Information pushing method, device and equipment based on enterprise WeChat and storage medium
By obtaining and analyzing the basic information of contacts and user behavior information, generating user tags and portraits, and using enterprise WeChat to push information, the problem of low accuracy and efficiency of information push in the existing technology is solved, and efficient and accurate information push effect is achieved.
Patent Information
- Application Number
- CN202411795171.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2025-03-21
AI Technical Summary
The prior art is difficult to improve the push efficiency while improving the accuracy of information push, resulting in poor information push effect.
By obtaining the basic information of the contact person and user behavior information, generating user tags based on the preset tag generation model, and generating user portraits based on the user tags. Finally, based on the preset information push strategy, product information is sent to the contacts corresponding to the user portraits through enterprise WeChat.
This has achieved improved accuracy and efficiency of information push. Through the automatic group push function, labor costs are reduced and user resistance is avoided.
Smart Images
Figure CN119676305A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to an information push method, device, computer equipment and computer-readable storage medium based on enterprise WeChat. Background Art
[0002] With the development of technology, user terminals receive more and more product information pushed from various application APPs. However, since users have been harassed by various information for a long time, such push information is generally ignored directly. Therefore, it is necessary to push accurate information according to the different needs of different customers in order to achieve the expected push effect. For example, insurance agents have their own customer groups and can push products to specific customers through WeChat sharing. Although it is highly targeted, the push efficiency is low. Therefore, how to improve the push efficiency while improving the accuracy of push information has become a technical problem that needs to be solved urgently. Summary of the invention
[0003] The main purpose of the present invention is to provide an information push method, device, equipment and computer-readable storage medium based on enterprise WeChat, aiming to improve the accuracy of pushed information while improving the push efficiency.
[0004] To achieve the above object, the present invention provides an information push method based on enterprise WeChat, and the information push method comprises the following steps:
[0005] Obtaining basic information and user behavior information of the contact, and generating a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information;
[0006] Based on the user tag, generating a user portrait corresponding to the contact;
[0007] Based on the preset information push strategy, the corresponding product information is sent to the contact groups corresponding to each user portrait through WeChat for Business.
[0008] In addition, to achieve the above-mentioned purpose, the present invention also provides an information push device based on enterprise WeChat, and the information push device based on enterprise WeChat includes:
[0009] A user tag generation module, used to obtain basic information and user behavior information of a contact, and generate a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information;
[0010] A user portrait generation module, used to generate a user portrait corresponding to the contact based on the user tag;
[0011] The associated product push module is used to send corresponding product information to the contact groups corresponding to each user portrait through enterprise WeChat based on the preset information push strategy.
[0012] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer device, which includes a processor, a memory, and an enterprise WeChat-based information push program stored in the memory and executable by the processor, wherein when the enterprise WeChat-based information push program is executed by the processor, the steps of the enterprise WeChat-based information push method as described above are implemented.
[0013] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which is stored an information push program based on enterprise WeChat. When the information push program based on enterprise WeChat is executed by a processor, the steps of the information push method based on enterprise WeChat as described above are implemented.
[0014] The present application provides an information push method based on WeChat for Enterprises, which obtains the basic information and user behavior information of the contact, and generates the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information; generates the user portrait corresponding to the contact based on the user tag; and sends the corresponding product information to the contacts corresponding to each user portrait through WeChat for Enterprises based on the preset information push strategy. In the above manner, the present application classifies the contacts by their tags and portraits, and sends the corresponding product information to different contacts based on the information push strategy and WeChat for Enterprises, thereby realizing the automatic group push of product information, improving the accuracy of information push and the efficiency of information push. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 This is a flow chart of a first embodiment of the information push method based on enterprise WeChat of the present invention;
[0016] Figure 2 This is a flow chart of a second embodiment of the information push method based on enterprise WeChat of the present invention;
[0017] Figure 3 This is a flow chart of a third embodiment of the information push method based on enterprise WeChat of the present invention;
[0018] Figure 4 It is a schematic diagram of an information push device based on enterprise WeChat of the present invention;
[0019] Figure 5 The figure is a schematic diagram of the hardware structure of a computer device involved in an embodiment of the present invention.
[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0022] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0023] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0024] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0025] The information push method based on enterprise WeChat involved in the embodiment of the present invention is mainly applied to computer equipment, which can be a PC, a portable computer, a mobile terminal and other equipment with display and processing functions.
[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0027] Reference Figure 1 , Figure 1 This is a flow chart of the first embodiment of the information push method based on enterprise WeChat of the present invention.
[0028] like Figure 1 As shown, an embodiment of the present invention provides an information push method based on enterprise WeChat, and the information push method based on enterprise WeChat includes steps S10 to S30.
[0029] Step S10: acquiring basic information and user behavior information of the contact, and generating a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information;
[0030] In this embodiment, in order to improve the accuracy of pushed information while improving the push efficiency, this embodiment classifies contacts by their labels and portraits, and based on the information push strategy and corporate WeChat, sends corresponding product information to different contacts, thereby realizing automatic group push of product information, thereby improving the accuracy of information push while improving the efficiency of information push.
[0031] Exemplarily, the generating the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information includes:
[0032] Inputting the gender, age, occupation, native place and current residential address in the basic information into the label generation model to obtain the initial label of the contact;
[0033] The initial tag is adjusted according to the purchase information, collection information, browsing information and click information in the user behavior information to generate the user tag.
[0034] Specifically, the basic information of the contact is first obtained, including but not limited to: gender, age, occupation, native place and current residential address. That is, according to the gender, age, occupation, native place and current residential address of the user to whom the current popular or newly launched products are applicable, relevant users are pushed. And the contact's click behavior and purchase behavior of the product are buried in advance to obtain the contact's user behavior information, including but not limited to: purchase information, collection information, browsing information and click information.
[0035] The basic information and / or the user behavior information is input into a tag generation model to obtain a user tag corresponding to the contact.
[0036] In a specific embodiment, the basic information can be input into a label generation model to obtain an initial label of the contact. The initial label is then updated according to the user behavior information to obtain a user label. The basic information and user behavior information can also be input into a label generation model to obtain a user label.
[0037] Step S20: generating a user portrait corresponding to the contact based on the user tag;
[0038] In this embodiment, a user portrait corresponding to the contact is generated through user tags of multiple dimensions.
[0039] Step S30: Based on the preset information push strategy, the corresponding product information is sent to the contacts corresponding to each user portrait through enterprise WeChat.
[0040] In this embodiment, the information push strategy includes but is not limited to: push time, push words and push product rules, so that different users can customize the push products and time for their own customer groups.
[0041] The product push rules are used to filter out the product information associated with each user portrait, and at the corresponding push time, the product information associated with each user portrait is pushed to the corresponding contacts through the enterprise WeChat group.
[0042] Specifically, contacts may be grouped or profiled based on user tags.
[0043] User grouping allows product managers, operations, customer service and other business personnel to view the population corresponding to a certain label when applying labels. Multiple labels can be combined according to actual needs to meet their business definition of the population. For example: combine the three labels of "the number of coupons received in the past 7 days is greater than 1 time", "activity is equal to high and very high", and "female" users to define the target population, view the number of users covered by this group, and then push the selected user groups to various business systems for product information push.
[0044] User group portraits can not only define user groups by combining tags, but also support analyzing and defining the characteristics of user groups from multiple dimensions.
[0045] The following information can be pushed based on the user portrait:
[0046] 1. Behavior-based push notifications, such as product browsing, adding to shopping carts, store code scanning, order cancellation, order returns, etc.
[0047] 2. Location-based push notifications, such as nearby stores, nearby activities, frequently visited areas, etc.
[0048] 3. Push notifications based on festivals: birthdays, Spring Festival, Double 11, Double 12, Christmas, etc.
[0049] Recommend different personalized product recommendations to contacts based on gender, age group, interests, hobbies, browsing and purchasing behavior and other tags in the contact's user portrait.
[0050] Furthermore, after generating the user portrait corresponding to the contact based on the user tag, the method further includes:
[0051] Obtain the return visit records and communication records corresponding to each contact, and based on the return visit records and communication records, update the user portrait corresponding to each contact.
[0052] In this embodiment, the user portrait can be further updated according to the subsequent operations of the contact, so that the pushed product information corresponding to the contact can be updated according to the updated user portrait, further improving the accuracy of information push. Subsequent operations include but are not limited to the follow-up records and communication records of the contact regarding the pushed information, as well as the purchase, browsing and collection of products added by the contact.
[0053] Therefore, through the enterprise WeChat group chat method, the connection between enterprise WeChat and the product push system is realized, which reduces the huge manpower cost brought by offline sharing and avoids user resistance caused by indiscriminate information push of online apps.
[0054] By preliminarily analyzing and classifying the basic information of contacts, product tags of interest, and all purchase behavior data, we can obtain user tags and generate user portraits based on user tags.
[0055] Classify customers with more than 50% similarity in user profiles into a customer group, push similar products to this group every day, and upload customers' click and purchase data records to the data platform to improve user profiles;
[0056] Through subsequent return visits or daily communication with the contacts, the contact's user tag or user portrait can be updated, and the contact's pushed product information can be updated, thereby improving the accuracy of targeted product push.
[0057] This embodiment provides an information push method based on WeChat for Enterprise, which obtains the basic information and user behavior information of the contact, and generates the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information; generates the user portrait corresponding to the contact based on the user tag; and sends the corresponding product information to the contacts corresponding to each user portrait through WeChat for Enterprise based on the preset information push strategy. In the above manner, this application classifies the contacts by their tags and portraits, and sends the corresponding product information to different contacts based on the information push strategy and WeChat for Enterprise, thus realizing the automatic group push of product information, improving the accuracy of information push and the efficiency of information push.
[0058] Reference Figure 2 , Figure 2 This is a flow chart of a second embodiment of the information push method based on enterprise WeChat of the present invention.
[0059] Based on the above Figure 1 In the embodiment shown, in this embodiment, before step S10, the following steps are further included:
[0060] Step S01, initializing the weight parameters and bias parameters of each network layer in the initial model, and generating the survival probability parameters of each network layer based on preset rules;
[0061] Step S02, based on the survival probability parameters of each network layer, determining a target network layer and an optimized network layer in each network layer, wherein the target network layer is a network layer to be trained, and the optimized network layer is a network layer for which training needs to be skipped;
[0062] Step S03, based on the preset label sample set, initial weight parameters and initial bias parameters, skip the optimized network layer, and train the target network layer until the preset convergence condition is reached, to obtain a trained model as the label generation model.
[0063] In this embodiment, in order to prevent the label generation model from overfitting or underfitting during training, thereby causing the model training time to be too long, a random depth mechanism is provided based on the survival probability corresponding to each network layer in the model. Based on the random depth mechanism, some network layers can be randomly skipped during the training process, reducing the amount of forward and backward propagation calculations during model training, thereby reducing the computational complexity during model training; and only part of the network layer is used in each training, so that the training time is significantly shortened while ensuring the convergence of the model, preventing the model from overfitting, and enhancing the model's robustness to abnormal data and noise data. In addition, the label generation model obtained by training based on the random depth mechanism. Under the premise of ensuring model performance, the model training efficiency and label generation accuracy can be further improved.
[0064] Specifically, the network parameters and the survival probability of each layer are initialized first. Then, in each forward propagation process, it is randomly decided whether to skip the layer according to the survival probability of each layer. For the network layers participating in the training, the parameters are updated by forward and backward propagation as usual. For the network layers not participating in the training, the parameters are not updated, thereby realizing multiple iterative training of the model to ensure that the model converges and achieves the optimal performance.
[0065] Exemplarily, the step S10 specifically includes:
[0066] Initializing the weight parameters and bias parameters of each network layer based on the He initialization method or the Xavier initialization method to obtain the initial weight parameters and the initial bias parameters;
[0067] Based on a linear decreasing strategy, the survival probability parameters of each network layer are generated, wherein the level of the network layer is inversely proportional to the corresponding survival probability parameter value.
[0068] In this embodiment, by introducing a random depth mechanism in the training process, efficient training of a deep neural network is achieved, specifically including:
[0069] 1. Initialize the network parameters, that is, initialize the weight parameters and bias parameters in each layer of the random deep neural network. Specifically, the model parameters of the random deep neural network can be initialized by using methods such as He initialization or Xavier initialization to ensure the stability and effectiveness of the training.
[0070] Second, initialize the survival probability, that is, assign an initial survival probability p to each layer of the network l .
[0071] Specifically, a linear decreasing strategy can be adopted, that is, the level of the network layer is inversely proportional to the corresponding survival probability parameter value. By adopting a linear decreasing survival probability design, the effective depth of the network during the training process is guaranteed, while avoiding overly complex calculations.
[0072] That is, the survival probability is higher near the input layer, while the survival probability is lower near the output layer. For example, the survival probability can be set as:
[0073]
[0074] Among them, l is the current network layer, L is the total number of network layers, and p L It is the survival probability of the output layer in the previous round. The initial value can be taken in the first round. The value is generally low, such as less than 50%.
[0075] Specifically, a preset probability threshold can be set. When the survival probability parameter is not less than the preset probability threshold, the network layer can be recorded as the target network layer to train the network layer. When the survival probability parameter is less than the preset probability threshold, the network layer can be recorded as the optimized network layer to skip the network layer.
[0076] The initial label model is a random deep network model with initial weight parameters and initial bias parameters as the current model parameters. In each forward propagation process, the basic information of the contacts in the preset label sample set is input into each target network layer in the initial random deep network model, that is, the output results of each target network layer skip the next layer of the optimization network layer and directly pass it to the next layer of the target network layer. After completing the training of all target network layers in the random deep network model, it is determined whether the current random deep network model has reached the convergence condition. If not, the target network layer in the random deep network model is iteratively trained again, and the optimization network layer is still skipped until the random deep network model reaches the preset convergence condition. Stop model training to obtain the trained label generation model.
[0077] Furthermore, the determining of the target network layer and optimizing the network layer at each network layer based on the survival probability parameters of each network layer specifically includes:
[0078] Obtain any value within a preset value range as a random parameter of a network layer;
[0079] Compare the survival probability parameter of each network layer with its corresponding random parameter;
[0080] Based on the comparison results of each network layer, the network layer whose survival probability parameter is not less than the random parameter is determined as the target network layer, and the network layer whose survival probability parameter is less than the random parameter is determined as the optimized network layer.
[0081] First, the contact basic information samples in the label sample set are input into the first-level network layer.
[0082] Then, each network layer except the first-level network layer in the random deep network model is processed layer by layer, and each network layer of the initialized random deep network model is forward propagated:
[0083] For each network layer l, generate a random number r between [0,1] l , as random parameters of each level of network layer;
[0084] The random parameters r of each network layer are l The corresponding survival probability parameter p l To compare:
[0085] 1. If r l ≤p l , then this layer participates in the calculation and performs normal forward propagation:
[0086] x l+1 =f l (x l ,W l ,b l )
[0087] Among them, x l is the input of the lth layer, W l and b l are the weight and bias of the lth layer, respectively, and f l is the activation function of this layer.
[0088] 2. If r l >p l , then skip this layer and pass the current input directly to the next layer:
[0089] x l+1 =x l
[0090] In the above manner, this embodiment generates corresponding random parameters for each level of network layer to ensure the randomness of skipping the layer, and then compares the random parameters of the layer with its corresponding survival probability parameters, and determines whether to skip the layer during training based on the comparison results. Thus, the randomness of the optimized network layer is ensured based on the random parameters, thereby avoiding the fixed probability parameter threshold leading to a fixed optimized network layer, and further improving the accuracy of the prediction results of the random deep network model.
[0091] After completing a round of forward propagation of the model, back propagation is performed to update the parameters of the network layers involved in the forward propagation. Specifically:
[0092] 1. Calculate the label sample (i.e. target value y) corresponding to the contact basic information sample true ) and the loss function of the current label (network output y):
[0093] According to the network output y and target value y true Calculate the loss function L(y,y true ), using cross entropy loss or mean squared error loss.
[0094] 2. Back propagation layer by layer:
[0095] Starting from the output layer, the gradient is calculated forward layer by layer.
[0096] For each layer l, if the layer participates in the forward propagation (i.e., r l ≤p l ), the gradient is calculated normally and the parameters are updated:
[0097]
[0098]
[0099] Among them, η is the preset learning rate.
[0100] If the layer is skipped (i.e. r l >p l ), no parameter update is performed and the gradient is directly passed to the previous layer:
[0101]
[0102] In the above manner, this embodiment will iterate multiple times on the entire training set based on the above forward propagation and back propagation steps until the loss function converges or reaches a preset number of training rounds. During each iteration, the survival probability p of each network layer in this round is l Keep it unchanged to ensure the stability and effect of model training.
[0103] Reference Figure 3 , Figure 3 This is a flow chart of a third embodiment of the information push method based on enterprise WeChat of the present invention.
[0104] Based on the above Figure 1 In the embodiment shown, in this embodiment, the step S30 specifically includes:
[0105] Step S31, calculating the similarity between the contacts based on the user portraits of the contacts;
[0106] Step S32, determining the contacts whose similarity exceeds a preset similarity threshold as the same user group;
[0107] Step S33, based on the information push strategy, determining the push time and product information corresponding to each user group;
[0108] Step S34, sending corresponding product information to each user group at the corresponding push time of each user group through the enterprise WeChat.
[0109] In this embodiment, the user portrait includes the labels of the contacts in multiple dimensions, and the similarity between the contacts is calculated based on all the labels corresponding to the contacts. The contacts whose similarity exceeds a preset similarity threshold (such as 80%) are divided into the same user group, which can be established through WeChat for Business.
[0110] For the same user group, at the same push time, enterprise WeChat will use preset push words to push the corresponding product information of the user group.
[0111] Furthermore, sending corresponding product information to each user group at the corresponding push time of each user group through the enterprise WeChat includes:
[0112] Generate scheduled push tasks for each user group based on the push time and product information corresponding to each user group;
[0113] Based on the scheduled push tasks corresponding to each user group, the corresponding product information is sent to each user group through the enterprise WeChat.
[0114] In this embodiment, the pushed product information may be automatically filtered by the system according to the contact's tag, or may be manually selected by the user.
[0115] Specifically, users can select target push products, preset product push time, configure push tasks for designated groups, and complete product push for each user group in the product center.
[0116] Users can also pre-set information push strategies, including product screening rules, such as automatically screening out products with the same tags as the user group, or screening out popular products in related areas, etc., configure the push time for each user group, and automatically push the corresponding product information to improve push efficiency. The push time for each user group can be the same, and the push time can also be set according to the work and rest time of different user groups or the group's active time.
[0117] Therefore, based on behavioral information such as clicks, purchases, and follow-ups, we can filter out the products that the contacts are most likely to need and push them in batches to the corresponding contacts, thereby achieving more refined one-to-one service and improving the accuracy of information push and user experience.
[0118] See also Figure 4 , Figure 4 The present application provides a functional module diagram of an information push device based on enterprise WeChat.
[0119] like Figure 4 As shown, the information push device 400 based on enterprise WeChat includes:
[0120] The user tag generation module 410 is used to obtain the basic information and user behavior information of the contact, and generate a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information;
[0121] A user portrait generation module 420, configured to generate a user portrait corresponding to the contact based on the user tag;
[0122] The associated product push module 430 is used to send corresponding product information to the contact groups corresponding to each user portrait through enterprise WeChat based on a preset information push strategy.
[0123] Furthermore, the information push device based on enterprise WeChat also includes:
[0124] The probability parameter generation module is used to initialize the weight parameters and bias parameters of each network layer in the initial model, and generate the survival probability parameters of each network layer based on preset rules;
[0125] A network layer classification module, used to determine a target network layer and an optimized network layer in each network layer based on the survival probability parameters of each network layer, wherein the target network layer is a network layer to be trained, and the optimized network layer is a network layer for which training needs to be skipped;
[0126] The label model training module is used to skip the optimization network layer based on a preset label sample set, initial weight parameters and initial bias parameters, and train the target network layer until a preset convergence condition is reached to obtain a trained model as the label generation model.
[0127] Furthermore, the network layer classification module specifically includes:
[0128] A random parameter generating unit, used to obtain any value within a preset value range as a random parameter of a network layer;
[0129] A network parameter comparison unit, used to compare the survival probability parameter of each network layer with its corresponding random parameter;
[0130] The network classification unit is used to determine, based on the comparison results of each network layer, the network layer whose survival probability parameter is not less than the random parameter as the target network layer, and determine the network layer whose survival probability parameter is less than the random parameter as the optimized network layer.
[0131] Furthermore, the related product push module 430 includes:
[0132] A similarity calculation unit, used to calculate the similarity between each contact based on the user portrait of each contact;
[0133] A user group generating unit, used to determine the contacts whose similarity exceeds a preset similarity threshold as the same user group;
[0134] A push information setting unit, used to determine the push time and product information corresponding to each user group based on the information push strategy;
[0135] The user group information push unit is used to send corresponding product information to each user group at the push time corresponding to each user group through the enterprise WeChat.
[0136] Furthermore, the user group information pushing unit includes:
[0137] A push task generation subunit, for generating a scheduled push task corresponding to each user group based on the push time and product information corresponding to each user group;
[0138] The push task execution subunit is used to send corresponding product information to each user group through the enterprise WeChat based on the scheduled push tasks corresponding to each user group.
[0139] Furthermore, the information push device based on enterprise WeChat also includes:
[0140] The user portrait updating module is used to obtain the return visit records and communication records corresponding to each contact, and based on the return visit records and communication records, update the user portrait corresponding to each contact.
[0141] Furthermore, the user tag generating module 410 includes:
[0142] An initial label generation unit, used to input the gender, age, occupation, native place and current residential address in the basic information into the label generation model to obtain the initial label of the contact;
[0143] The user tag generation unit is used to adjust the initial tag according to the purchase information, collection information, browsing information and click information in the user behavior information to generate the user tag.
[0144] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0145] The above-mentioned device can be implemented in the form of a computer program. Figure 5 Runs on the computer device shown.
[0146] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.
[0147] See also Figure 5 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
[0148] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any information push method based on enterprise WeChat.
[0149] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
[0150] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any information push method based on enterprise WeChat.
[0151] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0152] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0153] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:
[0154] Generate a user tag for the contact based on a preset tag generation model, the basic information, and the user behavior information;
[0155] Based on the user tag, generating a user portrait corresponding to the contact;
[0156] Based on the preset information push strategy, the corresponding product information is sent to the contact groups corresponding to each user portrait through WeChat for Business.
[0157] In one embodiment, the processor is used to process the acquisition of the basic information and user behavior information of the contact, and before generating the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information, it is also used to implement:
[0158] Initialize the weight parameters and bias parameters of each network layer in the initial model, and generate the survival probability parameters of each network layer based on preset rules;
[0159] Based on the survival probability parameters of each network layer, a target network layer and an optimized network layer are determined in each network layer, wherein the target network layer is a network layer to be trained, and the optimized network layer is a network layer for which training needs to be skipped;
[0160] Based on the preset label sample set, initial weight parameters and initial bias parameters, the optimization network layer is skipped, and the target network layer is trained until the preset convergence condition is reached, and the trained model is obtained as the label generation model.
[0161] In one embodiment, the processor is used to process the survival probability parameters based on each network layer, and when each network layer determines the target network layer and optimizes the network layer, it is also used to implement:
[0162] Obtain any value within a preset value range as a random parameter of a network layer;
[0163] Compare the survival probability parameter of each network layer with its corresponding random parameter;
[0164] Based on the comparison results of each network layer, the network layer whose survival probability parameter is not less than the random parameter is determined as the target network layer, and the network layer whose survival probability parameter is less than the random parameter is determined as the optimized network layer.
[0165] In one embodiment, the processor is used to process the sending of corresponding product information to the contacts corresponding to each user portrait through the enterprise WeChat based on the preset information push strategy, and is also used to implement:
[0166] Based on the user portraits of each contact, calculate the similarity between each contact;
[0167] Determine the contacts whose similarity exceeds a preset similarity threshold as the same user group;
[0168] Based on the information push strategy, determine the push time and product information corresponding to each user group;
[0169] Through the enterprise WeChat, corresponding product information is sent to each user group at the corresponding push time of each user group.
[0170] In one embodiment, the processor is used to process the sending of corresponding commodity information to each user group at the corresponding push time of each user group through the enterprise WeChat, and is also used to implement:
[0171] Generate scheduled push tasks for each user group based on the push time and product information corresponding to each user group;
[0172] Based on the scheduled push tasks corresponding to each user group, the corresponding product information is sent to each user group through the enterprise WeChat.
[0173] In one embodiment, after the processor is used to process the generation of the user portrait corresponding to the contact based on the user tag, it is also used to implement:
[0174] Obtain the return visit records and communication records corresponding to each contact, and based on the return visit records and communication records, update the user portrait corresponding to each contact.
[0175] In one embodiment, the processor is used to implement the generation of the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information, and is also used to implement:
[0176] Inputting the gender, age, occupation, native place and current residential address in the basic information into the label generation model to obtain the initial label of the contact;
[0177] The initial tag is adjusted according to the purchase information, collection information, browsing information and click information in the user behavior information to generate the user tag.
[0178] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the information push methods based on enterprise WeChat provided in the embodiments of the present application.
[0179] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Medi a Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), etc., equipped on the computer device.
[0180] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for pushing information based on enterprise WeChat, characterized in that: The information push method comprises the following steps: Obtaining basic information and user behavior information of the contact, and generating a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information; Based on the user tag, generating a user portrait corresponding to the contact; Based on the preset information push strategy, the corresponding product information is sent to the contact groups corresponding to each user portrait through WeChat for Business.
2. The information push method based on enterprise WeChat as claimed in claim 1, characterized in that: Before acquiring the basic information and user behavior information of the contact and generating the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information, the method further includes: Initialize the weight parameters and bias parameters of each network layer in the initial model, and generate the survival probability parameters of each network layer based on preset rules; Based on the survival probability parameters of each network layer, a target network layer and an optimized network layer are determined in each network layer, wherein the target network layer is a network layer to be trained, and the optimized network layer is a network layer for which training needs to be skipped; Based on the preset label sample set, initial weight parameters and initial bias parameters, the optimization network layer is skipped, and the target network layer is trained until the preset convergence condition is reached, and the trained model is obtained as the label generation model.
3. The information push method based on enterprise WeChat as claimed in claim 2, characterized in that: The determining of the target network layer and optimizing the network layer at each network layer based on the survival probability parameters of each network layer specifically includes: Obtain any value within a preset value range as a random parameter of a network layer; Compare the survival probability parameter of each network layer with its corresponding random parameter; Based on the comparison results of each network layer, the network layer whose survival probability parameter is not less than the random parameter is determined as the target network layer, and the network layer whose survival probability parameter is less than the random parameter is determined as the optimized network layer.
4. The information push method based on enterprise WeChat as claimed in claim 1, characterized in that: The method of sending corresponding product information to the contacts corresponding to each user portrait through WeChat for Business based on the preset information push strategy includes: Based on the user portraits of each contact, calculate the similarity between each contact; Determine the contacts whose similarity exceeds a preset similarity threshold as the same user group; Based on the information push strategy, determine the push time and product information corresponding to each user group; Through the enterprise WeChat, corresponding product information is sent to each user group at the corresponding push time of each user group.
5. The information push method based on enterprise WeChat as claimed in claim 4, characterized in that: The sending of corresponding product information to each user group at the corresponding push time of each user group through the enterprise WeChat includes: Generate scheduled push tasks for each user group based on the push time and product information corresponding to each user group; Based on the scheduled push tasks corresponding to each user group, the corresponding product information is sent to each user group through the enterprise WeChat.
6. The information push method based on enterprise WeChat as claimed in claim 1, characterized in that: After generating the user portrait corresponding to the contact based on the user tag, the method further includes: Obtain the return visit records and communication records corresponding to each contact, and based on the return visit records and communication records, update the user portrait corresponding to each contact.
7. The information push method based on enterprise WeChat as described in any one of claims 1 to 6, characterized in that: The generating the user tag of the contact based on the preset tag generation model, the basic information and the user behavior information includes: Inputting the gender, age, occupation, native place and current residential address in the basic information into the label generation model to obtain the initial label of the contact; The initial tag is adjusted according to the purchase information, collection information, browsing information and click information in the user behavior information to generate the user tag.
8. An information push device based on enterprise WeChat, characterized in that: The information push device based on enterprise WeChat includes: A user tag generation module, used to obtain basic information and user behavior information of a contact, and generate a user tag for the contact based on a preset tag generation model, the basic information and the user behavior information; A user portrait generation module, used to generate a user portrait corresponding to the contact based on the user tag; The associated product push module is used to send corresponding product information to the contact groups corresponding to each user portrait through enterprise WeChat based on the preset information push strategy.
9. A computer device, characterized in that: The computer device includes a processor, a memory, and an enterprise WeChat-based information push program stored in the memory and executable by the processor, wherein when the enterprise WeChat-based information push program is executed by the processor, the steps of the enterprise WeChat-based information push method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an information push program based on enterprise WeChat, wherein when the information push program based on enterprise WeChat is executed by the processor, the steps of the information push method based on enterprise WeChat as described in any one of claims 1 to 7 are implemented.