Information classification method, device and computer equipment

Abstract

The application relates to an information classification method and device, computer equipment, a storage medium and a computer program product. The information classification method comprises the following steps: obtaining sample features corresponding to a plurality of pieces of to-be-classified information; the sample features are extracted from the to-be-classified information by a target end according to at least one pre-set classification vocabulary; the classification features of the to-be-classified information are calculated according to the sample features; the information type corresponding to the to-be-classified information is determined according to the classification features and a pre-set information type; and the sample features, the classification features and the corresponding information type of the to-be-classified information are stored correspondingly. Through the setting, the terminal can directly extract the sample features, the server obtains the sample features of the to-be-classified information from the terminal instead of the complete content of the to-be-classified information, the extraction and transmission of the complete to-be-classified information are avoided, communication resources are saved, and user privacy is ensured.

Description

Technical Field

[0001] This application relates to the field of computer applications, and in particular to an information classification method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] As electronic devices become increasingly sophisticated, more and more devices can not only meet users' communication needs but also provide more intelligent services based on user information, greatly facilitating users' work and life. For example, electronic devices can collect and analyze users' text messages, distinguishing between spam, advertising, and useful information to provide users with text message classification services and an efficient and convenient text message display interface.

[0003] The method of classifying text messages based on their content is similar to that of spam filtering, using methods such as blacklists / whitelists, keyword matching, and machine learning. However, since text message content involves user privacy, common classification methods can no longer meet current needs. Furthermore, common text message classification methods are not only not accurate enough, but also slow in classification speed. Summary of the Invention

[0004] Therefore, it is necessary to provide an information classification method, apparatus, computer equipment, storage medium, and computer program product that can improve classification accuracy in response to the above-mentioned technical problems.

[0005] Firstly, this application provides an information classification method, including:

[0006] Acquire sample features corresponding to multiple pieces of information to be classified; the sample features are extracted from the information to be classified by the target end according to at least one pre-set classification vocabulary;

[0007] Based on the sample characteristics, calculate the classification features of the information to be classified;

[0008] Based on the classification features and the pre-set information types, determine the information type corresponding to the information to be classified;

[0009] The sample features and classification features of the information to be classified are stored in correspondence with the information types.

[0010] In one embodiment, the information classification method further includes:

[0011] According to a pre-set update frequency, the latest at least one category vocabulary is sent to the target end so that the target end updates the category vocabulary according to the received latest category vocabulary;

[0012] The sample features are extracted from the information to be classified by the target end based on the latest classification vocabulary received.

[0013] In one embodiment, the sample features include the number of times each of the various classification terms is matched from the information to be classified;

[0014] The step of calculating the classification features of the information to be classified based on the sample features includes:

[0015] The classification features of the information to be classified are calculated based on the number of times each of the various classification terms is matched from the information to be classified and the pre-set weight values ​​of each of the classification terms.

[0016] In one embodiment, after storing the sample features and classification features of the information to be classified in correspondence with the corresponding information types, the method further includes:

[0017] Send the information type corresponding to the information to be classified to the target end.

[0018] In one embodiment, after sending the information type corresponding to the information to be classified to the target end, the method further includes:

[0019] Receives an information type change instruction from the target terminal; the information type change instruction carries an information tag;

[0020] Based on the information tag, the classification feature corresponding to the information type change instruction is matched;

[0021] Change the information type corresponding to the matched classification feature to the information type indicated by the information type change instruction.

[0022] In one embodiment, before determining the information type corresponding to the information to be classified based on the classification features and a pre-set information type, the process includes:

[0023] The classification features are matched with the classification features corresponding to the stored information to be classified;

[0024] The step of determining the information type corresponding to the information to be classified based on the classification features and the pre-set information type includes:

[0025] When a stored classification feature that is identical to the classification feature is matched, the information type corresponding to the matched classification feature is taken as the information type of the information to be classified.

[0026] In one embodiment, determining the information type corresponding to the information to be classified based on the classification features and a pre-set information type includes:

[0027] The classification features are input into a pre-trained prediction model to obtain the predicted probability that the classification features belong to each of the information types.

[0028] Based on the predicted probability, the information type corresponding to the classification feature is determined.

[0029] Secondly, this application also provides an information classification device, comprising:

[0030] The acquisition module is used to acquire sample features corresponding to multiple pieces of information to be classified; the sample features are extracted from the information to be classified by the target end according to at least one pre-set classification vocabulary;

[0031] The calculation module is used to calculate the classification features of the information to be classified based on the sample features;

[0032] The determination module is used to determine the information type corresponding to the information to be classified based on the classification features and the pre-set information type.

[0033] The storage model is used to store the sample features and classification features of the information to be classified in correspondence with the corresponding information types.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the information classification method described in any of the above embodiments.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the information classification method described in any of the above embodiments.

[0036] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the information classification method described in any of the above embodiments.

[0037] The aforementioned information classification method, apparatus, computer equipment, storage medium, and computer program products can send classification terms to the terminal, enabling the terminal to directly extract sample features. The server obtains sample features of the information to be classified from the terminal, rather than the complete content of the information to be classified, thus avoiding the extraction and transmission of the complete information to be classified. This not only saves communication resources but also protects user privacy. By assigning corresponding weight values ​​to different classification terms, dynamic adjustment of classification features is achieved, further enabling the final classification result to favor the information type corresponding to the key classification terms. When the server has a stored classification feature that is the same as the classification feature, the information type corresponding to the stored classification feature can be directly used as the information type of the current classification feature, thereby achieving rapid classification. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating an information classification method in one embodiment;

[0039] Figure 2 This is a diagram illustrating the application environment of the information classification method in one embodiment;

[0040] Figure 3 This is a flowchart illustrating an information classification method in one embodiment;

[0041] Figure 4 This is a flowchart illustrating an information classification method in one embodiment;

[0042] Figure 5 This is a flowchart illustrating an information classification method in one embodiment;

[0043] Figure 6 This is a flowchart illustrating an information classification method in one embodiment;

[0044] Figure 7 This is a flowchart illustrating the information classification device in one embodiment;

[0045] Figure 8 This is a flowchart illustrating the information classification device in one embodiment;

[0046] Figure 9 This is a flowchart illustrating the information classification device in one embodiment;

[0047] Figure 10 This is a flowchart illustrating the information classification device in one embodiment;

[0048] Figure 11 This is a flowchart illustrating the determination module in an information classification device in one embodiment;

[0049] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] In one embodiment, an information classification method is provided, such as Figure 1 As shown, this information classification method includes:

[0052] Step 202: Obtain sample features corresponding to multiple pieces of information to be classified; the sample features are extracted from the information to be classified by the target end according to at least one pre-set classification vocabulary.

[0053] Uncategorized information refers to SMS messages received by users, including verification code SMS messages, express delivery information SMS messages, financial information SMS messages, special offer SMS messages, business notification SMS messages, etc.

[0054] Sample features can refer to the content of the SMS message, the sender of the SMS message, the format of the SMS message, and information related to the sender of the SMS message; for example, sample features can be some fields contained in the SMS message content, the identity information of the SMS sender, whether a Uniform Resource Locator (URL) exists, whether the SMS message contains a signature, whether the SMS message contains a phone number, etc.

[0055] Category terms refer to a set of at least one word that is classified into the same field or with the same meaning. For example, "express delivery," "parcel," and "pickup code" are classified as express delivery information terms; "income," "expense," and "deduction" are classified as financial information terms; and "on sale," "hot-selling," and "benefits" are classified as special offers terms, and so on.

[0056] like Figure 2 As shown, the target terminal can be a user's terminal 102 receiving SMS messages. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Correspondingly, the information classification method in this embodiment can be applied to server 104. Server 104 stores at least one classification term and the received sample features in a data storage system. It is understood that the data storage system can be an independent storage device, or the data storage system can be located on a server, or the data storage system can be located on another terminal.

[0057] Step 204: Calculate the classification features of the information to be classified based on the sample features.

[0058] Categorical features refer to the characteristic information that can characterize the category of an SMS message. Categorical features are used to distinguish between different categories of information to be classified.

[0059] As an example, the sample features are numerically processed to obtain classification features for subsequent processing.

[0060] Step 206: Determine the information type corresponding to the information to be classified based on the classification features and the pre-set information types.

[0061] Message type refers to a pre-defined category used to further categorize SMS messages. For example, message types may include verification codes, express delivery information, financial information, special offers, business notifications, etc.

[0062] Step 208: Store the sample features and classification features of the information to be classified in correspondence with the information type.

[0063] In this embodiment, the sample features, classification features, and information types of the information to be classified are linked one-to-one and then stored on the server.

[0064] In this embodiment, the terminal can obtain the content of at least one pre-set classification vocabulary from the server, and extract sample features from at least one received information to be classified based on the classification vocabulary. The server obtains the sample features corresponding to at least one information to be classified from the terminal, avoiding the extraction and transmission of complete information to be classified, which not only saves communication resources but also protects user privacy.

[0065] In some optional embodiments, the information classification method further includes:

[0066] According to a pre-set update frequency, the latest at least one category word is sent to the target end so that the target end can update the category words according to the latest category words received.

[0067] Sample features are extracted from the information to be classified by the target end based on the latest classification vocabulary received.

[0068] In this embodiment, the target terminal can be at least one terminal connected to the server. The server sends at least one category term stored on the server to the terminal according to a pre-set update frequency to ensure that the category term used by the terminal to extract sample features is up-to-date. For example, a worker can modify the content of the category term stored on the server through the terminal. The server sends the modified category term content to the terminal according to a pre-set update frequency. The terminal deletes the saved category term content and stores the newly received modified category term, which is then used to extract sample features. This setup ensures that the sample features obtained by the server are most closely related to the latest modified category term content by the worker.

[0069] In some optional embodiments, the sample features include the number of times various classification words are matched from the information to be classified; step 204 includes: calculating the classification features of the information to be classified based on the number of times various classification words are matched from the information to be classified and the pre-set weight values ​​of various classification words.

[0070] In this embodiment, the terminal sequentially matches the SMS text content of the information to be classified with various category words and obtains the number of times it matches the words in each category word.

[0071] As an example, the terminal stores category terms for express delivery information ("express delivery," "parcel," "pickup code"), financial information ("account," "income," "expense," "deduction," "balance"), and special offers ("promotion," "recharge," "hot sale," "benefits," "free," "great value"). The first text message to be categorized reads, "Your account was deducted X yuan on XX / XX / XX, current account balance XXX yuan." The second text message to be categorized reads, "XX Supermarket's anniversary promotion: recharge 100 yuan to enjoy double the balance, great value, and a chance to enjoy free express delivery service." The first text message to be categorized is then compared with the various category terms. The matching results show that the message matched 0 times with the category terms for express delivery information, 4 times with the category terms for financial information (including the words "account," "deduction," "account," and "balance"), and 0 times with the category terms for special offers. Matching the text content of the second message to be categorized with each category term shows that it matched 1 time with the category terms for express delivery information (including the word "express delivery"), 1 time with the category terms for financial information (including the word "balance"), and 3 times with the category terms for special offers (including the words "activity," "recharge," and "great value").

[0072] Furthermore, the server obtains the sample features corresponding to each piece of information to be classified from the terminal. Since the sample features are derived from various classification terms, the server further multiplies the values ​​in the sample features with the pre-set weight values ​​of the corresponding classification terms to obtain the classification features.

[0073] Specifically, staff input the weight values ​​corresponding to several category terms via a terminal and send them to the server. The server stores the weight values ​​for each category term. By changing the weight values ​​of different categories of terms, type bias can be achieved during the SMS classification process. For example, assigning higher weight values ​​to financial information category terms can make the classification feature data of the information to be classified more prominently reflect the relevant features of financial information, thereby achieving feature bias control for different types of SMS messages.

[0074] As an example, as shown above, the sample features of the first piece of information to be classified can be summarized as three-dimensional features {0, 4, 0}, and the sample features of the second piece of information to be classified can be summarized as three-dimensional features {1, 1, 3}. The server pre-stores the weight values ​​of the classification terms for express delivery information (1), financial information (1.5), and special offers (0.8). The server multiplies the sample features {0, 4, 0} of the first piece of information to be classified by the weight values ​​of the corresponding classification terms to obtain the classification features {0, 6, 0} of the first piece of information to be classified. Multiplying the sample features {1, 1, 3} of the first piece of information to be classified by the weight values ​​of the corresponding classification terms to obtain the classification features {1, 1.5, 2.4} of the second piece of information to be classified.

[0075] In another embodiment, in addition to using the number of times various classification words are matched from the information to be classified as sample features, the terminal can also obtain sample features based on the identity information of the SMS sender in the information to be classified, whether a Uniform Resource Locator (URL) exists, whether an SMS signature is included, and whether a phone number is included.

[0076] The server can preset two identity lists, used as a whitelist and a blacklist. If the identity information of the SMS sender of the information to be classified matches the identity information in the whitelist, the sample feature of the corresponding dimension of the information to be classified is set to 1. If the identity information of the SMS sender of the information to be classified matches the identity information in the blacklist, the sample feature of the corresponding dimension of the information to be classified is set to 0. If the identity information of the SMS sender of the information to be classified does not match the identity information in either the whitelist or the blacklist, the sample feature of the corresponding dimension of the information to be classified is set to 0.5.

[0077] If the information to be classified contains a URL, the sample feature of the corresponding dimension is 1; if the information to be classified contains a text message signature, the sample feature of the corresponding dimension is 1; if the information to be classified contains a phone number, the sample feature of the corresponding dimension is 1; otherwise, the sample feature of the corresponding dimension is 0.

[0078] As an example, the server pre-stores whitelists A and B, and blacklists C and D. As shown above, the identity information of the sender of the first SMS message to be classified is A, there is no URL, it contains an SMS signature, and it contains a phone number. Therefore, its final classification feature is a six-dimensional feature {0, 6, 0, 1, 0, 1, 1}. The identity information of the sender of the second SMS message to be classified is D, there is a URL, it does not contain an SMS signature, and it does not contain a phone number. Therefore, its final classification feature is a six-dimensional feature {1, 1.5, 2.4, 0, 1, 0, 0}.

[0079] In this embodiment, the server can pre-set weight values ​​for various categorized words to adjust the emphasis of categorization features.

[0080] like Figure 3 As shown, in some optional embodiments, after step 208, the method further includes:

[0081] Step 210: Send the information type corresponding to the information to be classified to the target end.

[0082] As an example, the target end can pre-set multiple storage areas according to the pre-defined information types to store information to be classified of different types. After the server sends the information type of the information to be classified to the target end, the target end can store the information to be classified into the corresponding storage area according to the information type, so as to realize the detailed classification of SMS messages.

[0083] like Figure 4 As shown, in some optional embodiments, after step 2010, the method further includes:

[0084] Step 212: Receive the information type change instruction sent by the target terminal; the information type change instruction carries an information tag;

[0085] Step 214: Match the classification features corresponding to the information type change instruction based on the information tags;

[0086] Step 216: Change the information type corresponding to the matched classification feature to the information type indicated by the information type change instruction.

[0087] Information type change command refers to the command issued by the user through the terminal to change the information type corresponding to the information to be classified.

[0088] As an example, when the server determines that a piece of information to be classified belongs to the category of financial information, it sends the information that the information type corresponding to the classification feature of the information to be classified is financial information to the target end, and the target end stores the information to be classified in the storage area corresponding to the category of financial information.

[0089] Furthermore, when users view the unclassified information stored in different storage areas on the terminal, if they have any objections to the terminal's classification, they can change the storage area of ​​the unclassified information to correct the information type corresponding to the unclassified information. At this time, the terminal generates an information type change action for the information to be updated, and further automatically generates an information type change instruction and sends it to the server.

[0090] Information tags are used to uniquely identify classification features. As an example, when a server receives sample features of any information to be classified and calculates the classification features, it assigns an identity tag to it for subsequent quick matching and searching of stored sample features-classification features-information types. The information tag can be a tag with the same content as the identity tag, and the information tag can be composed of at least one of letters, characters, or numbers.

[0091] In one embodiment, the information type change instruction may be issued by the target end in response to the information type corresponding to the classification features of the received information to be classified.

[0092] like Figure 5 As shown, in some optional embodiments, before step 206, the method includes: step 205, matching the classification feature with the classification feature corresponding to the stored information to be classified; step 206 includes: when a stored classification feature that is the same as the classification feature is matched, the information type corresponding to the matched classification feature is used as the information type of the information to be classified.

[0093] In this embodiment, after the server calculates the classification features corresponding to the information to be classified, it can first match the classification features with previously stored classification features. If the match is successful, the information type corresponding to the matched classification features is extracted and directly used as the information type of the information to be classified. This setting speeds up the process of determining the type of information to be classified with the same classification features.

[0094] like Figure 6 As shown, in some optional embodiments, step 206 includes:

[0095] Step 2062: Input the classification features into the pre-trained prediction model to obtain the predicted probability of the classification features belonging to each information type;

[0096] Step 2064: Determine the information type corresponding to the classification feature based on the predicted probability.

[0097] The prediction model can be a Bayesian model. As an example, the Bayesian model uses the Naive Bayes algorithm with the assumption of probability independence to obtain the predicted probability.

[0098] As an example, in step 204, n classification features are obtained, denoted as X1, X2, X3…X n Each categorical feature contains m-dimensional features, X i =(X i1 X i2 …X im Let i ∈ n, and the server pre-sets k information types. The server inputs each of the n classification features into a pre-trained prediction model. According to Bayes' theorem, it can obtain X. i Belongs to Y j The probability of the category P(Y) j |X i ), j∈k:

[0099]

[0100] The Naive Bayes algorithm assumes that the features X in each dimension i1 X i2 …X im Assuming that they are mutually independent, the final Naive Bayes classifier after transformation is expressed as:

[0101]

[0102] The classification features are input into the prediction model, and the prediction model with the highest prediction probability is selected. The information type corresponding to the highest prediction probability is taken as the information type corresponding to the classification feature.

[0103] In the aforementioned information classification method, the server sends at least one classification term to the terminal, enabling the terminal to directly extract sample features corresponding to different information to be classified based on the classification term. The server can determine the type of the SMS message without obtaining the complete SMS content, avoiding the extraction and transmission of the complete information to be classified, thus saving communication resources and protecting user privacy. The server can also set different weight values ​​for different classification terms to dynamically adjust the classification features of the information to be classified that match the key classification terms, thereby making the final prediction result of the information to be classified biased towards the information type corresponding to the key classification terms. The server can match the classification features of the information to be classified with previously stored sample features-classification features-information types, and directly use the information type corresponding to the matched classification feature as the information type corresponding to the current classification feature, thereby accelerating the type determination of the information to be classified. Based on each classification feature, the Naive Bayes algorithm is used to obtain the predicted probability of the information to be classified belonging to each information type, reducing the model's computational load and accelerating the prediction process.

[0104] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0105] Based on the same inventive concept, this application also provides a memory data access apparatus for implementing the memory data access method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more memory data access apparatus embodiments provided below can be found in the limitations of the memory data access method described above, and will not be repeated here.

[0106] In one embodiment, such as Figure 7 As shown, an information classification device 700 is provided, including: an acquisition module 702, a calculation module 704, a determination module 706, and a storage model 708, wherein:

[0107] The acquisition module 702 is used to acquire sample features corresponding to multiple pieces of information to be classified; the sample features are extracted from the information to be classified by the target end according to at least one pre-set classification vocabulary;

[0108] The calculation module 704 is used to calculate the classification features of the information to be classified based on the sample features;

[0109] The determination module 706 is used to determine the information type corresponding to the information to be classified based on the classification features and the pre-set information type.

[0110] The storage module 708 is used to store the sample features and classification features of the information to be classified in correspondence with the information type.

[0111] In some optional embodiments, the acquisition module 702 is further configured to:

[0112] According to a pre-set update frequency, the latest at least one category word is sent to the target end so that the target end can update the category words according to the latest category words received.

[0113] The sample features are extracted from the information to be classified by the target end based on the latest classification vocabulary received.

[0114] In some optional embodiments, the sample features include the number of times various classification words are matched from the information to be classified; the calculation module 704 is also configured to calculate the classification features of the information to be classified based on the number of times various classification words are matched from the information to be classified and the pre-set weight values ​​of various classification words.

[0115] like Figure 8 As shown, in some optional embodiments, the information classification device 700 further includes:

[0116] The sending module 710 is used to send the information type corresponding to the information to be classified to the target end.

[0117] like Figure 9 As shown, in some optional embodiments, the information classification device 700 further includes:

[0118] The receiving module 712 is used to receive the information type change instruction sent by the target end; the information type change instruction carries an information tag.

[0119] The first matching module 714 is used to match the information to be classified corresponding to the information type change instruction based on the information tag;

[0120] Modify module 716 to change the information type corresponding to the matched information to be classified to the information type indicated by the information type change instruction.

[0121] like Figure 10 As shown, in some optional embodiments, the information classification device 700 further includes:

[0122] The second matching module 705 is used to match the classification features with the classification features corresponding to the stored information to be classified;

[0123] The determining module 706 is further configured to: when a stored classification feature that is identical to the classification feature is matched, use the information type corresponding to the matched classification feature as the information type of the information to be classified.

[0124] like Figure 11 As shown, in some optional embodiments, the determining module 706 includes:

[0125] The prediction unit 7062 is used to input the classification features into a pre-trained prediction model to obtain the predicted probability that the classification features belong to each information type.

[0126] The determination unit 7064 is used to determine the information type corresponding to the classification feature based on the predicted probability.

[0127] Each module in the aforementioned information classification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0128] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an information classification method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0129] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0130] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the various steps of the information classification method described above.

[0131] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the various steps of the information classification method described above.

[0132] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0133] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of classifying information, characterized by, The method comprises the following steps: obtaining sample features corresponding to a plurality of pieces of information to be classified; the sample features are extracted from the information to be classified by a target terminal according to at least one classification vocabulary set in advance; a server calculates classification features of the information to be classified according to the sample features; wherein the sample features include the number of times of matching various classification vocabularies from the information to be classified; the server calculates the classification features of the information to be classified according to the sample features, which comprises the following steps: calculating the classification features of the information to be classified according to the number of times of matching various classification vocabularies from the information to be classified and the weight values of the various classification vocabularies set in advance; the server determines the information type corresponding to the information to be classified according to the classification features and the information type set in advance; storing the sample features, the classification features and the corresponding information type of the information to be classified correspondingly.

2. The method of claim 1, wherein, The method further comprises the following steps: sending the latest at least one classification vocabulary to the target terminal according to a preset update frequency, so that the target terminal updates the classification vocabulary according to the received latest classification vocabulary; the sample features are extracted from the information to be classified by the target terminal according to the received latest classification vocabulary.

3. The method of claim 1, wherein, After the step of storing the sample features, the classification features and the corresponding information type of the information to be classified correspondingly, the method further comprises the following step: sending the information type corresponding to the information to be classified to the target terminal.

4. The method of claim 3, wherein, After the step of sending the information type corresponding to the information to be classified to the target terminal, the method further comprises the following steps: receiving an information type changing instruction sent by the target terminal; the information type changing instruction carries an information label; matching the classification features corresponding to the information type changing instruction according to the information label; changing the information type corresponding to the matched classification features to the information type indicated by the information type changing instruction.

5. The method of claim 4, wherein, Before the step of determining the information type corresponding to the information to be classified according to the classification features and the information type set in advance, the method further comprises the following step: matching the classification features with the stored classification features corresponding to the information to be classified; The step of determining the information type corresponding to the information to be classified according to the classification features and the information type set in advance comprises the following step: when the same stored classification features as the classification features are matched, the information type corresponding to the matched classification features is taken as the information type of the information to be classified.

6. The method of claim 1, wherein, The step of determining the information type corresponding to the information to be classified according to the classification features and the information type set in advance comprises the following steps: inputting the classification features into a pre-trained prediction model to obtain prediction probabilities of the classification features belonging to various information types; determining the information type corresponding to the classification features according to the prediction probabilities.

7. An information classifying apparatus characterized by comprising: The method comprises the following steps: an obtaining module is configured to obtain sample features corresponding to a plurality of pieces of information to be classified; the sample features are extracted from the information to be classified by a target terminal according to at least one classification vocabulary set in advance; A computing module is configured to calculate a classification feature of the information to be classified according to the sample feature; wherein the sample feature comprises a number of times of matching the information to be classified to various classification vocabularies; the computing module is further configured to calculate the classification feature of the information to be classified according to the number of times of matching the information to be classified to various classification vocabularies and a pre-set weight value of various classification vocabularies; A determining module is configured to determine an information type corresponding to the information to be classified according to the classification feature and a pre-set information type; A storage model is configured to store the sample feature, the classification feature and the corresponding information type of the information to be classified.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the information classification method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the information classification method in any one of claims 1 to 6.

10. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program product is executed by the processor to implement the steps of the information classification method in any one of claims 1 to 6.

Images