of the embodiment of the present invention: receiving question information from a first client regarding a target product; obtaining a weighting factor for the current time period, where the weighting factor is a characteristic variable that increases over time; calculating the current push amount of the target product in the current time period based on the weighting factor and the average push amount of the target product, where the average push amount is the average number of pushable historical question information regarding the target product; and pushing the question information to multiple second clients based on the current push amount, where the multiple second clients are clients of purchasers of the target product.

[0109] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed, the operations specified by the above-mentioned information pushing method are implemented.

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the possible system frameworks, functions and operations of the systems, methods and devices of the embodiments of the present invention. The boxes on the flowcharts and block diagrams can represent a module, a program segment or just a piece of code, and the modules, program segments and codes are all executable instructions for implementing the specified logical functions. It should also be noted that the executable instructions for implementing the specified logical functions can be recombined to generate new modules and program segments. Therefore, the boxes and the order of the boxes in the accompanying drawings are only used to better illustrate the process and steps of the embodiments, and should not be used as a limitation on the invention itself.

[0111] Each module or unit of the system can be implemented by hardware, firmware or software. Software, for example, includes a coding program formed by various programming languages ​​such as JAVA, C / C++ / C#, SQL, etc. Although the steps and the order of the steps of the embodiment of the present invention are given in the method and the method legend, the executable instructions for the steps to implement the specified logical functions can be recombined to generate new steps. The order of the steps should not be limited to the order of the steps in the method and the method legend, and can be adjusted at any time according to the needs of the function. For example, some of the steps are executed in parallel or in reverse order.

[0112] The system and method according to the present invention can be deployed on a single or multiple servers. For example, different modules can be deployed on different servers to form dedicated servers. Alternatively, the same functional units, modules or systems can be deployed in a distributed manner on multiple servers to reduce load pressure. The servers include but are not limited to multiple PCs, PC servers, blade computers, supercomputers, etc. in the same local area network and connected via the Internet.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An information push method, characterized in that: include: Receiving question information from a first client regarding a target product; Obtaining a weighting factor for the current period, wherein the weighting factor is a characteristic variable that increases with the period; Comparing the minimum push amount and the weighted value of the target product, the weighted value being equal to the product of the weighted factor and the average push amount of the target product, the minimum push amount being the minimum push amount of the answer obtained by the question information, taking the larger value of the minimum push amount and the weighted value as the current push amount of the target product in the current time period, and the average push amount being the average pushable quantity of the historical question information for the target product; as well as Pushing the question information to multiple second clients according to the current push amount, wherein the multiple second clients are clients of the target product that has purchased the target product. The weighted factor, the average push amount, the minimum push amount and the sequence of purchased users are calculated offline in the early morning every day.

2. The push method according to claim 1, characterized in that: The minimum push amount is determined by the click probability and the answer rate, wherein the click probability is the probability of receiving a click after the historical question information about the product is sent, and the answer rate is the probability of receiving an answer after the historical question information about the product is clicked by a purchaser.

3. The push method according to claim 1, characterized in that: The average push volume is the ratio of the daily average number of historical question information about the target product to the number of purchasers of the target product.

4. The push method according to claim 1, characterized in that: Pushing the question information to multiple second clients according to the current push amount includes: Obtain the quantity of the target product that has been purchased by each purchaser; Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence; The question information is pushed to the second clients of the purchasers in the purchaser sequence, and each of the second clients receives one question information.

5. An information push system, characterized in that: include: A receiving module, used for receiving question information from a first client regarding a target product; An acquisition module, used to acquire a weighting factor of the current period, wherein the weighting factor is a characteristic variable that increases with the period; A calculation module compares the minimum push amount of the target product with a weighted value, where the weighted value is equal to the product of the weighted factor and the average push amount of the target product, and the minimum push amount is the minimum push amount of the question information to obtain an answer; The larger value between the minimum push amount and the weighted value is used as the current push amount of the target product in the current time period, and the average push amount is the average pushable amount of historical question information for the target product; as well as a push module, configured to push the question information to a plurality of second clients according to the current push amount, wherein the plurality of second clients are clients of the target product that has purchased the target product; The weighted factor, the average push amount, the minimum push amount and the sequence of purchased users are calculated offline in the early morning every day.

6. The push system according to claim 5, characterized in that: The push module is used for: Obtain the quantity of the target product that has been purchased by each purchaser; Sort the purchasers of the target product in ascending order according to the quantity of the product to obtain a purchaser sequence; The question information is pushed to the current pushed amount purchasers earlier in the purchaser sequence, and each purchaser in the purchaser sequence receives one question information.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed, the information push method according to any one of claims 1 to 4 is implemented.

8. An information push device, characterized in that: include: Memory, for storing computer instructions; A processor is coupled to the memory, and the processor is configured to execute the information push method according to any one of claims 1 to 4 based on computer instructions stored in the memory.

Images