WO2020258695A1 - System and method for establishing public material library - Google Patents

Abstract

A method and system for establishing a public material library. The method comprises: acquiring material data in an official account information base, and creating an official account/material data table (S1); creating an initial material library by taking material information as a basic knowledge unit and associations between material categories and material property types as a framework (S2); and adding new material information, and updating the initial material library (S3). The invention can solve the problem associated with unified collection, editing, classification, management and analysis of materials performed for operating a WeChat official account. In a process of editing materials, duplication check is performed on existing titles in a material library, such that a drop in a reading rate due to title duplication can be prevented, thereby ensuring highly efficient and accurate management of a material library.

Description

System and method for establishing public material library Technical field

The invention relates to the field of data processing and management, in particular to a system and method for establishing a public material library.

Background technique

At this stage, various types of WeChat official accounts are nearly saturated, and different people are interested in content that is very different. Vertically segmented WeChat official accounts have more obvious focus, higher user viscosity, and greater marketing opportunities. By establishing differently positioned WeChat official accounts, using content dissemination and planning interaction to attract different types of people, publicity and marketing of WeChat official accounts can enhance corporate brand awareness, reputation and loyalty, and then transform into the potential of corporate brands consumer. In addition, the incubation and operation of WeChat regional accounts and vertical accounts can further promote the construction of Internet informatization and better serve the construction of corporate overall marketing.

The existing software that manages multiple WeChat official accounts at the same time generally only has the function of article management and simultaneous opening of the WeChat official account backend, and each WeChat official account is independent and unrelated to each other. The existing WeChat public account management software does not have corresponding message reminding, auditing, statistical analysis and other functions, and its functions are not perfect. WeChat material can be connected to the WeChat official account backend, and can be directly grouped and edited online, but only the WeChat editor can be used for editing, and the material cannot be directly added to the material synthesizer and then synthesized; in the process of editing the material, the title will be generated Duplication, duplication of titles in the material library will cause a decrease in user reading rate.

Summary of the invention

In order to solve the problems of the prior art, on the one hand, an embodiment of the present invention provides a method for establishing a public material library, characterized in that the method for establishing a public material library includes the following steps:

S1. Obtain the material data in the official account information database and prepare the official account/material data table;

S2. Create an initial material library with material information as the basic knowledge unit and the association between material categories and material attribute types as the framework;

S3. Add material information and update the initial material library.

As a further improvement of the embodiment of the present invention, the steps of adding material information in step S3 and updating the initial material library specifically include:

S301. Add material information and define a new material information unit;

S302: Determine the type of the newly added material information;

S303: Using the framework of the initial material library as a constraint condition and based on the type of the newly added material information unit, identify the material attributes in the newly added material information unit and the association relationship between the material attribute categories, and form candidate material knowledge items;

S304. Correct the candidate material knowledge items and update the initial material library.

As a further improvement of the embodiment of the present invention, the step of adding a material information unit and adding an association relationship further includes:

Perform clustering and classification according to the association between the text in the newly added material information unit and the material attributes extracted from the picture, and the attributes of the text paragraph or image area to which the material information belongs;

Compared with the initial material library, the newly-added material attributes and the newly-added association relationship between the material attributes are obtained, and the new material attributes and the newly-added association relationship between the material attributes are given confidence to form the material candidate knowledge items.

As a further improvement of the embodiment of the present invention, the new material information is added in the step S301, and the definition of the added material information unit also includes extracting the new material title, and judging whether the title of the new material and the title in the material library are Repetitive

If there are repetitions, update the title of the added material;

If there is no repetition, go to S302.

As a further improvement of the embodiment of the present invention, the step of extracting the title of the newly added material, and judging whether the title of the newly added material is overlapped with the title in the material library specifically includes the following steps:

a. Identify the title of the newly added material, and extract the text in the title of the newly added material;

b. Identify the title in the material library, and extract the text of the title in the material library;

c. Calculate the similarity between the title of the newly added material and the title in the material library;

d. Determine the relative magnitude of the similarity and the preset threshold;

If the similarity> the preset threshold, it is determined to be a duplicate, and the title of the newly added material is updated;

If the similarity is less than the preset threshold, it is determined that it is not repeated, and S302 is entered.

On the other hand, the present invention also discloses the above-mentioned public material library establishment system, which includes:

The material information acquisition module is used to obtain the material data in the official account information database and prepare the official account account/material data table;

The material information classification module is used to classify the material data to generate category information, including material category and material attribute type;

The material information increase module is used to add new material information and define new material information knowledge units;

The association relationship increase module is used to identify the association relationship between the material attribute and the material attribute category in the new material information unit;

The initial material library architecture module is used to create an initial material library with material information as the basic knowledge unit and the association relationship between material categories and material attribute types as the framework;

The material library update module is used to update the association relationship between the material information knowledge unit and the material category and the material attribute type in the initial material library;

A communication module, connected to the material information acquisition module, and used for sending and/or receiving material information;

The material storage module is used to store text information and image information as material knowledge units, and store the material information knowledge units and the association relationship; and

The control module is configured to send the material data stored in the material storage module to the external device according to the request of the external device;

The input end of the material information classification module is connected to the material information acquisition module,

The output terminal of the material information acquisition module is connected to the communication module.

As a further improvement of the embodiment of the present invention, the system further includes: a material title duplicate checking module for identifying and judging whether the title of the newly added material is overlapped with the title in the material library;

The material title duplicate checking module includes a material title recognition submodule, a similarity calculation submodule, a title duplication judgment submodule, and a title update submodule. The output terminal of the recognition submodule and the input terminal of the similarity calculation submodule Connected, the output terminal of the similarity calculation submodule is connected with the input terminal of the title duplication judging submodule.

As a further improvement of the embodiment of the present invention, the material library update module further includes a candidate material knowledge item correction unit, which is used to correct the candidate material formed by the association between the newly added material information knowledge unit and the material attribute and the material attribute category. The material knowledge item is corrected; the output end of the candidate material knowledge item correction unit is connected to the input end of the material storage module.

As a further improvement of the embodiment of the present invention, the material information classification module is used to classify according to at least one of information type, storage time, material subject category, and popularity.

As a further improvement of the embodiment of the present invention, the title recognition sub-module is used to identify the title of the material;

The title recognition sub-module includes a text information extraction unit, and the text information extraction unit is used to extract the text in the title of the material and is also used to extract the text of the title in the material database.

As a further improvement of the embodiment of the present invention, the similarity calculation submodule is used to calculate the similarity between the title of the judged material and the title in the material database; the similarity is the text extracted from the title of the material and the The repetition rate of the text extracted from the title in the material database.

As a further improvement of the embodiment of the present invention, the title duplication determination sub-module is used to determine the relative size of the similarity between the title of the material and the title in the material database and a preset threshold; said 0.8<preset threshold<1.

As a further improvement of the embodiment of the present invention, the title update submodule is used to update the title of the identification material when the similarity is greater than the preset threshold; the input of the title update submodule is the same as the title It is judged that the output terminal of the sub-module is connected.

The present invention has the following beneficial effects: it effectively solves the problems of unified collection, editing, classified management and analysis of materials in the operation of WeChat official accounts, WeChat operators can effectively manage the materials of multiple official accounts at the same time, and the materials between accounts are no longer independent Yes, the material interconnection between multiple accounts is realized, and the efficiency of material utilization is improved;

In the process of editing materials, writing titles will cause repetitions. Title repetitions will lead to a decrease in user reading rate, redundancy of material library information and inefficiency of material management; before material submission, check with existing titles in the material library. Heavy, there will be repeated reminders to update the title, and the material without the corresponding title will be stored in the material library, making the material management more efficient.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained from these drawings without creative work.

Figure 1 is a flowchart of a method for establishing a public material library provided by an embodiment of the present invention;

Fig. 2 is a schematic structural diagram of a public material library establishment system provided by an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are merely Some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Example 1

The embodiment of the present invention provides a method for establishing a public material library, as shown in FIG. 1, including the following steps:

S1. Obtain the material data in the official account information database and prepare the official account/material data table;

S2. Create an initial material library with material information as the basic knowledge unit and the association between material categories and material attribute types as the framework;

S3. Add material information and update the initial material library.

As a further improvement of the embodiment of the present invention, the steps of adding material information in step S3 and updating the initial material library specifically include:

S301. Add material information and define a new material information unit;

S302: Determine the type of the newly added material information;

S303: Using the framework of the initial material library as a constraint condition and based on the type of the newly added material information unit, identify the material attributes in the newly added material information unit and the association relationship between the material attribute categories, and form candidate material knowledge items;

S304. Correct the candidate material knowledge items and update the initial material library.

As a further improvement of the embodiment of the present invention, the step of adding a material information unit and adding an association relationship further includes:

Perform clustering and classification according to the association between the text in the newly added material information unit and the material attributes extracted from the picture, and the attributes of the text paragraph or image area to which the material information belongs;

Compared with the initial material library, the newly-added material attributes and the newly-added association relationship between the material attributes are obtained, and the new material attributes and the newly-added association relationship between the material attributes are given confidence to form the material candidate knowledge items.

As a further improvement of the embodiment of the present invention, the new material information is added in the step S301, and the definition of the added material information unit also includes extracting the new material title, and judging whether the title of the new material and the title in the material library are Repetitive

If there are repetitions, update the title of the added material;

If there is no repetition, go to S302.

As a further improvement of the embodiment of the present invention, the step of extracting the title of the newly added material, and judging whether the title of the newly added material is overlapped with the title in the material library specifically includes the following steps:

a. Identify the title of the newly added material, and extract the text in the title of the newly added material;

b. Identify the title in the material library, and extract the text of the title in the material library;

c. Calculate the similarity between the title of the newly added material and the title in the material library;

d. Determine the relative magnitude of the similarity and the preset threshold;

If the similarity> the preset threshold, it is determined to be a duplicate, and the title of the newly added material is updated;

If the similarity is less than the preset threshold, it is determined that it is not repeated, and S302 is entered.

Example 2

The present invention also discloses the above-mentioned public material library establishment system. As shown in Fig. 2, the public material library establishment system includes:

The material information acquisition module is used to obtain the material data in the official account information database and prepare the official account account/material data table;

The material information classification module is used to classify the material data to generate category information, including material category and material attribute type;

The material information increase module is used to add new material information and define new material information knowledge units;

The association relationship increase module is used to identify the association relationship between the material attribute and the material attribute category in the new material information unit;

The initial material library architecture module is used to create an initial material library with material information as the basic knowledge unit and the association relationship between material categories and material attribute types as the framework;

The material library update module is used to update the association relationship between the material information knowledge unit and the material category and the material attribute type in the initial material library;

A communication module, connected to the material information acquisition module, and used for sending and/or receiving material information;

The material storage module is used to store text information and image information as a material knowledge unit, and store the material information knowledge unit and the association relationship; and

The control module is configured to send the material data stored in the material storage module to the external device according to the request of the external device;

The input end of the material information classification module is connected to the material information acquisition module,

The output terminal of the material information acquisition module is connected to the communication module.

Further, the system further includes: a material title duplicate check module, which is used to identify and determine whether the title of the newly added material is overlapped with the title in the material library;

The material title duplicate checking module includes a material title recognition submodule, a similarity calculation submodule, a title duplication judgment submodule, and a title update submodule. The output of the recognition submodule is connected to the input of the similarity calculation submodule, The output terminal of the similarity calculation submodule is connected to the input terminal of the title duplication judgment submodule.

Further, the material library update module further includes a candidate material knowledge item correction unit, which is used to correct the candidate material knowledge item formed by the association relationship between the newly added material information knowledge unit and the material attribute and the material attribute category; The output terminal of the candidate material knowledge item correction unit is connected to the input terminal of the material storage module.

Specifically, the material information classification module is used to classify according to at least one of information type, storage time, material subject category, and popularity.

Specifically, the title recognition sub-module is used to recognize the title of the material;

The title recognition sub-module includes a text information extraction unit, and the text information extraction unit is used to extract the text in the title of the material and is also used to extract the text of the title in the material database.

Further, the similarity calculation sub-module is used to calculate the similarity between the title of the judged material and the title in the material database; the similarity is the text extracted from the title of the material and the title extracted from the material database The repetition rate of the text.

Specifically, the title duplication determination sub-module is used to determine the relative magnitude of the similarity between the title of the material and the title in the material database and a preset threshold; said 0.8<preset threshold<1.

Further, the title update submodule is configured to update the title of the recognized material when the similarity is greater than the preset threshold; the input end of the title update submodule and the output end of the title duplication judgment submodule Connected.

The present invention has the following beneficial effects: it effectively solves the problems of unified collection, editing, classified management and analysis of materials in the operation of WeChat official accounts, WeChat operators can effectively manage the materials of multiple official accounts at the same time, and the materials between accounts are no longer independent Yes, the material interconnection between multiple accounts is realized, and the efficiency of material utilization is improved;

In the process of editing materials, writing titles will cause repetitions. Title repetitions will lead to a decrease in user reading rate, redundancy of material library information and inefficiency of material management; before the material is submitted, check with existing titles in the material library. Heavy, there will be repeated reminders to update the title, and the material without the corresponding title will be stored in the material library, making the material management more efficient.

All the above-mentioned optional technical solutions can be combined in any way to form an optional embodiment of the present invention, which will not be repeated here.

It should be noted that when the public material library establishment system provided in the above embodiment executes the public material library establishment method, only the division of the above functional modules is used as an example. In actual applications, the above functions can be allocated according to needs. It is completed by different functional modules, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above. In addition, the method for establishing a public material library and the system embodiment provided by the above-mentioned embodiment belong to the same concept. For the specific implementation process, please refer to the method embodiment, which will not be repeated here.

Those of ordinary skill in the art can understand that all or part of the steps in the foregoing embodiments can be implemented by hardware, or by a program instructing relevant hardware to be completed. The program can be stored in a computer-readable storage medium. The storage medium mentioned can be a read-only memory, a magnetic disk or an optical disk, etc.

The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection of the present invention. Within range.

Claims (10)

1. A method for establishing a public material library, characterized in that the method for establishing a public material library includes the following steps:

   S1. Obtain the material data in the official account information database and prepare the official account/material data table;

   S2. Create an initial material library with material information as the basic knowledge unit and the association between material categories and material attribute types as the framework;

   S3. Add material information and update the initial material library.
2. The method for establishing a public material library according to claim 1, wherein the step of adding material information in step S3 and updating the initial material library specifically includes:

   S301. Add material information and define a new material information unit;

   S302: Determine the type of the newly added material information;

   S303: Using the framework of the initial material library as a constraint condition and based on the type of the newly added material information unit, identify the material attributes in the newly added material information unit and the association relationship between the material attribute categories, and form candidate material knowledge items;

   S304. Correct the candidate material knowledge items and update the initial material library.
3. The method for establishing a public material library according to claim 2, wherein the step of adding a material information unit and adding an association relationship further comprises:

   Perform clustering and classification according to the association between the text in the newly added material information unit and the material attributes extracted from the picture, and the attributes of the text paragraph or image area to which the material information belongs;

   Compared with the initial material library, the newly-added material attributes and the newly-added association relationship between the material attributes are obtained, and the new material attributes and the newly-added association relationship between the material attributes are given confidence to form the material candidate knowledge items.
4. The method for establishing a public material library according to claim 2, characterized in that, in step S301, adding material information, defining a new material information unit further comprises extracting a new material title, and determining whether the title and Whether the titles in the material library are repeated;

   If there are repetitions, update the title of the added material;

   If there is no repetition, go to S302.
5. The method for managing material information based on a WeChat official account according to claim 4, wherein the step extracts the title of the newly added material, and determines whether the title of the newly added material and the title in the material library overlap specifically. It includes the following steps:

   a. Identify the title of the newly added material, and extract the text in the title of the newly added material;

   b. Identify the title in the material library, and extract the text of the title in the material library;

   c. Calculate the similarity between the title of the newly added material and the title in the material library;

   d. Determine the relative magnitude of the similarity and the preset threshold;

   If the similarity> the preset threshold, it is determined to be a duplicate, and the title of the newly added material is updated;

   If the similarity is less than the preset threshold, it is determined that it is not repeated, and S302 is entered.
6. A public material library establishment system, characterized in that the public material library establishment system includes: a material information acquisition module for obtaining material data in an official account information library to prepare an official account/material data table;

   The material information classification module is used to classify the material data to generate category information, including material category and material attribute type;

   The material information increase module is used to add new material information and define new material information knowledge units;

   The association relationship increase module is used to identify the association relationship between the material attribute and the material attribute category in the new material information unit;

   The initial material library architecture module is used to create an initial material library with material information as the basic knowledge unit and the association relationship between material categories and material attribute types as the framework;

   The material library update module is used to update the association relationship between the material information knowledge unit and the material category and the material attribute type in the initial material library;

   A communication module, connected to the material information acquisition module, and used for sending and/or receiving material information;

   The material storage module is used to store text information and image information as material knowledge units, and store the material information knowledge units and the association relationship; and

   The control module is configured to send the material data stored in the material storage module to the external device according to the request of the external device;

   The input end of the material information classification module is connected to the material information acquisition module,

   The output terminal of the material information acquisition module is connected to the communication module.
7. The public material library establishment system according to claim 6, characterized in that the system further comprises: a material title duplicate checking module, which is used to identify and determine whether the title of the newly added material and the title in the material library Repetitive

   The material title duplicate checking module includes a material title recognition submodule, a similarity calculation submodule, a title duplication judgment submodule, and a title update submodule. The output terminal of the recognition submodule and the input terminal of the similarity calculation submodule Connected, the output terminal of the similarity calculation submodule is connected with the input terminal of the title duplication judging submodule.
8. The public material library establishment system according to claim 6, wherein the material library update module further comprises a candidate material knowledge item correction unit, which is used to correct the difference between the new material information knowledge unit, material attribute, and material attribute category. The candidate material knowledge items formed by the association relationship between them are corrected; the output terminal of the candidate material knowledge item correction unit is connected with the input terminal of the material storage module.
9. The public material library establishment system according to claim 6, wherein the material information classification module is used to classify according to at least one of information type, storage time, material subject category, and popularity.
10. The public material library establishment system according to claim 7, wherein the title recognition sub-module is used to recognize the title of the material;

    The title recognition sub-module includes a text information extraction unit, and the text information extraction unit is used to extract the text in the title of the material and is also used to extract the text of the title in the material database.

Images