A service evaluation processing method, device and electronic equipment
By acquiring and analyzing internal and external business evaluation information, identifying satisfaction levels and scope of influence, the problem of incomplete business evaluation information collection was solved, resulting in more accurate and comprehensive evaluation results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INDUSTRIAL AND COMMERCIAL BANK OF CHINA
- Filing Date
- 2023-06-21
- Publication Date
- 2026-06-02
AI Technical Summary
The existing technology suffers from incomplete collection of business evaluation information, leading to low evaluation accuracy.
Obtain internal and external evaluation information of the target business, identify satisfaction levels through sentiment classification models, and calculate the overall satisfaction and scope of influence by combining the influence of external evaluation information, thereby determining the evaluation results of the business.
This improves the accuracy and comprehensiveness of business evaluations, ensuring that the evaluation results are more reliable and comprehensive.
Smart Images
Figure CN116738293B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer multimedia information processing, and more specifically, to a business evaluation processing method, apparatus, and electronic device. Background Technology
[0002] Currently, there are two main methods for collecting and optimizing user feedback: one is to collect customer evaluations at offline outlets, including questionnaires, handwritten reviews, and verbal feedback; the other is to collect customer complaints and feedback online, such as through voice services. Under the existing feedback methods, firstly, frontline staff may prioritize resolving complex issues hindering customer use, neglecting optimization suggestions; secondly, the current collection scope is not broad enough, resulting in the loss of much genuine user feedback and low accuracy in business evaluations.
[0003] There is currently no effective solution to the problem of incomplete collection of business evaluation information in related technologies, which leads to low accuracy of business evaluation. Summary of the Invention
[0004] The main objective of this application is to provide a business evaluation processing method, apparatus, and electronic device to solve the problem of incomplete business evaluation information collection in related technologies, which leads to low accuracy of business evaluation.
[0005] To achieve the above objectives, according to one aspect of this application, a business evaluation processing method is provided. The method includes: acquiring N pieces of business evaluation information corresponding to a target business, wherein the N pieces of business evaluation information include M pieces of internal evaluation information acquired within the target business system and NM pieces of external evaluation information acquired outside the target business system, wherein N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M; determining the satisfaction level corresponding to each of the N pieces of business evaluation information, and determining the influence range corresponding to each of the NM pieces of external evaluation information; determining the overall satisfaction level of the target business based on the satisfaction levels corresponding to each of the N pieces of business evaluation information; determining the overall influence range of the target business based on the influence ranges corresponding to each of the NM pieces of external evaluation information; and determining the evaluation result of the target business based on the overall satisfaction level and the overall influence range.
[0006] To achieve the above objectives, according to another aspect of this application, a business evaluation processing apparatus is provided. The apparatus includes: a first acquisition module, configured to acquire N pieces of business evaluation information corresponding to a target business, wherein the N pieces of business evaluation information include M pieces of internal evaluation information acquired within the target business system and NM pieces of external evaluation information acquired outside the target business system, wherein N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M; a second determination module, configured to determine the satisfaction level corresponding to each of the N pieces of business evaluation information and to determine the influence range corresponding to each of the NM pieces of external evaluation information; a third determination module, configured to determine the overall satisfaction level of the target business based on the satisfaction levels corresponding to each of the N pieces of business evaluation information; a fourth determination module, configured to determine the overall influence range of the target business based on the influence ranges corresponding to each of the NM pieces of external evaluation information; and a fifth determination module, configured to determine the evaluation result of the target business based on the overall satisfaction level and the overall influence range.
[0007] To achieve the above objectives, according to another aspect of this application, an electronic device is also provided, including one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the above-described business evaluation processing methods.
[0008] This application employs the following steps: obtaining N pieces of business evaluation information corresponding to the target business, wherein the N pieces of business evaluation information include M internal evaluation information obtained from within the target business system and NM external evaluation information obtained from outside the target business system, where N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M; determining the satisfaction level corresponding to each of the N pieces of business evaluation information and determining the influence scope corresponding to each of the NM external evaluation information; determining the overall satisfaction level of the target business based on the satisfaction levels corresponding to the N pieces of business evaluation information; determining the overall influence scope of the target business based on the influence scope corresponding to the NM external evaluation information; and determining the evaluation result of the target business based on the overall satisfaction level and the overall influence scope. This achieves the goal of accurately determining the business evaluation result based on the business satisfaction level and influence scope, solving the problem of incomplete collection of business evaluation information in related technologies, which leads to low accuracy in business evaluation. This ultimately improves the accuracy and comprehensiveness of business evaluation. Attached Figure Description
[0009] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0010] Figure 1 This is a flowchart of a business evaluation processing method provided according to an embodiment of this application;
[0011] Figure 2 This is a schematic diagram of a deep neural network model structure provided according to an embodiment of this application;
[0012] Figure 3 This is a schematic diagram of an optional business evaluation processing method according to an embodiment of this application;
[0013] Figure 4 This is a schematic diagram of a business evaluation processing apparatus provided according to an embodiment of this application;
[0014] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation
[0015] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0016] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0017] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0018] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, if there is an interface between this system and the relevant user or organization, before obtaining the relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information from the aforementioned user or organization.
[0019] The following describes this application in conjunction with the preferred implementation steps. Figure 1 This is a flowchart of a business evaluation processing method provided according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:
[0020] Step S101: Obtain N service evaluation information corresponding to the target service. The N service evaluation information includes M internal evaluation information obtained from within the target service system and NM external evaluation information obtained from outside the target service system. N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M.
[0021] Optionally, all N business evaluation information entries are in text format, including M internal evaluation entries obtained from within the target business system and NM external evaluation entries obtained from outside the target business system. The external evaluation information from the target business system is obtained using web crawling technology based on preset keywords.
[0022] In one optional embodiment, obtaining the aforementioned M internal evaluation information items includes: obtaining M initial evaluation information items corresponding to the target business obtained within the target business system; determining the format corresponding to each of the M initial evaluation information items, wherein the format corresponding to each of the M initial evaluation information items is at least one of the following: text format, voice format, and image format; if it is determined that the aforementioned M initial evaluation information items include evaluation information in voice format and / or image format, performing text conversion processing on the evaluation information in voice format and / or image format to obtain the aforementioned M internal evaluation information items.
[0023] Optionally, internal evaluation information can be collected through oral and questionnaire surveys, or through image collection of voice recordings and handwritten opinions. The initial evaluation information can be in at least one of the following formats: text, voice, or image. If the initial evaluation information is in voice format, a speech-to-text model is used to convert it into text. If the initial evaluation information is in image format, an image-to-text model is used to convert it into text, resulting in text-based internal evaluation information. By collecting evaluation information in multiple formats—text, voice, and images—related to the target business, the evaluation information is obtained more comprehensively, leading to more accurate and reliable final evaluation results for the target business.
[0024] Step S102: Determine the satisfaction level corresponding to each of the above N business evaluation information items, and determine the scope of influence corresponding to each of the above NM external evaluation information items.
[0025] Optionally, the satisfaction level corresponding to each of the N business evaluation information is obtained by performing sentiment classification on each of the N business evaluation information; the influence range corresponding to each of the NM external evaluation information is determined based on the number of comments, reposts and likes corresponding to each of the NM external evaluation information.
[0026] In one optional embodiment, determining the satisfaction level corresponding to each of the N service evaluation information items includes: using an emotion classification model to perform emotion recognition on each of the N service evaluation information items to obtain the emotion classification results corresponding to each of the N service evaluation information items; and determining the satisfaction level corresponding to each of the N service evaluation information items based on the emotion classification results corresponding to each of the N service evaluation information items.
[0027] Optionally, the sentiment classification model includes at least pre-trained models such as BERT, RoBERT, and AlBERT. The sentiment classification model is used to perform sentiment recognition on N business evaluation information, and the sentiment classification results corresponding to the N business evaluation information are obtained as very dissatisfied, dissatisfied, no emotion, satisfied, and very satisfied, respectively. Based on the sentiment classification results corresponding to the N business evaluation information, the satisfaction levels of 1, 2, 3, 4, and 5 corresponding to the N business evaluation information are obtained.
[0028] In one optional embodiment, determining the influence range corresponding to each of the NM external evaluation information items includes: based on the evaluation parameters corresponding to each of the NM external evaluation information items, using a pre-trained influence range classification model to obtain the influence range corresponding to each of the NM external evaluation information items, wherein the evaluation parameters corresponding to each of the NM external evaluation information items include at least the number of comments, the number of reposts, and the number of likes corresponding to each of the NM external evaluation information items.
[0029] Optionally, the evaluation parameters corresponding to each of the NM external evaluation pieces should include at least the number of comments, reposts, and likes for each of the NM external evaluation pieces. The influence range corresponding to each of the NM external evaluation pieces is obtained using a pre-trained deep-learning neural network (DNN) model.
[0030] It should be noted that externally obtained evaluation information is usually public, and users can comment, forward, like, etc., on each piece of external evaluation information. The number of comments, forwards, and likes can, to some extent, reflect the scope of influence of external evaluation information. Determining the scope of influence of external evaluation information based on a comprehensive analysis of the number of comments, forwards, and likes improves the accuracy and reliability of this determination.
[0031] In an optional embodiment, the method further includes: obtaining K sample evaluation information, and evaluation parameters and influence ranges corresponding to the K sample evaluation information respectively, wherein the evaluation parameters corresponding to the K sample evaluation information respectively include at least: the number of comments, the number of reposts, and the number of likes corresponding to the K sample evaluation information respectively; and training an initial deep neural network model based on the evaluation parameters and influence ranges corresponding to the K sample evaluation information respectively to obtain the influence range classification model.
[0032] Optionally, the K sample evaluation information can be obtained using a web crawler, including the number of comments, reposts, and likes corresponding to each of the K sample evaluation information. A DNN model can then be used to train the model to obtain a trained influence range classification model. For example, Figure 2 This is a schematic diagram of the DNN model structure provided in the embodiments of this application. The DNN adopts a 3-layer fully connected network with a network size of 4*8*6. It then passes through a softmax classifier to output the final propagation influence level, such as... Figure 2 As shown.
[0033] Step S103: Based on the satisfaction levels corresponding to the above N business evaluation information, determine the overall satisfaction level of the above target business.
[0034] Optionally, the average of the satisfaction levels corresponding to the N business evaluation information is calculated, and the average of the satisfaction levels corresponding to the N business evaluation information is used as the overall satisfaction level of the target business.
[0035] In one optional embodiment, determining the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information includes: calculating the average value of the satisfaction levels corresponding to the N service evaluation information; and using the average value of the satisfaction levels corresponding to the N service evaluation information as the overall satisfaction level.
[0036] Optionally, the average of the satisfaction levels corresponding to the N service evaluation messages can be used as the overall satisfaction level of the target service. It can be understood that the satisfaction levels corresponding to the N service evaluation messages reflect the satisfaction of different users with the target service, while the overall satisfaction level obtained by calculating the average of the satisfaction levels corresponding to the N service evaluation messages reflects the average satisfaction level of multiple users with the target service.
[0037] In one optional embodiment, determining the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information includes: obtaining L evaluation tables corresponding to the target service; performing feature extraction processing on the L evaluation tables to obtain the satisfaction levels corresponding to the L evaluation tables; and calculating the average of the satisfaction levels corresponding to the N service evaluation information and the satisfaction levels corresponding to the L evaluation tables to obtain the overall satisfaction level.
[0038] Optionally, obtain L evaluation tables corresponding to the target business, and extract the satisfaction level corresponding to each of the L evaluation tables; use the average of the satisfaction levels corresponding to the N business evaluation information and the satisfaction levels corresponding to the L evaluation tables as the comprehensive satisfaction level.
[0039] Optionally, in practical applications, business evaluation information for the target service can be obtained not only through internal system access and external network access, but also through questionnaires. The L evaluation forms mentioned above were obtained through questionnaires. By combining these methods to determine the overall satisfaction level of the target service, the business evaluation information obtained through questionnaires, internal system access, and external network access will be comprehensively assessed, resulting in more comprehensive information and a more accurate and reliable overall satisfaction level.
[0040] Step S104: Based on the impact range corresponding to the above NM external evaluation information, determine the comprehensive impact range of the above target business.
[0041] Optionally, the overall impact range is determined by the average of the impact ranges corresponding to the NM external evaluation information items.
[0042] In one optional embodiment, determining the comprehensive impact range of the target business based on the impact ranges corresponding to the NM external evaluation information items includes: calculating the average value of the impact ranges corresponding to the NM external evaluation information items, and using the average value of the impact ranges corresponding to the NM external evaluation information items as the comprehensive impact range.
[0043] Optionally, by calculating the average of the impact ranges corresponding to the NM external evaluation information items, the comprehensive impact range can be obtained, which can reflect the degree of comprehensive impact of the target business on the social scale.
[0044] Step S105: Based on the above-mentioned comprehensive satisfaction level and the above-mentioned comprehensive impact range, determine the evaluation result of the above-mentioned target business.
[0045] Optionally, when conducting business evaluations, in addition to considering users' overall satisfaction with the business, factors affecting the scope of the business's impact should also be taken into account. This more comprehensive consideration of factors leads to more accurate and reliable business evaluation results.
[0046] In an optional embodiment, determining the evaluation result of the target service based on the overall satisfaction level and the overall influence range includes: determining a first weight value corresponding to the overall satisfaction level and a second weight value corresponding to the overall influence range; and obtaining the evaluation result of the target service based on the overall satisfaction level, the first weight value, the overall influence range, and the second weight value.
[0047] Optionally, a weighted summation of the overall satisfaction level and the overall influence scope can be performed to obtain the evaluation result of the target business. That is, the evaluation result of the target business equals the overall satisfaction level multiplied by its corresponding first weight value, plus the overall influence scope multiplied by its corresponding second weight value. It can be understood that different factors may have different degrees of influence on the evaluation result of the target business; that is, the satisfaction level and the influence scope may have different impacts on the evaluation result. Based on this, when evaluating the target business, different weight values are assigned to overall satisfaction and the overall influence scope, and a weighted summation is performed on both to obtain the evaluation result of the target business.
[0048] In an optional embodiment, after determining the evaluation result of the target service based on the overall satisfaction level and the overall impact range, the method further includes: extracting keywords from the N service evaluation information to obtain evaluation keywords corresponding to the target service; determining the service type and the number of evaluations corresponding to the target service; and generating a service report corresponding to the target service based on the service type, the number of evaluations, the evaluation keywords, the overall satisfaction level, the overall impact range, and the evaluation result.
[0049] Optionally, keywords are extracted from N business evaluation information to obtain the evaluation keywords corresponding to the target business; the business type, number of evaluations, evaluation keywords, overall satisfaction level, overall impact scope, and evaluation results corresponding to the target business are determined, and a business report corresponding to the target business is generated.
[0050] Through steps S101 to S105, the goal of accurately determining the business evaluation results based on the business satisfaction level and the scope of influence can be achieved, solving the problem of incomplete business evaluation information collection and low accuracy in related technologies. This ultimately improves the accuracy and comprehensiveness of business evaluations.
[0051] Based on the above embodiments and optional embodiments, this application proposes an optional implementation method. Figure 3 This is a flowchart of an optional business evaluation processing method according to an embodiment of this application, such as... Figure 3 As shown, the method includes:
[0052] Step S1: Obtain M initial evaluation information entries obtained from within the target business system.
[0053] Step S2: If the initial evaluation information is determined to be in the form of speech, a speech-to-text model is used to convert the speech-to-text evaluation information into text; if the initial evaluation information is determined to be in the form of image, an image-to-text model is used to convert the image-to-text evaluation information into text.
[0054] Step S3: Use web crawler technology to obtain NM external evaluation information from outside the target business system. Fill in the obtained information as customer evaluation, number of comments, number of reposts and number of likes. Fill in 4 for evaluation source, the feedback time is the time when the customer published the article, and fill in 5 for evaluation status (to be analyzed).
[0055] Step S4: Build a database specifically to store all evaluations. The database table structure can be designed as shown in Table 1 below.
[0056] Table 1
[0057]
[0058]
[0059] The meaning of each field is as follows:
[0060] An auto-incrementing column is a unique sequence number for each record in the database.
[0061] Evaluation sources: The data dictionary includes: 1-Collected from offline employees, 2-Collected from voice recordings, 3-Collected from images, and 4-Collected from social media web crawlers;
[0062] Account feedback time: This is the date the customer submits their feedback or evaluation.
[0063] System entry time: This is the time when the customer review information is stored in the database; no manual entry is required.
[0064] Business scenario type: These are custom scenarios, such as 1-Telephone banking business line, 2-Mobile banking business line, 6-Branch service, 7-Branch infrastructure;
[0065] Satisfaction rating: There are five levels, with level 1 indicating extreme dissatisfaction and level 5 indicating extreme satisfaction;
[0066] Scope of impact: Divided into 5 levels, from 1 to 5, indicating an increasing degree of impact;
[0067] Analysis status: The data dictionary has 1-Employee data collected and analyzed, 2-Employee data collected and to be analyzed, 3-Speech conversion data collected and to be analyzed, 4-Image conversion data collected and to be analyzed, 5-Web crawler data collected and to be analyzed, and 6-Analysis completed;
[0068] The number of comments, reposts, and likes should be filled in when the evaluation source is 4; other sources can be left blank.
[0069] For evaluations collected through oral reports or questionnaires, staff will enter customer feedback and fill in the form with "customer feedback time, business scenario classification, satisfaction level, and scope of impact," while also setting "analysis method" to 1. If staff cannot determine "business scenario classification, satisfaction level, and scope of impact," they do not need to fill in these information, and the analysis status will be set to 2 (pending analysis).
[0070] For both voice collection and handwritten feedback image collection, the voice and image are first recognized and converted into text format. Then, the information is automatically filled into the business report, including customer evaluation, evaluation source, customer feedback time, and entry into the system. At the same time, the analysis status is set to 3 and 4 (to be analyzed).
[0071] For social media articles and comments obtained by the automated crawler, fill in the customer reviews, review sources, customer feedback time, and enter them into the system in Table 1, while setting the analysis status to 5 (to be analyzed).
[0072] For records whose analysis status is pending (i.e., 2, 3, 4, 5), Natural Language Processing (NLP) technology will be used to perform a unified analysis of the customer feedback content.
[0073] Step S5: Use a sentiment classification model to perform sentiment recognition on each of the N business evaluation information pieces, and obtain the sentiment classification results corresponding to each of the N business evaluation information pieces.
[0074] Step S6: Based on the sentiment classification results corresponding to the N business evaluation information, obtain the satisfaction levels of 1, 2, 3, 4, and 5 corresponding to the N business evaluation information, and fill the analysis results into the "Business Scenario Classification, Satisfaction Level" column, while setting the analysis status to 6.
[0075] Step S7: Use web crawler technology to obtain K sample evaluation information, including the number of comments, reposts and likes corresponding to the K sample evaluation information. Use a DNN model to train and obtain a trained influence range classification model.
[0076] Step S8: Based on the number of comments, reposts and likes corresponding to NM external evaluation information, a pre-trained influence range classification model is used to obtain the influence range corresponding to NM external evaluation information, and the analysis results are filled into the "Influence Range" column.
[0077] Step S9: Obtain L evaluation tables corresponding to the target business, perform feature extraction processing on each of the L evaluation tables, and obtain the satisfaction level corresponding to each of the L evaluation tables.
[0078] Step S10: Take the average of the satisfaction levels corresponding to the N business evaluation information and the satisfaction levels corresponding to the L evaluation tables as the comprehensive satisfaction level.
[0079] Step S11: The average value of the influence range corresponding to each of the NM external evaluation information items, and the average value of the influence range corresponding to each of the NM external evaluation information items, are taken as the comprehensive influence range.
[0080] Step S12: Calculate the evaluation result of the target business. The evaluation result of the target business is equal to the comprehensive satisfaction level multiplied by the corresponding first weight value plus the comprehensive influence range multiplied by the corresponding second weight value.
[0081] Step S13: Extract keywords from N business evaluation information to obtain the evaluation keywords corresponding to the target business.
[0082] Step S14: Determine the business type, number of evaluations, evaluation keywords, overall satisfaction level, overall impact scope, and evaluation results corresponding to the target business, and generate a business report corresponding to the target business, as shown in Table 2 below.
[0083] Table 2
[0084]
[0085]
[0086] Step S15: Automatically send to the head of each business line. This can be done by connecting to an email system. First, assign a head to each business line. After the report is generated, send it automatically to the head of the business line in the first column of the main sender table, and copy other business line heads.
[0087] The embodiments of this invention can achieve at least the following technical effects: 1. The system establishes a database specifically for storing all reviews and supports speech recognition and image recognition, automatically categorizing customer voice and text reviews into text format for storage. 2. The system automatically retrieves articles and comments on social media related to ICBC banking services. 3. Based on NLP technology, the system analyzes text, identifying user experience scenarios and user satisfaction; based on a DNN model, it can analyze the social dissemination scope of online reviews. 4. The system can automatically generate analysis reports according to a custom cycle and automatically send them to the responsible persons for all business scenarios.
[0088] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.
[0089] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0090] This application also provides a service evaluation processing apparatus. It should be noted that the service evaluation processing apparatus of this application can be used to execute the service evaluation processing method provided in this application. The service evaluation processing apparatus provided in this application is described below.
[0091] Figure 4 This is a schematic diagram of a service evaluation processing apparatus according to an embodiment of this application. Figure 4 As shown, the device includes: a first acquisition module 401, a first determination module 402, a second determination module 403, a third determination module 404, and a fourth determination module 405, wherein,
[0092] The first acquisition module 401 is used to acquire N business evaluation information corresponding to the target business. The N business evaluation information includes M internal evaluation information acquired from within the target business system and NM external evaluation information acquired from outside the target business system. N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M.
[0093] The first determining module 402 is connected to the first acquiring module 401 and is used to determine the satisfaction level corresponding to the N business evaluation information and the influence range corresponding to the NM external evaluation information.
[0094] The second determining module 403 is connected to the first determining module 402 and determines the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information.
[0095] The third determining module 404, connected to the second determining module 403, determines the comprehensive impact range of the target business based on the impact range corresponding to the NM external evaluation information items.
[0096] The fourth determining module 405, connected to the third determining module 404, determines the evaluation result of the target business based on the comprehensive satisfaction level and the comprehensive impact range.
[0097] In this application, a first acquisition module 401 is set up to acquire N pieces of business evaluation information corresponding to the target business. These N pieces of business evaluation information include M internal evaluation information acquired from within the target business system and NM external evaluation information acquired from outside the target business system, where N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M. A first determination module 402 is used to determine the satisfaction level corresponding to each of the N pieces of business evaluation information and the influence range corresponding to each of the NM external evaluation information. A second determination module 403 determines the overall satisfaction level of the target business based on the satisfaction levels corresponding to each of the N pieces of business evaluation information. A third determination module 404 determines the overall influence range of the target business based on the influence ranges corresponding to each of the NM external evaluation information. A fourth determination module 405 determines the evaluation result of the target business based on the overall satisfaction level and the overall influence range. This achieves the goal of accurately determining the business evaluation result based on the business satisfaction level and influence range, solving the problem of incomplete collection of business evaluation information and resulting in low accuracy of business evaluations in related technologies. This resulted in improved accuracy and comprehensiveness in business evaluation.
[0098] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0099] It should be noted that the first acquisition module 401, the first determination module 402, the second determination module 403, the third determination module 404, and the fourth determination module 405 mentioned above correspond to steps S101 to S105 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but they are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.
[0100] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.
[0101] The aforementioned business evaluation processing device includes a processor and a memory. All of the aforementioned units are stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.
[0102] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and their parameters can be adjusted (for the purposes of this application).
[0103] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0104] This application provides a non-volatile storage medium storing a program that, when executed by a processor, implements the aforementioned business evaluation processing method.
[0105] This application provides a processor for running a program, wherein the program executes the aforementioned business evaluation processing method during runtime.
[0106] like Figure 5 As shown in the illustration, this application provides an electronic device 10, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring N service evaluation information items corresponding to a target service, wherein the N service evaluation information items include M internal evaluation information items acquired within the target service system and NM external evaluation information items acquired outside the target service system, where N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M; determining the satisfaction level corresponding to each of the N service evaluation information items, and determining the influence range corresponding to each of the NM external evaluation information items; determining the overall satisfaction level of the target service based on the satisfaction level corresponding to each of the N service evaluation information items; determining the overall influence range of the target service based on the influence range corresponding to each of the NM external evaluation information items; and determining the evaluation result of the target service based on the overall satisfaction level and the overall influence range. The device in this document can be a server, PC, PAD, mobile phone, etc.
[0107] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: acquiring N pieces of business evaluation information corresponding to a target business, wherein the N pieces of business evaluation information include M pieces of internal evaluation information acquired within the target business system and NM pieces of external evaluation information acquired outside the target business system, wherein N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M; determining the satisfaction level corresponding to each of the N pieces of business evaluation information, and determining the influence range corresponding to each of the NM pieces of external evaluation information; determining the overall satisfaction level of the target business based on the satisfaction levels corresponding to each of the N pieces of business evaluation information; determining the overall influence range of the target business based on the influence ranges corresponding to each of the NM pieces of external evaluation information; and determining the evaluation result of the target business based on the overall satisfaction level and the overall influence range.
[0108] Optionally, the aforementioned computer program product is also suitable for executing an initialization program with the following steps: using an emotion classification model to perform emotion recognition on the aforementioned N business evaluation information respectively, and obtaining the emotion classification results corresponding to the aforementioned N business evaluation information respectively; based on the emotion classification results corresponding to the aforementioned N business evaluation information respectively, determining the satisfaction level corresponding to the aforementioned N business evaluation information respectively.
[0109] Optionally, the aforementioned computer program product is also suitable for executing a program that initializes the following steps: based on the evaluation parameters corresponding to the aforementioned NM external evaluation information, a pre-trained influence range classification model is used to obtain the influence range corresponding to the aforementioned NM external evaluation information, wherein the evaluation parameters corresponding to the aforementioned NM external evaluation information include at least the number of comments, the number of reposts, and the number of likes corresponding to the aforementioned NM external evaluation information.
[0110] Optionally, the aforementioned computer program product is also suitable for executing an initialization program with the following method steps: obtaining K sample evaluation information, and the evaluation parameters and influence range corresponding to the K sample evaluation information respectively, wherein the evaluation parameters corresponding to the K sample evaluation information respectively include at least: the number of comments, the number of reposts, and the number of likes corresponding to the K sample evaluation information respectively; and training an initial deep neural network model based on the evaluation parameters and influence range corresponding to the K sample evaluation information respectively to obtain the aforementioned influence range classification model.
[0111] Optionally, the aforementioned computer program product is also suitable for executing a program that initializes the following steps: The determination of the overall satisfaction level of the target business based on the satisfaction levels corresponding to the N business evaluation information items includes: calculating the average of the satisfaction levels corresponding to the N business evaluation information items; and using the average of the satisfaction levels corresponding to the N business evaluation information items as the overall satisfaction level; The determination of the overall influence range of the target business based on the influence ranges corresponding to the NM external evaluation information items includes: calculating the average of the influence ranges corresponding to the NM external evaluation information items; and using the average of the influence ranges corresponding to the NM external evaluation information items as the overall influence range.
[0112] Optionally, the aforementioned computer program product is also suitable for executing an initialization program with the following method steps: obtaining L evaluation tables corresponding to the aforementioned target service; performing feature extraction processing on the aforementioned L evaluation tables respectively to obtain the satisfaction level corresponding to the aforementioned L evaluation tables respectively; calculating the satisfaction level corresponding to the aforementioned N service evaluation information respectively, and the average value of the satisfaction level corresponding to the aforementioned L evaluation tables respectively, to obtain the aforementioned comprehensive satisfaction level.
[0113] Optionally, the aforementioned computer program product is also suitable for executing an initialization program with the following method steps: determining a first weight value corresponding to the aforementioned overall satisfaction level and a second weight value corresponding to the aforementioned overall influence range; and obtaining the evaluation result of the aforementioned target business based on the aforementioned overall satisfaction level, the aforementioned first weight value, the aforementioned overall influence range, and the aforementioned second weight value.
[0114] Optionally, the aforementioned computer program product is also suitable for executing a program that initializes the following steps: obtaining M initial evaluation information items corresponding to the target business obtained internally by the target business system; determining the form corresponding to each of the M initial evaluation information items, wherein the form corresponding to each of the M initial evaluation information items is at least one of the following: text form, voice form, and image form; if it is determined that the M initial evaluation information items include evaluation information in voice form and / or image form, performing text conversion processing on the evaluation information in voice form and / or image form to obtain the aforementioned M internal evaluation information items.
[0115] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0116] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0117] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0118] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0119] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0120] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0121] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0122] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0123] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0124] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A business evaluation processing method, characterized in that, include: Obtain N service evaluation information items corresponding to the target service, wherein the N service evaluation information items include M internal evaluation information items obtained from within the target service system and NM external evaluation information items obtained from outside the target service system, wherein N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M. Determining the satisfaction level corresponding to each of the N business evaluation information items and the influence range corresponding to each of the NM external evaluation information items includes: based on the evaluation parameters corresponding to each of the NM external evaluation information items, using a pre-trained influence range classification model to obtain the influence range corresponding to each of the NM external evaluation information items, wherein the evaluation parameters corresponding to each of the NM external evaluation information items include at least: the number of comments, the number of reposts, and the number of likes corresponding to each of the NM external evaluation information items, the influence range classification model is trained based on a DNN model, the DNN model uses a 3-layer fully connected network, and then passes through a softmax classifier to output the final influence range, the influence range is used to indicate the degree of dissemination influence; Based on the satisfaction levels corresponding to the N service evaluation information, the overall satisfaction level of the target service is determined. Based on the impact range corresponding to each of the NM external evaluation information items, the overall impact range of the target business is determined; The evaluation result of the target business is determined based on the overall satisfaction level and the overall influence range, including: determining a first weight value corresponding to the overall satisfaction level and a second weight value corresponding to the overall influence range; and obtaining the evaluation result of the target business based on the overall satisfaction level, the first weight value, the overall influence range, and the second weight value.
2. The method according to claim 1, characterized in that, Determining the satisfaction level corresponding to each of the N service evaluation information items includes: A sentiment classification model is used to perform sentiment recognition on the N business evaluation information pieces respectively, and the sentiment classification results corresponding to the N business evaluation information pieces are obtained respectively; Based on the sentiment classification results corresponding to the N business evaluation information, the satisfaction level corresponding to each of the N business evaluation information is determined.
3. The method according to claim 1, characterized in that, The method further includes: Obtain K sample evaluation information, as well as the evaluation parameters and influence range corresponding to the K sample evaluation information respectively, wherein the evaluation parameters corresponding to the K sample evaluation information respectively include at least: the number of comments, the number of reposts and the number of likes corresponding to the K sample evaluation information respectively; Based on the evaluation parameters and influence ranges corresponding to the K sample evaluation information, the initial deep neural network model is trained to obtain the influence range classification model.
4. The method according to claim 1, characterized in that, The step of determining the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information includes: calculating the average value of the satisfaction levels corresponding to the N service evaluation information; and using the average value of the satisfaction levels corresponding to the N service evaluation information as the overall satisfaction level. The step of determining the comprehensive impact range of the target business based on the impact ranges corresponding to the NM external evaluation information items includes: calculating the average value of the impact ranges corresponding to the NM external evaluation information items, and using the average value of the impact ranges corresponding to the NM external evaluation information items as the comprehensive impact range.
5. The method according to claim 1, characterized in that, The step of determining the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information includes: Obtain the L evaluation tables corresponding to the target service; Feature extraction is performed on each of the L evaluation tables to obtain the satisfaction level corresponding to each of the L evaluation tables; The overall satisfaction level is obtained by calculating the average of the satisfaction levels corresponding to the N business evaluation information and the L evaluation tables.
6. The method according to any one of claims 1 to 5, characterized in that, Obtaining the M internal evaluation information items includes: Obtain M initial evaluation information items corresponding to the target business obtained from within the target business system; The format corresponding to the M initial evaluation information is determined, wherein the format corresponding to the M initial evaluation information is at least one of the following: text format, voice format, and image format; If it is determined that the M initial evaluation information includes evaluation information in the form of voice and / or image, the evaluation information in the form of voice and / or image is processed by text conversion to obtain the M internal evaluation information.
7. A business evaluation processing device, characterized in that, include: The first acquisition module is used to acquire N business evaluation information corresponding to the target business. The N business evaluation information includes M internal evaluation information acquired from within the target business system and NM external evaluation information acquired from outside the target business system. N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and N is greater than M. The first determining module is used to determine the satisfaction level corresponding to each of the N business evaluation information items and to determine the influence range corresponding to each of the NM external evaluation information items. This includes: based on the evaluation parameters corresponding to each of the NM external evaluation information items, using a pre-trained influence range classification model to obtain the influence range corresponding to each of the NM external evaluation information items. The evaluation parameters corresponding to each of the NM external evaluation information items include at least the number of comments, reposts, and likes corresponding to each of the NM external evaluation information items. The influence range classification model is trained based on a DNN model, which uses a 3-layer fully connected network and then passes through a softmax classifier to output the final influence range. The influence range is used to indicate the level of dissemination influence. The second determining module determines the overall satisfaction level of the target service based on the satisfaction levels corresponding to the N service evaluation information. The third determining module determines the overall impact range of the target business based on the impact range corresponding to each of the NM external evaluation information items; The fourth determining module determines the evaluation result of the target service based on the overall satisfaction level and the overall influence range, including: determining a first weight value corresponding to the overall satisfaction level and a second weight value corresponding to the overall influence range; and obtaining the evaluation result of the target service based on the overall satisfaction level, the first weight value, the overall influence range, and the second weight value.
8. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the business evaluation processing method according to any one of claims 1 to 6.