Feedback information classification method, device, electronic device, storage medium and product

Abstract

The present disclosure provides a feedback information classification method, device, electronic device, storage medium and product, which relate to the field of computer processing technology, and in particular to the field of application feedback information technology. The specific implementation scheme is: in response to detecting feedback information, obtaining other information related to the feedback information; extracting the characteristics of the feedback information and the other information, and determining the type of the feedback information based on the characteristics. The present disclosure can improve the processing efficiency of feedback information, improve the timeliness of user feedback, and reduce the production cost of business lines.

Description

Technical Field

[0001] The present disclosure relates to the field of computer processing technology, in particular to the field of application feedback information technology, and specifically to a feedback information classification method, device, electronic device, storage medium and product. Background Art

[0002] User generated content (UGC) generally refers to information that users actively feedback. For example, in electronic maps, UGC refers to content information that users actively feedback when using map applications. Content information includes location data error reporting, road data error reporting, emergency event reporting, etc.

[0003] In the related art, the user can report the information that the user needs to report through different option entrances provided on the user reporting page of the map application. Further, the map data update information can be obtained based on the information reported by the user. Summary of the invention

[0004] The present disclosure provides a feedback information classification method, device, electronic device, storage medium and product.

[0005] According to one aspect of the present disclosure, a feedback information classification method is provided, the method comprising:

[0006] In response to detecting feedback information, other information related to the feedback information is acquired; features of the feedback information and the other information are extracted, and based on the features, a type of the feedback information is determined.

[0007] According to a second aspect of the present disclosure, a feedback information classification device is provided, the device comprising:

[0008] The acquisition module is used to acquire other information related to the feedback information in response to detecting the feedback information; the extraction module is used to extract the characteristics of the feedback information and the other information; the determination module is used to determine the type of the feedback information based on the characteristics.

[0009] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0010] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect.

[0011] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect.

[0012] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to the first aspect.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0015] Figure 1 A schematic diagram of a reporting page in the related technology of the embodiment of the present disclosure is shown;

[0016] Figure 2 A schematic diagram showing the processing of feedback information in the related technology of the embodiment of the present disclosure is shown;

[0017] Figure 3 A schematic diagram of a flow chart of a feedback information classification method provided by an embodiment of the present disclosure is shown;

[0018] Figure 4 A schematic diagram of a process for determining the type of feedback information provided by an embodiment of the present disclosure is shown;

[0019] Figure 5 A schematic diagram of a process of training a feedback information classification model provided by an embodiment of the present disclosure is shown;

[0020] Figure 6 A schematic diagram of a multi-classification model based on multi-source information provided by an embodiment of the present disclosure is shown;

[0021] Figure 7 A schematic diagram of automatic matching of business lines based on multi-source information provided by an embodiment of the present disclosure is shown;

[0022] Figure 8 A schematic diagram of the structure of a feedback information classification device provided by an embodiment of the present disclosure is shown;

[0023] Fig. 9 It is a block diagram of an electronic device used to implement the feedback information classification method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] User feedback generally refers to information that users actively provide feedback. For example, in electronic maps, UGC refers to content information that users actively provide feedback when using map applications. Content information includes location data errors, road data errors, and emergency reports.

[0026] In the map application software, a reporting page is provided, which includes different reporting options. Users can report feedback information through different option entrances, and the reported feedback information will be transferred to the corresponding intelligence production business line for processing. Figure 1 FIG. 1 shows a schematic diagram of a reporting page in the related technology of the embodiment of the present disclosure. Figure 1 As shown, the page is displayed as a reporting page in the map application software, and the reporting entrances include location-related entrances, road-related entrances and other reporting entrances. Users can feedback information through different reporting entrances, so that the intelligence information of user feedback content can be processed efficiently and correctly. The user feedback content page provided by the map application software can not only significantly improve the user reporting experience, but also is one of the important information sources for updating the application software map data.

[0027] However, in the related technology, when users report map feedback information, they may make wrong judgments or be unable to make judgments. As a result, a considerable amount of intelligence enters the wrong intelligence production business line, causing this intelligence to circulate secondary between internal business lines. The feedback information is manually classified and delivered to the corresponding intelligence line. Figure 2 FIG. 1 is a schematic diagram showing a process of processing feedback information in a related technology of an embodiment of the present disclosure. Figure 2As shown, under normal circumstances, users report feedback information through the reporting portal, and transmit the feedback information to the corresponding business line. The feedback information business line operation is completed, and the result of the feedback information is sent to the user on the client. Under abnormal circumstances, feedback information is reported through the reporting portal, and the feedback information is transmitted to the wrong business line, resulting in secondary circulation of the feedback information. Through manual processing, the feedback information is transmitted to the correct business line, the operation is completed, and the result of the feedback information is sent to the user on the client. For example, the user mistakenly reports feedback information about road conditions (road speed) to the speed limit business line. Alternatively, problems that cannot be classified are uniformly reported to other road problems or other reports, resulting in at least one manual operation required for business line allocation. Therefore, abnormal reporting of feedback information leads to waste of business line production costs and affects the timeliness of intelligence processing.

[0028] Based on this, the present disclosure provides a feedback information classification method and device. Through deep learning, text information features are extracted, and the features of multi-source information are integrated and input into the machine learning model to accurately classify the text content reported by users and match the intelligence business line. This method can improve the processing efficiency of feedback information, improve the timeliness of user feedback, and reduce the production cost of the business line.

[0029] The following embodiments will illustrate the feedback information classification method and device provided by the present disclosure in conjunction with the accompanying drawings.

[0030] Figure 3 A schematic diagram of a feedback information classification method provided by an embodiment of the present disclosure is shown. Figure 3 As shown in , the method may include:

[0031] In step S110 , in response to detecting the feedback information, other information related to the feedback information is acquired.

[0032] In the disclosed embodiment, taking the application software of the electronic map as an example, the application software of the electronic map can provide the user with a web page for reporting feedback information, and the user can report the information related to the current map based on the page.

[0033] It is understandable that the application software can be applied to various terminals of the user, and the terminal can also be understood as a client.

[0034] In the present disclosure, when feedback information reported by a user is detected, other information related to the feedback information is obtained. The other information can be understood as related information corresponding to multiple different information sources. In the present disclosure, the other information can also be understood as other multi-source information different from the feedback information.

[0035] In step S120, features of the feedback information and other information are extracted, and based on the features, the type of the feedback information is determined.

[0036] In the embodiment of the present disclosure, the required features are extracted based on the detected feedback information and other acquired information. In addition, the feature is at least one feature.

[0037] According to the extracted features, the user's feedback information is analyzed to determine the type corresponding to the feedback information, and further determine the business line corresponding to the feedback information. The business line can also be called an intelligence business line.

[0038] By using the feedback information classification method provided by the present disclosure, the feedback information is analyzed based on the feedback information and other information corresponding to the feedback information, so that the type of the feedback information can be accurately determined. By matching the corresponding business line according to the type of feedback information, the processing efficiency of the feedback information can be improved, and the timeliness of user feedback can be improved. The corresponding business line can be accurately matched to the feedback information to reduce the production cost of the business line.

[0039] In the embodiment of the present disclosure, other information includes at least one of the following:

[0040] The text content of the feedback information;

[0041] Geographic location of feedback information;

[0042] The historical feedback records of the application to which the feedback information belongs; and

[0043] Image information of feedback information.

[0044] In the disclosed embodiment, text encoding features and / or image recognition features of the feedback information may also be extracted, as well as behavioral features and / or geographic features of other information.

[0045] Furthermore, in the present disclosure, the text encoding features of the text content can be extracted based on the pre-trained neural network model. In other words, the present disclosure can map the text content in the feedback information reported by the user to a one-dimensional vector of a specified dimension based on the pre-trained neural network model. The one-dimensional vector of the specified dimension is the text encoding feature.

[0046] The pre-trained neural network model may be a pre-trained language representation model (Bidirectional Encoder Representation from Transformers, BERT). The language representation model adopts a new masked language model (MLM) so as to generate deep bidirectional language representation.

[0047] In the disclosed embodiment, it is first determined whether the feedback information contains an image. In response to the feedback information containing an image, the recognition features in the image are extracted based on the image detection model. For example, recognition features such as road traffic elements and obstacles. The image recognition features can be used as auxiliary information to determine the type of feedback information. If the feedback information does not contain an image, the corresponding part has a default value of 0.

[0048] Among them, the image detection model can be an object recognition and positioning algorithm based on a deep neural network (You Only Look Once, Yolov3), a regional convolutional neural network (Faster-Region CNN) and other models to improve the efficiency of image detection.

[0049] For example, whether there is an electronic eye, a speed limit sign, or a restriction sign (such as no U-turn) in the image: if there is, it is recorded as 1, and if there is no, it is recorded as 0. Whether there is an obstacle (such as a construction barrier, an ice cream cone, an immovable roadblock, etc.): if there is, it is recorded as 1, and if there is no, it is recorded as 0.

[0050] In the embodiment of the present disclosure, the behavior feature includes one or more of the number of feedbacks in the historical feedback record, the number of adoptions in the historical feedback record, and the running state of the application to which the feedback information belongs. The geographic feature includes the spatial dimension feature of the geographic location.

[0051] In the disclosed embodiment, the behavior characteristics refer to the behavior characteristics of the user based on the application software, including the number of contents reported by the user in the map history, the number of times adopted, the navigation status of the user when reporting, and other collectible information. By extracting the user behavior characteristics, the credibility of the feedback information reported by the user can be determined, so that the type of feedback information can be accurately determined.

[0052] For example, the number of content reported by the user in the past, such as 5. The number of valid content reported by the user in the past, such as 1. The most recent navigation status when the user reported: navigation type (driving, public transportation, walking and cycling, recorded as a 3*1 dimensional vector, the corresponding type is marked as 1, and the other is marked as 0). Navigation status (0 after navigation is completed, 1 during navigation).

[0053] In the disclosed embodiment, the geographic feature can be understood as tracing back the most recent navigation route and related locations where the user reported the behavior, and extracting effective spatial dimension features. Among them, the user location point refers to the location where the user reported the behavior, the user error point refers to the error range circled by the user on the map, and the user deviation point refers to the location where the user deviates from the specified navigation planning route.

[0054] For example, the relative distances among the user's location point, the user's error reporting point, and the user's deviation point; if any location information is missing, fill in the default value 0. The user's error reporting point corresponds to road features: including road traffic and road grade.

[0055] In the embodiments of the present disclosure, the extraction of the above-mentioned multiple features can be increased or decreased according to actual conditions, and the type of feedback information is determined based on the multiple features actually extracted, such as the following embodiments.

[0056] Figure 4 A schematic diagram of a process for determining the type of feedback information provided by an embodiment of the present disclosure is shown. Figure 4 As shown in , the method may include:

[0057] In step S210, a predetermined feedback information classification model is obtained.

[0058] In step S220, the features are processed to obtain an information encoding feature vector, and the information encoding feature vector is input into a feedback information classification model to obtain an output result of the feedback information classification model.

[0059] In step S230, the type of feedback information is determined according to the output result.

[0060] In the disclosed embodiment, the feedback information classification model can be applied to the application software as an offline model. The feedback information classification model in the offline model is obtained, and the extracted features are spliced ​​to obtain the information encoding feature vector of the feature. The determined information encoding feature vector is input into the feedback information classification model to obtain the output result of the feedback information classification model. Among them, the output result can be a business line corresponding to the feedback information type. For example, the output result can be business line A, business line B, business line C..., invalid and other information.

[0061] According to the output result of the feedback information classification model, the business line that transmits the feedback information is determined, and it is determined that the feedback information is invalid.

[0062] In the embodiment of the present disclosure, the offline feedback information classification model is predetermined, and the determination process is as follows.

[0063] Figure 5 A flow chart of a training feedback information classification model provided by an embodiment of the present disclosure is shown, Figure 5 As shown in , the method may include:

[0064] In step S310, historical feedback information, other historical information related to the historical feedback information, and a real type corresponding to the historical feedback information are obtained.

[0065] In step S320, features of historical feedback information and other historical information are extracted.

[0066] In step S330, the features are processed to obtain an information encoding feature vector, the information encoding feature vector is used as input, the true type is used as output, a multi-classification model is trained, and a feedback information classification model is obtained.

[0067] In the disclosed embodiment, a large amount of historical data needs to be obtained, including historical feedback information, other historical information related to the historical feedback information, and the real type corresponding to the historical feedback information. Among them, the real type corresponding to the historical feedback information can be understood as the business line corresponding to the historical feedback information.

[0068] Extract the text encoding features and / or image recognition features corresponding to the text content of the historical feedback information, as well as the behavioral features and geographic features of other historical information. Further extract one or more of the number of feedbacks recorded in the historical feedback, the number of adoptions recorded in the historical feedback, the running status of the application to which the feedback information belongs, and the spatial dimension features.

[0069] The extracted features are processed to obtain an information encoding feature vector, the information encoding feature vector is used as input and the true type is used as output, a multi-classification model is trained, and a feedback information classification model is obtained.

[0070] For example, Figure 6 A schematic diagram of a multi-classification model based on multi-source information provided by an embodiment of the present disclosure is shown. Figure 6 As shown in , text coding features are extracted through user-reported content (i.e., feedback information), user behavior features are extracted through user-reported historical behavior information, user geographic features are extracted through user-reported location information, and image recognition features are extracted through user-uploaded pictures. If the corresponding features are extracted, the extracted features are represented by numbers, and the unextracted features are recorded as 0. The extracted features are spliced ​​to obtain an information coding feature vector. As in the above embodiment, the information coding feature vector is spliced ​​from the features of multiple information sources. In the present disclosure, the information coding feature vector can also be referred to as a multi-source information coding vector. For example, 1005... is used to characterize the multi-source information coding feature vector.

[0071] The multi-classification model of machine learning is trained by using the information encoding feature vector and the corresponding real type of feedback information, and a feedback information classification model whose output is the business line corresponding to the feedback information is obtained.

[0072] After determining the type of feedback information, the feedback information needs to be delivered to the corresponding business line. The implementation process is as follows.

[0073] In the embodiment of the present disclosure, after obtaining the type of feedback information, the corresponding relationship between the type of feedback information and the business line can also be obtained. And according to the determined type of feedback information and the corresponding relationship, the feedback information is transmitted to the corresponding business line.

[0074] In the present disclosure, there is a corresponding relationship between the feedback information and the business line to which it belongs. For example, if the feedback information is speed limit information, it corresponds to the speed limit business line. If the feedback information is road condition information, it corresponds to the road condition business line.

[0075] Obtain the correspondence between the feedback information and the business line, and based on the correspondence, determine the business line corresponding to the current feedback information, and transmit the feedback information to the corresponding business line to complete the operation.

[0076] In the disclosed embodiment, after the feedback information reported by the user is transmitted to the corresponding business line, the reporting result can also be fed back on the client used by the user.

[0077] For example, Figure 7 A schematic diagram of automatic matching of business lines based on multi-source information provided by an embodiment of the present disclosure is shown. Figure 7 As shown in the figure, the user uploads feedback information through the reporting portal, and the business line corresponding to the feedback information (for example, business line A) is determined based on a predetermined multi-source information classification service (i.e., a pre-trained feedback information classification model). The job corresponding to the user's feedback information is completed, and the reporting result is fed back on the user's client.

[0078] Through this method, the business line corresponding to the feedback information reported by the user can be accurately obtained, so that the feedback information can be accurately transmitted to the corresponding business line without manual secondary operation on the erroneous feedback information transmitted to the business line. This not only reduces the operating cost of transmitting the feedback information, but also improves the efficiency of transmitting the feedback information to the business line and the timeliness of the user's feedback.

[0079] Based on Figure 1 The same principle as shown in the method, Figure 8 A schematic diagram of the structure of a feedback information classification device provided by an embodiment of the present disclosure is shown. Figure 8 As shown, the feedback information classification device 100 may include:

[0080] The acquisition module 101 is used to acquire other information related to the feedback information in response to detecting the feedback information; the extraction module 102 is used to extract the features of the feedback information and the other information; the determination module 103 is used to determine the type of the feedback information based on the features.

[0081] In the embodiment of the present disclosure, the other information includes at least one of the following:

[0082] The text content of the feedback information;

[0083] The geographical location of the feedback information;

[0084] Historical feedback records of the application to which the feedback information belongs; and

[0085] The feedback information includes image information.

[0086] In the disclosed embodiment, the extraction module 102 is used to extract text encoding features and / or image recognition features of the feedback information.

[0087] In the embodiment of the present disclosure, the extraction module 102 is used to extract the behavioral features and / or geographic features of the other information.

[0088] In the embodiment of the present disclosure, the behavior feature includes one or more of the number of feedbacks in the historical feedback records, the number of adoptions in the historical feedback records, and the running state of the application to which the feedback information belongs.

[0089] In the embodiment of the present disclosure, the geographic feature includes a spatial dimension feature of a geographic location.

[0090] In the embodiment of the present disclosure, the determination module 103 is used to obtain a predetermined feedback information classification model; process the features to obtain an information encoding feature vector, input the information encoding feature vector to the feedback information classification model, and obtain an output result of the feedback information classification model; and determine the type of the feedback information based on the output result.

[0091] In the embodiment of the present disclosure, the determination module 103 is used to obtain historical feedback information, other historical information related to the historical feedback information, and the true type corresponding to the historical feedback information; extract the features of the historical feedback information and the other historical information; process the features to obtain an information encoding feature vector, use the information encoding feature vector as input and the true type as output, train a multi-classification model, and obtain the feedback information classification model.

[0092] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0093] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0094] Fig. 9A schematic block diagram of an example electronic device 200 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 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 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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 disclosure described and / or required herein.

[0095] like Fig. 9 As shown, the device 200 includes a computing unit 201, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 202 or a computer program loaded from a storage unit 208 into a random access memory (RAM) 203. In the RAM 203, various programs and data required for the operation of the device 200 can also be stored. The computing unit 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0096] A number of components in the device 200 are connected to the I / O interface 205, including: an input unit 206, such as a keyboard, a mouse, etc.; an output unit 207, such as various types of displays, speakers, etc.; a storage unit 208, such as a disk, an optical disk, etc.; and a communication unit 209, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 209 allows the device 200 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The computing unit 201 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 201 performs the various methods and processes described above, such as the method feedback information classification method. For example, in some embodiments, the method feedback information classification method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 208. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 200 via ROM 202 and / or communication unit 209. When the computer program is loaded into RAM 203 and executed by the computing unit 201, one or more steps of the method feedback information classification method described above may be performed. Alternatively, in other embodiments, the computing unit 201 may be configured to perform the method feedback information classification method in any other appropriate manner (e.g., by means of firmware).

[0098] 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.

[0099] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may 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.

[0100] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. 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.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein may be implemented in a computing system that includes back-end 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 front-end 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 back-end components, middleware components, or front-end 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), and the Internet.

[0103] A computer 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 relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0104] 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 recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. 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 disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A feedback information classification method, characterized in that: The method comprises: In response to detecting the feedback information, acquiring other information related to the feedback information; extracting features of the feedback information and the other information, and determining a type of the feedback information based on the features; Determine the business line corresponding to the type of the feedback information; The feedback information is the content information actively fed back by the user in the process of using the electronic map; the content information includes at least one of the following: location data error reporting, road data error reporting, and emergency event reporting; The other information includes at least one of the following: The text content of the feedback information; The geographical location of the feedback information; Historical feedback records of the application to which the feedback information belongs; and The feedback information includes image information.

2. The method according to claim 1, wherein: The extracting the feature of the feedback information includes: Extract text encoding features and / or image recognition features of the feedback information.

3. The method according to claim 1, wherein: The extracting the features of the other information includes: The behavioral characteristics and / or geographic characteristics of the other information are extracted.

4. The method according to claim 3, wherein: The behavior feature includes one or more of the number of feedbacks in the historical feedback records, the number of adoptions in the historical feedback records, and the running state of the application to which the feedback information belongs.

5. The method according to claim 3, wherein: The geographic features include spatial dimension features of the geographic location.

6. The method according to any one of claims 1 to 5, wherein: The determining the type of the feedback information based on the feature includes: Obtaining a predetermined feedback information classification model; Processing the features to obtain an information encoding feature vector, inputting the information encoding feature vector into the feedback information classification model, and obtaining an output result of the feedback information classification model; The type of the feedback information is determined according to the output result.

7. The method according to claim 6, wherein: The determining the feedback information classification model comprises: Acquire historical feedback information, other historical information related to the historical feedback information, and the real type corresponding to the historical feedback information; Extracting features of the historical feedback information and the historical other information; The feature is processed to obtain an information encoding feature vector, the information encoding feature vector is used as input, the true type is used as output, a multi-classification model is trained, and the feedback information classification model is obtained.

8. A feedback information classification device, characterized in that: The device comprises: an acquisition module, configured to acquire other information related to the feedback information in response to detecting the feedback information; An extraction module, used to extract features of the feedback information and other information; A determination module, configured to determine the type of the feedback information based on the feature; A business module, used to determine the business line corresponding to the type of the feedback information; The feedback information is the content information actively fed back by the user in the process of using the electronic map; the content information includes at least one of the following: location data error reporting, road data error reporting, and emergency event reporting; The other information includes at least one of the following: The text content of the feedback information; The geographical location of the feedback information; Historical feedback records of the application to which the feedback information belongs; and The feedback information includes image information.

9. The device according to claim 8, wherein: The extraction module is used to: Extract text encoding features and / or image recognition features of the feedback information.

10. The device according to claim 8, wherein: Extraction module for: The behavioral characteristics and / or geographic characteristics of the other information are extracted.

11. The device according to claim 10, wherein: The behavior feature includes one or more of the number of feedbacks in the historical feedback records, the number of adoptions in the historical feedback records, and the running state of the application to which the feedback information belongs.

12. The device according to claim 10, wherein: The geographic features include spatial dimension features of the geographic location.

13. The device according to any one of claims 8 to 12, wherein: The determining module is used to: Obtaining a predetermined feedback information classification model; Processing the features to obtain an information encoding feature vector, inputting the information encoding feature vector into the feedback information classification model, and obtaining an output result of the feedback information classification model; The type of the feedback information is determined according to the output result.

14. The device according to claim 13, wherein: The determining module is used to: Acquire historical feedback information, other historical information related to the historical feedback information, and the real type corresponding to the historical feedback information; Extracting features of the historical feedback information and the historical other information; The feature is processed to obtain an information encoding feature vector, the information encoding feature vector is used as input, the true type is used as output, a multi-classification model is trained, and the feedback information classification model is obtained.

15. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

17. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images