Information publishing method and system, electronic equipment and storage medium

Abstract

The invention discloses an information publishing method and system, electronic equipment and a storage medium. The method comprises the following steps: receiving bad data sent by first user equipment, and extracting bad information in the bad data; processing the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data; sending the bad data and the receiving object information to an information issuing server, so that the information issuing server sends the bad data to second user equipment corresponding to the receiving object information; wherein the first user equipment is used for sending the bad data, and the second user equipment is used for receiving the bad data. According to the invention, a worker can be prevented from receiving information irrelevant to the worker, high-precision pushing of the information is realized, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to an information publishing method, system, electronic device and storage medium. Background Art

[0002] With the development of communication technology, companies now use instant messaging systems, which can achieve convenient and fast communication while ensuring information security throughout the communication process.

[0003] Existing methods for automatic information release are mainly based on certain rules, the department where the personnel are located or the relationship between superiors and subordinates. They cannot meet the requirements of high-precision target push in special business scenarios. Staff members often receive information that is not related to them, which reduces work efficiency. Summary of the invention

[0004] The present invention provides an information publishing method, system, electronic device and storage medium to achieve high-precision information push, thereby improving work efficiency.

[0005] According to one aspect of the present invention, there is provided an information publishing method, which is applied to a data processing server and comprises:

[0006] Receiving bad data sent by the first user equipment, and extracting bad information from the bad data;

[0007] Processing the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data;

[0008] Sending the bad data and the receiving object information to an information publishing server, so that the information publishing server sends the bad data to a second user device corresponding to the receiving object information;

[0009] The first user equipment is used to send bad data, and the second user equipment is used to receive bad data.

[0010] According to another aspect of the present invention, there is provided an information publishing system, comprising: a plurality of user devices, a data processing server and an information publishing server; the user devices comprise a first user device and a second user device, the first user device is used to send bad data, and the second user device is used to receive bad data;

[0011] The first user equipment is used to send the bad data to the data processing server in response to the bad data sending operation;

[0012] The data processing server is used to receive the bad data, extract bad information from the bad data, and input the bad information into a data receiving object prediction model for prediction to obtain receiving object information of the bad data; and send the bad data and the receiving object information to an information publishing server;

[0013] The information publishing server is used to receive the bad data and the receiving object information, and send the bad data to a second user device corresponding to the receiving object information.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the information publishing method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information publishing method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention receives bad data sent by a first user device and extracts bad information from the bad data; processes the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data; sends the bad data and receiving object information to an information publishing server, so that the information publishing server sends the bad data to a second user device corresponding to the receiving object information. This can prevent staff from receiving information that is irrelevant to them, achieve high-precision information push, and improve work efficiency.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of an information publishing method provided by Embodiment 1 of the present invention;

[0023] Figure 2 It is a structural diagram of an information publishing device provided by Embodiment 2 of the present invention;

[0024] Figure 3 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first user device", "second user device", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] Embodiment 1

[0028] Figure 1 This is a flow chart of an information publishing method provided in the first embodiment of the present invention. This embodiment is applicable to the situation of high-precision push of bad data between enterprise employees. The method can be executed by an information publishing system. The information publishing system can be implemented in the form of hardware and / or software. The information publishing system can be configured in electronic devices such as computers and servers. Figure 1As shown, the method includes:

[0029] S110: Receive bad data sent by a first user equipment, and extract bad information from the bad data.

[0030] Wherein, the first user device is used to send bad data. Specifically, the user device can be a user terminal, a computer and other devices. In an embodiment of the present invention, a user can send bad data through the first user device. Wherein, bad data refers to data that does not meet expectations or user purposes at each node of the business process. It can be understood that the bad data at each node of the business process is handled by specific business responsible personnel. Further, bad information is extracted from the bad data. Wherein, the bad information includes bad name, bad classification, importance, bad data collection personnel information, etc.

[0031] S120: Process the bad information based on a pre-trained data receiving object prediction model to obtain the receiving object information of the bad data.

[0032] Among them, the data receiving object prediction model is used to predict the receiving object of bad data. In an embodiment of the present invention, the bad information is input into the data receiving object prediction model and the pre-trained data is processed by the data receiving object prediction model to obtain the receiving object information of at least one receiving object corresponding to the bad data. Among them, the receiving object information is actually information related to the staff who processes the bad data. It can be understood that since the bad data needs to be processed by a specific object, the bad data needs to be sent to a specific object for processing to avoid the impact of the message on non-specific objects.

[0033] On the basis of the above embodiment, optionally, the data receiving object prediction model includes a bad information classification sub-model and a receiving object prediction sub-model, and the data receiving object prediction model based on pre-training processes the bad information to obtain the receiving object information of the bad data, including: inputting the bad information into the bad information classification sub-model for classification processing to obtain the classification result of the bad information; inputting the bad information classification result into the receiving object prediction sub-model for prediction to obtain the receiving object information of the bad data.

[0034] In an embodiment of the present invention, the bad information is input into the bad information classification sub-model, and the bad information classification sub-model determines the probability that the bad information belongs to each category according to the characteristics of the bad information, and takes the category with the highest probability as the classification result of the bad information. Further, based on the classification result of the bad information, the receiving object prediction sub-model is used to perform prediction to obtain the receiving object information of at least one receiving object of the bad data. Among them, the bad information classification sub-model is a logistic regression model, and the receiving object prediction sub-model is a decision tree model.

[0035] On the basis of the above embodiments, optionally, the training method of the data receiving object prediction model includes: establishing a training sample data set, wherein the training sample data set includes historical bad data and target receiving object information corresponding to the historical bad data; iteratively performing the following steps to obtain the data receiving object prediction model when the training stop condition is met: extracting historical bad information from the historical bad data, and inputting the historical bad information into an initial classification sub-model to obtain a bad classification result of the historical bad data; inputting the bad classification result into an initial prediction sub-model for prediction to obtain predicted receiving object information of the historical bad data; determining a loss function based on the predicted receiving object information and the target receiving object information; and adjusting the network parameters of the initial classification sub-model and the initial prediction sub-model based on the loss function.

[0036] In an embodiment of the present invention, the training process of the data receiving object prediction model is as follows:

[0037] Step 1: Establish a training sample data set, which includes historical bad data and target receiving object information corresponding to the historical bad data; wherein the target receiving object information refers to the information of the object for processing the historical bad data stored in the historical database.

[0038] Step 2: extract historical bad information from the historical bad data, and input the historical bad information into the initial classification sub-model to obtain the bad classification result of the historical bad data;

[0039] Step 3: Input the bad classification results into the initial prediction sub-model for prediction, and obtain the prediction receiving object information of the historical bad data;

[0040] Step 4: Determine the loss function based on the predicted receiving object information and the target receiving object information; and adjust the network parameters of the initial classification sub-model and the initial prediction sub-model using a preset optimization algorithm according to the gradient of the loss function. Among them, the loss function includes but is not limited to the mean square error loss function, the cross entropy loss function, etc., which are not limited here. The preset optimization algorithm includes but is not limited to gradient descent, Adam (Adam optimization algorithm) optimization algorithm, etc.

[0041] Step 5: Iterate step 2 to step 4 to obtain a data receiving object prediction model when the training stop condition is met. The training stop condition may be when the loss function converges and the number of iterations reaches a preset number of iterations, which is not limited here.

[0042] Based on the above embodiment, optionally, establishing a training sample data set includes: obtaining historical bad data and target receiving object information corresponding to the historical bad data; performing data cleaning processing on the historical bad data and the target object information to obtain the processed historical bad data and target object information, and constructing a training sample data set based on the processed historical bad data and target object information.

[0043] In an embodiment of the present invention, historical bad data and target receiving object information corresponding to the historical bad data are obtained from a historical database, and data cleaning processing is performed on the historical bad data and the target object information to obtain the processed historical bad data and the target object information. Among them, the data processing operation of the historical bad data includes duplicate data removal operation, missing value processing operation, error data correction operation, etc., and the duplicate data removal operation is to use a unique identifier (such as ID) or business logic to remove duplicate records. The missing value processing operation is to select filling (such as using mean, median, mode, etc.) or deletion for missing data according to specific circumstances. The error data correction operation is to identify and correct obvious errors in the data, such as format errors, logical errors, etc. Verify information integrity: ensure that each record contains necessary fields, such as name, contact information, etc. The data cleaning processing operation of the target object information includes data standardization operation, deduplication and merging operation, etc. The data standardization operation is used to unify the data format, such as date format, telephone number format, etc. The deduplication and merging operation is used to perform deduplication or merging processing on the possible duplicate target receiving object information. This embodiment can eliminate errors, duplications, missing data and other problems in the data by performing data cleaning processing on historical bad data and target object information, so as to improve data quality.

[0044] On the basis of the above embodiment, optionally, when the training stop condition is met, a data receiving object prediction model is obtained, including: in each training round, for each training sample in the training sample data set, determining whether the target receiving object information and the predicted receiving object information of the training sample are the same, and if they are the same, marking the training sample as a correct sample; determining the accuracy score based on the number of correct samples in the training sample data set and the total number of samples in the training sample data set; if the accuracy score is greater than a preset accuracy threshold, determining the data receiving object prediction model based on the initial classification sub-model and the initial prediction sub-model of the current training round.

[0045] In an embodiment of the present invention, in each training round, for each training sample in the training sample data set, the target receiving object information and the predicted receiving object information in the training sample are compared. If the target receiving object information and the predicted receiving object information are the same, it indicates that the predicted receiving object information is correct, and the training sample is marked as a correct sample. Further, the accuracy score is determined based on the number of correct samples in the training sample data set and the total number of samples in the training sample data set, wherein the accuracy score is the accuracy of the predicted receiving object information obtained by the model prediction of the current training round. Further, the accuracy score is compared with a preset accuracy threshold. If the accuracy score is greater than the preset accuracy threshold, it indicates that the initial classification sub-model and the initial prediction sub-model of the current training round have met the training requirements, and the data receiving object prediction model is determined based on the initial classification sub-model and the initial prediction sub-model of the current training round.

[0046] S130: Send the bad data and the receiving object information to an information publishing server, so that the information publishing server sends the bad data to a second user device corresponding to the receiving object information.

[0047] The second user device is a device for receiving bad data, such as a user terminal. In an embodiment of the present invention, the bad data and the receiving object information are sent to the information publishing server, so that the information publishing server pushes the bad data and sends the bad data to the second user device corresponding to the receiving object information. The information publishing server is a server of an instant messaging system, which is used to push the bad data to the second user device.

[0048] In some embodiments, optionally, the method also includes: obtaining the organizational structure of the receiving object, and determining the parent object information of the receiving object based on the organizational structure and the receiving object information; when preset conditions are met, sending the parent object information to the information publishing server, so that the information publishing server sends the bad data to the second user device corresponding to the parent object information.

[0049] Among them, the organizational structure includes the superior-subordinate relationship between employees of the enterprise. In an embodiment of the present invention, the organizational structure of the receiving object is obtained, and the superior object information of the receiving object can be determined through the organizational structure. When the preset conditions are met, the bad data is sent to the second user device corresponding to the superior object information. Among them, the preset condition can be that the unprocessed time of the bad data is greater than the preset time threshold. Specifically, when the unprocessed time of the bad data is greater than the preset time threshold, the bad data is sent to the second user device corresponding to the superior object information, so that the superior object can supervise the processing of the bad data. It can also be that the sending user performs a copy operation on the first user device. Specifically, when the sending user performs a copy operation on the first user device, while sending the bad data to the second user device corresponding to the receiving object information, the bad data is sent to the second user device corresponding to the superior object information.

[0050] The technical solution of this embodiment receives bad data sent by the first user device and extracts bad information from the bad data; processes the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data; sends the bad data and receiving object information to the information publishing server, so that the information publishing server sends the bad data to the second user device corresponding to the receiving object information. This can prevent staff from receiving information that is irrelevant to them, achieve high-precision information push, and improve work efficiency.

[0051] Embodiment 2

[0052] Figure 2 Schematic diagram of the structure of an information publishing device provided by Embodiment 2 of the present invention. Figure 2 As shown, the system includes: multiple user devices 210, a data processing server 220 and an information publishing server 230; the user device 210 includes a first user device 211 and a second user device 212, the first user device 211 is used to send bad data, and the second user device 212 is used to receive bad data;

[0053] The first user equipment 211 is used for sending the bad data to the data processing server 220 in response to the bad data sending operation;

[0054] The data processing server 220 is used to receive the bad data, extract bad information from the bad data, and input the bad information into a data receiving object prediction model for prediction to obtain receiving object information of the bad data; and send the bad data and the receiving object information to the information publishing server 230;

[0055] The information publishing server 230 is configured to receive the bad data and the receiving object information, and send the bad data to the second user equipment 212 corresponding to the receiving object information.

[0056] The technical solution of this embodiment receives bad data sent by the first user device and extracts bad information from the bad data; processes the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data; sends the bad data and receiving object information to the information publishing server, so that the information publishing server sends the bad data to the second user device corresponding to the receiving object information. This can prevent staff from receiving information that is irrelevant to them, achieve high-precision information push, and improve work efficiency.

[0057] On the basis of the above embodiment, optionally, the data receiving object prediction model includes a bad information classification sub-model and a receiving object prediction sub-model, and the data processing server 220 is specifically used to: input the bad information into the bad information classification sub-model for classification processing to obtain the classification result of the bad information; input the bad information classification result into the receiving object prediction sub-model for prediction to obtain the receiving object information of the bad data.

[0058] Based on the above embodiment, optionally, the bad information classification sub-model is a logistic regression model, and the receiving object prediction sub-model is a decision tree model.

[0059] On the basis of the above embodiment, optionally, the data processing server 220 is also used to: establish a training sample data set, the training sample data set including historical bad data and target receiving object information corresponding to the historical bad data; iteratively perform the following steps to obtain a data receiving object prediction model when the training stop condition is met: extract historical bad information from the historical bad data, and input the historical bad information into the initial classification sub-model to obtain a bad classification result of the historical bad data; input the bad classification result into the initial prediction sub-model for prediction to obtain predicted receiving object information of the historical bad data; determine a loss function based on the predicted receiving object information and the target receiving object information; and adjust the network parameters of the initial classification sub-model and the initial prediction sub-model based on the loss function.

[0060] On the basis of the above embodiment, optionally, the data processing server 220 is also used to: in each training round, for each training sample in the training sample data set, determine whether the target receiving object information and the predicted receiving object information of the training sample are the same; if they are the same, mark the training sample as a correct sample; determine the accuracy score based on the number of correct samples in the training sample data set and the total number of samples in the training sample data set; if the accuracy score is greater than a preset accuracy threshold, determine the data receiving object prediction model based on the initial classification sub-model and the initial prediction sub-model of the current training round.

[0061] Based on the above embodiment, optionally, the data processing server 220 is also used to: obtain historical bad data and target receiving object information corresponding to the historical bad data; perform data cleaning processing on the historical bad data and the target object information to obtain the processed historical bad data and target object information.

[0062] On the basis of the above embodiment, optionally, the data processing server 220 is also used to: obtain the organizational structure of the receiving object, determine the superior object information of the receiving object based on the organizational structure and the receiving object information; and when preset conditions are met, send the superior object information to the information publishing server, so that the information publishing server sends the superior object information to the second user device that sends the bad data to the superior object information.

[0063] The information publishing device provided in the embodiment of the present invention can execute the information publishing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0064] Embodiment 3

[0065] Figure 3 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0066] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0067] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0068] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the information publishing method.

[0069] In some embodiments, the information publishing method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the information publishing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the information publishing method in any other appropriate manner (e.g., by means of firmware).

[0070] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] The computer programs for implementing the information publishing method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0072] Embodiment 4

[0073] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute an information publishing method, the method comprising:

[0074] Receiving bad data sent by the first user equipment, and extracting bad information from the bad data;

[0075] Processing bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of bad data;

[0076] Sending the bad data and the receiving object information to the information publishing server, so that the information publishing server sends the bad data to the second user device corresponding to the receiving object information;

[0077] The first user equipment is used to send bad data, and the second user equipment is used to receive bad data.

[0078] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0079] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0080] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0081] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0082] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0083] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An information publishing method, characterized in that: Applicable to data processing servers, including: Receiving bad data sent by the first user equipment, and extracting bad information from the bad data; Processing the bad information based on a pre-trained data receiving object prediction model to obtain receiving object information of the bad data; Sending the bad data and the receiving object information to an information publishing server, so that the information publishing server sends the bad data to a second user device corresponding to the receiving object information; The first user equipment is used to send bad data, and the second user equipment is used to receive bad data.

2. The method according to claim 1, characterized in that The data receiving object prediction model includes a bad information classification sub-model and a receiving object prediction sub-model. The data receiving object prediction model based on pre-training processes the bad information to obtain the receiving object information of the bad data, including: Inputting the negative information into the negative information classification sub-model for classification processing to obtain the classification result of the negative information; The bad information classification result is input into the receiving object prediction sub-model for prediction to obtain the receiving object information of the bad data.

3. The method according to claim 2, characterized in that The bad information classification sub-model is a logistic regression model, and the receiving object prediction sub-model is a decision tree model.

4. The method according to claim 2, characterized in that: The training method of the data receiving object prediction model comprises: Establishing a training sample data set, wherein the training sample data set includes historical bad data and target receiving object information corresponding to the historical bad data; Iterate the following steps to obtain the data receiving object prediction model when the training stop condition is met: Extracting historical bad information from the historical bad data, and inputting the historical bad information into an initial classification sub-model to obtain a bad classification result of the historical bad data; Inputting the bad classification result into the initial prediction sub-model for prediction, and obtaining the prediction receiving object information of the historical bad data; Determine a loss function based on the predicted receiving object information and the target receiving object information; The network parameters of the initial classification sub-model and the initial prediction sub-model are adjusted based on the loss function.

5. The method according to claim 4, characterized in that The step of obtaining a data receiving object prediction model when the training stop condition is met includes: In each training round, for each training sample in the training sample data set, determining whether the target receiving object information and the predicted receiving object information of the training sample are the same, and if they are the same, marking the training sample as a correct sample; Determine a correctness score based on the number of correct samples in the training sample data set and the total number of samples in the training sample data set; If the accuracy score is greater than a preset accuracy threshold, a data receiving object prediction model is determined based on the initial classification sub-model and the initial prediction sub-model of the current training round.

6. The method according to claim 4, characterized in that The step of establishing a training sample data set includes: Acquire historical bad data and target receiving object information corresponding to the historical bad data; Data cleaning is performed on the historical bad data and the target object information to obtain the processed historical bad data and target object information.

7. The method according to claim 1, characterized in that The method further comprises: Acquire the organizational structure of the receiving object, and determine the parent object information of the receiving object based on the organizational structure and the receiving object information; When a preset condition is met, the upper-level object information is sent to the information publishing server, so that the information publishing server sends the upper-level object information to the second user equipment corresponding to the upper-level object information.

8. An information publishing system, characterized in that: include: A plurality of user devices, a data processing server and an information publishing server; the user devices include a first user device and a second user device, the first user device is used to send bad data, and the second user device is used to receive bad data; The first user equipment is used to send the bad data to the data processing server in response to the bad data sending operation; The data processing server is used to receive the bad data, extract bad information from the bad data, and input the bad information into a data receiving object prediction model for prediction to obtain receiving object information of the bad data; and send the bad data and the receiving object information to an information publishing server; The information publishing server is used to receive the bad data and the receiving object information, and send the bad data to a second user device corresponding to the receiving object information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the information publishing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the information publishing method according to any one of claims 1 to 7 when executed.

Images