Service system optimization method and device and electronic equipment

Abstract

The invention provides a business system optimization method and device and electronic equipment, and the method comprises the steps: constructing a vocabulary database which at least comprises professional vocabularies, emotion vocabularies and modification vocabularies; a text input by a user is obtained, the vocabulary database is matched with the text input by the user, target professional vocabularies, target emotion vocabularies and target modification vocabularies in the text input by the user are extracted, a service system corresponding to the target professional vocabularies is determined, and the service system is used for handling financial services; obtaining the emotion intensity of the target emotion vocabulary and the modification intensity of the target modification vocabulary, determining the emotion of the user according to the emotion intensity and the modification intensity, and optimizing the service system according to the emotion of the user, so that the optimized service system meets the requirements of the user. Through the method, the user emotion can be accurately determined, so that the service system can be optimized according to the user emotion, and the service system can better meet the requirements of the user.

Description

Technical Field

[0001] The present application relates to the field of language analysis technology, and in particular to a method, device, computer-readable storage medium, and electronic device for optimizing a business system. Background Art

[0002] In customer service, users typically interact by inputting text. The text data they input is often specialized and often carries personal emotions. The main drawbacks of existing language sentiment analysis technologies are:

[0003] (1) The application of sentiment analysis in specialized fields requires domain expertise and experience. However, existing language sentiment analysis technologies often lack such expertise and experience and require more labeled data and specific algorithms for training. This leads to high model training difficulty and data labeling costs, resulting in inaccurate analysis results or failure to fully meet requirements and low generalization ability.

[0004] (2) The results of fine-grained sentiment analysis usually need to be highly interpretable in order to understand how the model makes decisions. However, existing sentiment analysis models often lack sufficient interpretability, making it difficult for users to understand and trust the model's results and making it difficult to adjust the model.

[0005] (3) Sentiment itself is diverse and complex, especially in user suggestion data. Sentiment classification cannot be simply based on “negative” and “positive.” A more multi-layered and fine-grained sentiment analysis approach is required. Existing sentiment analysis techniques may not fully capture these differences, resulting in inaccurate analysis results in some cases. Summary of the Invention

[0006] The main purpose of this application is to provide a business system optimization method, device, computer-readable storage medium and electronic device, so as to at least solve the problem that the existing technology cannot recognize relevant vocabulary in professional fields, and these professional vocabulary may be mistakenly recognized as words representing user emotions, resulting in inaccurate final emotion analysis results for the user.

[0007] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for optimizing a business system is provided, comprising: constructing a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary and modifying vocabulary, the professional vocabulary represents proper nouns in the financial profession, the emotional vocabulary is vocabulary that represents the user's emotions, and the modifying vocabulary is vocabulary that plays a modifying role; obtaining user input text, matching the vocabulary database with the user input text, extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determining the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business; obtaining the emotional intensity of the target emotional vocabulary and the modifying intensity of the target modifying vocabulary, determining the user emotion based on the emotional intensity and the modifying intensity, and optimizing the business system based on the user emotion, so that the optimized business system meets the needs of the user.

[0008] Optionally, constructing a vocabulary database includes: obtaining a professional knowledge base, annotating the professional knowledge base to obtain the professional vocabulary, wherein the professional knowledge base is a database of knowledge including financial expertise; obtaining a general knowledge base, annotating the general knowledge base to obtain the emotional vocabulary and the modifying vocabulary, wherein the general knowledge base is a knowledge database that is common to multiple professions; and generating the vocabulary database from the professional vocabulary, the emotional vocabulary, and the modifying vocabulary.

[0009] Optionally, after obtaining the user input text, the method further includes: obtaining preset punctuation marks, searching the preset punctuation marks in the user input text to obtain target punctuation marks, and deleting the target punctuation marks, wherein the preset punctuation marks include at least one of a comma, a period, and a semicolon; obtaining preset words, searching the preset words in the user input text to obtain target words, and deleting the target words to obtain the preprocessed user input text, wherein the preset words include at least one of a preposition, an auxiliary word, and a function word.

[0010] Optionally, extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary from the user input text includes: calculating the similarity between the professional vocabulary in the vocabulary database and the user input text to obtain a first similarity, and when the first similarity is greater than a similarity threshold, determining the professional vocabulary as the target professional vocabulary; calculating the similarity between the emotional vocabulary in the vocabulary database and the user input text to obtain a second similarity, and when the second similarity is greater than the similarity threshold, determining the emotional vocabulary as the target emotional vocabulary; calculating the similarity between the modifying vocabulary in the vocabulary database and the user input text to obtain a third similarity, and when the third similarity is greater than the similarity threshold, determining the modifying vocabulary as the target modifying vocabulary.

[0011] Optionally, the user emotion is determined based on the emotion intensity and the modification intensity, including: calculating the product of the emotion intensity and the modification intensity to obtain an emotion score; when the emotion score is greater than a preset score, determining that the user emotion is a positive emotion; when the emotion score is less than or equal to the preset score, determining that the user emotion is a negative emotion.

[0012] Optionally, optimizing the business system according to the user emotion includes: when the user emotion is the negative emotion, generating user suggestions based on the user input text, and obtaining a one-to-one mapping relationship between preset user suggestions and optimization measures; determining the optimization measures corresponding to the user suggestions with negative emotions according to the one-to-one mapping relationship between the preset user suggestions and optimization measures, and using the optimization measures to optimize the business system.

[0013] Optionally, after constructing the vocabulary database, the method further includes: recording the construction time of the vocabulary database; obtaining the current time, and calculating the time difference between the current time and the construction time, and updating the vocabulary database when the time difference is greater than a preset time difference.

[0014] According to another aspect of the present application, a business system optimization device is provided, including: a construction unit, used to construct a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary and modifying vocabulary, the professional vocabulary represents the proper nouns of the financial profession, the emotional vocabulary is vocabulary that represents the user's emotions, and the modifying vocabulary is vocabulary that plays a modifying role; a determination unit, used to obtain user input text, match the vocabulary database with the user input text, extract target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determine the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business; an optimization unit, used to obtain the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determine the user emotion according to the emotional intensity and the modification intensity, and optimize the business system according to the user emotion, so that the optimized business system meets the needs of the user.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute any one of the business system optimization methods.

[0016] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include an optimization method for executing any one of the business systems described.

[0017] By applying the technical solution of the present application, a vocabulary database is constructed, the vocabulary database is matched with the user input text, and the professional vocabulary, emotional vocabulary and modifying vocabulary in the user input text are respectively identified to distinguish the professional vocabulary, and finally the corresponding emotional intensity and modifying vocabulary are used to determine the user's emotions, and the business system is optimized to meet the needs of the user. Compared with the prior art, which may identify the user's professional vocabulary as a vocabulary representing the user's emotions, resulting in inaccurate judgment of the user's emotions, the present application can identify and filter the user input text through a pre-constructed vocabulary database including professional vocabulary, etc., so as to accurately filter out the target emotional vocabulary and target modifying vocabulary to accurately determine the user's emotions, thereby being able to optimize the business system according to the user's emotions, so that the business system can better meet the needs of the user. Therefore, it can solve the problem that the language analysis technology in the prior art cannot identify the relevant vocabulary in the professional field, resulting in the problem that the final emotional analysis results of the user are not accurate enough, and achieve the effect of accurately determining the user's emotions, thereby being able to optimize the business system according to the user's emotions, so that the business system can better meet the needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0019] Figure 1 A hardware structure block diagram of a mobile terminal for executing a business system optimization method provided in an embodiment of the present application is shown;

[0020] Figure 2 A schematic diagram illustrating a process flow of a business system optimization method provided by an embodiment of the present application is shown;

[0021] Figure 3 A flowchart of a method for constructing a vocabulary database provided in an embodiment of the present application is shown;

[0022] Figure 4 A schematic diagram of a process flow of a method for obtaining user input text provided by an embodiment of the present application is shown;

[0023] Figure 5 A schematic flow chart of a method for determining similarity between a word and a word in a user input text provided by an embodiment of the present application is shown;

[0024] Figure 6 A schematic diagram of a flow chart of a method for calculating an emotion score provided in an embodiment of the present application is shown;

[0025] Figure 7 A schematic diagram of a method for sentiment word matching and sentiment score calculation provided by an embodiment of the present application is shown;

[0026] Figure 8 A flow chart of a specific method for determining user emotions based on emotion scores provided in an embodiment of the present application is shown;

[0027] Figure 9 A schematic diagram of an optimization device for a business system provided in an embodiment of the present application is shown.

[0028] The above drawings include the following reference numerals:

[0029] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] For ease of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0034] NLP: Natural Language Processing (NLP) is a discipline that studies language issues in the interaction between humans and computers.

[0035] Sentiment analysis: also known as opinion mining, tendency analysis, etc. It is the process of analyzing, processing, summarizing, and reasoning about subjective text with emotional connotations.

[0036] Word segmentation: Break down long texts such as sentences, paragraphs, and articles into data structures based on words to facilitate subsequent processing and analysis.

[0037] Artificial neural network: abstract the human brain's neural network from the perspective of information processing, establish a certain model, and form different networks according to different connection methods.

[0038] Supervised learning: The process of adjusting the parameters of a classifier to achieve the required performance using a set of samples of known categories, also known as supervised training or learning with a teacher.

[0039] Unsupervised learning: Solving various problems in pattern recognition based on training samples with unknown categories (not labeled) is called unsupervised learning.

[0040] Proprietary domain: Proprietary domain refers to expertise or skills in a specific field.

[0041] As described in the background, existing sentiment analysis models often lack sufficient interpretability, making it difficult for users to understand and trust the model's results and making it difficult to adjust the model. This can lead to inaccurate analysis results in some cases. To address the problem that existing language analysis technologies cannot identify relevant vocabulary in professional fields, and these professional vocabulary may be misidentified as vocabulary representing user emotions, resulting in inaccurate analysis results for users' emotions, embodiments of the present application provide a business system optimization method, apparatus, computer-readable storage medium, and electronic device.

[0042] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0043] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG is a hardware structure diagram of a mobile terminal of a business system optimization method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0044] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the optimization method of the business system in the embodiment of the present invention. The processor 102 executes the computer program stored in the memory 104 to execute various functional applications and data processing, thereby implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of such networks may include a wireless network provided by the mobile terminal's communications provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0045] In this embodiment, a method for optimizing a business system is provided. It should be noted that the steps shown in the flowchart of 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 can be executed in an order different from that shown here.

[0046] Figure 2 This is a flow chart of the optimization method of the business system according to the embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0047] Step S201, constructing a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary and modifying vocabulary, professional vocabulary represents proper nouns in the financial profession, emotional vocabulary is vocabulary that expresses the user's emotions, and modifying vocabulary is vocabulary that plays a modifying role.

[0048] Specifically, professional vocabulary refers to technical terms in the financial field, such as "deposit", "asset liability", "intelligent approval" and "risk indicator"; emotional vocabulary refers to words that can express user emotional tendencies (positive or negative), such as "perfect", "stuttering" and "satisfied"; modifying vocabulary includes adverbs of degree, negative words, transition words, fixed sentence patterns and comprehensive modifying component information, such as "very", "slightly", "not", "but" and "although, but".

[0049] Step S202, obtain the user input text, match the vocabulary database with the user input text, extract the target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determine the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business.

[0050] Specifically, the text input by the user is obtained. This text can be the user's suggestions, feedback or comments on the business or system in the financial field. Then, the constructed vocabulary database is matched with the obtained user input text, with the goal of extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the text. The target professional vocabulary refers to the above-mentioned proper nouns in the text related to the financial field, the target emotional vocabulary can express the user's emotional tendency (positive or negative), and the target modifying vocabulary refers to the above-mentioned modifying vocabulary of degree adverbs, negative words, transition words, fixed sentence patterns and comprehensive modifying component information. The business system is a system used to handle various financial businesses such as assets and liabilities, risk indicators, and intelligent approval.

[0051] Step S203, obtaining the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determining the user emotion according to the emotional intensity and the modification intensity, and optimizing the business system according to the user emotion so that the optimized business system meets the user's needs.

[0052] Specifically, the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary are obtained. The emotional intensity can be a preset score. For example, "satisfied" may be preset to a score of 5 points, while "stuck" may be preset to a score of 1 point. The modification intensity depends on the modifying effect of the vocabulary and can also be a preset score. For example, "very" may be preset to a score of 5 points, and "not" may be preset to a score of 2 points. By combining the calculation formula preset by the technicians and bringing the preset scores corresponding to the emotional intensity and modification intensity into the formula for calculation, the user's emotional attitude towards a specific business can be accurately calculated, which provides a direct basis for subsequent business system optimization.

[0053] Through this embodiment,

[0054] By building a vocabulary database, matching the vocabulary database with the user input text, respectively identifying the professional vocabulary, emotional vocabulary and modifying vocabulary in the user input text, so as to distinguish the professional vocabulary, and finally using the corresponding emotional intensity and modifying vocabulary to determine the user's emotions, and optimizing the business system to meet the needs of the user. Compared with the prior art, which may identify the user's professional vocabulary as a vocabulary representing the user's emotions, resulting in inaccurate judgment of the user's emotions, the present application can identify and filter the user input text through a pre-built vocabulary database including professional vocabulary, etc., so as to accurately filter out the target emotional vocabulary and target modifying vocabulary, so as to accurately determine the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user. Therefore, it can solve the problem that the language analysis technology in the prior art cannot identify the relevant vocabulary in the professional field, resulting in the problem that the final emotional analysis results of the user are not accurate enough, and achieve the effect of accurately determining the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user.

[0055] In the specific implementation process, the above-mentioned step S201 can be achieved through the following steps: Step S2011: Acquire a professional knowledge base, annotate the professional knowledge base, and obtain the professional vocabulary, wherein the professional knowledge base is a database of knowledge including financial expertise; Step S2012: Acquire a general knowledge base, annotate the general knowledge base, and obtain the emotional vocabulary and the modifying vocabulary, wherein the general knowledge base is a knowledge database common to multiple professions; Step S2013: Generate the vocabulary database by combining the professional vocabulary, the emotional vocabulary, and the modifying vocabulary. This method constructs a professional and comprehensive vocabulary database by annotating the professional knowledge base and the general knowledge base. This database not only contains professional terms in the financial field, ensuring applicability within the specialized field, but also covers vocabulary that expresses emotions and intensity, making sentiment analysis more accurate and explanatory.

[0056] Specifically, for the acquisition of professional vocabulary, it is necessary to obtain it from the knowledge base of the corresponding technical field. For example, the professional vocabulary of the present embodiment is the vocabulary of the financial professional field. Therefore, the professional knowledge base of the financial field is obtained. Based on the automatic extraction of the proprietary knowledge base, manual annotation and combination of existing dictionary resources, textbooks and other methods, vocabulary annotation is performed to obtain a large number of professional vocabulary in general and financial proprietary fields. In the actual application process, if it is vocabulary in other fields, it is necessary to obtain the professional knowledge base of other corresponding fields. Since emotional vocabulary and modifying vocabulary are universal in most fields, for the acquisition of emotional vocabulary and modifying vocabulary, they can be annotated through the knowledge base that is universal in multiple fields, thereby obtaining emotional vocabulary and modifying vocabulary. Thereby, the above-mentioned vocabulary database contains both professional vocabulary in the financial field and vocabulary and modifying words that can express user emotions.

[0057] In order to simplify the text structure and enable the algorithm to focus more on the recognition and analysis of sentiment words during processing. Unnecessary calculations are reduced, the processing efficiency is improved, the accuracy of the analysis is ensured, and analysis deviations caused by non-semantic elements are avoided. The above step S202 of this application can be implemented through the following steps: Step S204: Obtain preset punctuation marks, search for the preset punctuation marks in the user input text, obtain target punctuation marks, and delete the target punctuation marks, where the preset punctuation marks at least include one of commas, periods, and semicolons; Step S205: Obtain preset words, search for the preset words in the user input text, obtain target words, and delete the target words to obtain the preprocessed user input text, where the preset words at least include one of prepositions, auxiliary words, and function words. According to the above-mentioned constructed vocabulary database, the method performs preprocessing such as word segmentation, stop word removal, and punctuation mark removal on the obtained user input text, so as to obtain usable data.

[0058] Specifically, after obtaining the user input text, the preset punctuation marks in the text are removed to reduce the interference of punctuation marks on subsequent analysis. These punctuation marks are usually used to separate sentences or express pauses in the text, but they do not contain actual effective information for analysis. The preset punctuation marks include, but are not limited to, commas, periods, and semicolons, etc. By searching for and deleting the above punctuation marks, the interference of non-semantic information is avoided. Obtain preset words, and the preset words include, but are not limited to, prepositions, auxiliary words, and function words, such as "de", "shi", "zai", etc. The above preset words do not have a clear emotional color and do not provide additional useful information during the analysis process. By searching for and deleting the preset words, the text can be further streamlined, and the efficiency and accuracy of the analysis can be improved.

[0059] In a specific implementation process, the above step S202 can be implemented by the following steps: step S2021: calculating the similarity between the professional vocabulary in the vocabulary database and the user input text to obtain a first similarity, and when the first similarity is greater than a similarity threshold, determining the professional vocabulary as the target professional vocabulary; step S2022: calculating the similarity between the emotional vocabulary in the vocabulary database and the user input text to obtain a second similarity, and when the second similarity is greater than the similarity threshold, determining the emotional vocabulary as the target emotional vocabulary; step S2023: calculating the similarity between the modifying vocabulary in the vocabulary database and the user input text to obtain a third similarity, and when the third similarity is greater than the similarity threshold, determining the modifying vocabulary as the target modifying vocabulary. By calculating the similarity and setting the threshold, the method can effectively extract highly relevant target professional vocabulary, target emotional vocabulary and target modifying vocabulary from the user input text, thereby improving the accuracy of vocabulary matching and reducing noise in the analysis process, ensuring the pertinence of the analysis and the accuracy of the results.

[0060] Specifically, for each category of target professional vocabulary, target sentiment vocabulary, and target modifier vocabulary in the user-entered text, the similarity between the vocabulary in the aforementioned vocabulary database and the user-entered text is calculated. This similarity calculation can be achieved through techniques such as semantic similarity or string matching, enabling accurate identification of vocabulary in the text that matches the vocabulary database. For example, for professional vocabulary, a first similarity is calculated using the aforementioned method; for sentiment vocabulary, a second similarity is calculated using the aforementioned method; and for modifier vocabulary, a third similarity is calculated using the aforementioned method. After calculating the similarities for these different vocabulary types, a similarity threshold preset by the technician is used as the judgment criterion. If the first similarity exceeds the preset similarity threshold, the professional vocabulary is identified as the target professional vocabulary; if the second similarity exceeds the similarity threshold, the sentiment vocabulary is identified as the target sentiment vocabulary; and if the third similarity exceeds the similarity threshold, the modifier vocabulary is identified as the target modifier vocabulary. The thresholds are set based on financial business scenarios to enhance the targetedness and effectiveness of the analysis, ensuring that the extracted vocabulary is highly relevant and representative.

[0061] In order to clearly define positive and negative emotions, quantify the emotion score, and thus improve the accuracy of decision-making and ensure the correct direction of business system optimization, the above-mentioned step S203 of the present application can be implemented by the following steps: step S2031 calculates the product of the emotion intensity and the modification intensity to obtain the emotion score; step S2032 determines that the user emotion is positive when the emotion score is greater than a preset score; step S2033 determines that the user emotion is negative when the emotion score is less than or equal to the preset score.

[0062] Specifically, the sentiment score is calculated by multiplying the sentiment intensity and the modifier intensity. For example, if the preset sentiment intensity score for the sentiment word "satisfied" is 0.8, and the preset modifier intensity score for the modifier "very" is 1.5, then the sentiment score is 0.8 * 1.5 = 1.2. Based on the characteristics of the financial field and the semantic relationships between sentiment words and modifiers, technical personnel can design weight calculation rules to calculate the sentiment score for the entire text. This ensures the accuracy and rationality of the sentiment score. Technical personnel use a preset score, such as 0.5, as a standard for distinguishing positive from negative emotions. When the sentiment score is greater than the preset score, the user's emotion is judged to be positive; when the sentiment score is less than or equal to the preset score, the user's emotion is judged to be negative. This provides a more objective and quantitative reference for business system optimization, enhancing the practicality and controllability of the optimization method.

[0063] In order to accurately match negative emotions with specific user suggestions, it is possible to accurately identify the problems or deficiencies mentioned in user feedback, thereby providing a clear direction for the formulation of optimization measures. The above-mentioned step S203 of the present application can be implemented by the following steps: Step S2034 generates user suggestions based on the user input text when the user emotion is the negative emotion, and obtains a one-to-one mapping relationship between the preset user suggestions and the optimization measures; Step S2035 determines the optimization measures corresponding to the user suggestions with negative emotions based on the one-to-one mapping relationship between the preset user suggestions and the optimization measures, and uses the optimization measures to optimize the business system.

[0064] Specifically, when the user emotion is determined to be negative, specific user suggestions are generated based on the text content entered by the user. These suggestions are usually direct feedback from users on the functions, performance or experience of the business system, pointing out problems or deficiencies in the system. Obtain a one-to-one mapping relationship between preset user suggestions and optimization measures. Optimization measures for different user suggestions can be preset in a mapping table or database, and each user suggestion corresponds to one or more specific optimization solutions. By comparing the negative emotion user suggestions with the preset mapping relationship, the system can determine the corresponding optimization measures and use the above optimization measures to optimize the business system. This can quickly and effectively solve the problems raised by users and improve the user experience.

[0065] In the specific implementation process, the above-mentioned step S201 of the present application can be implemented through the following steps: S206 records the construction time of the vocabulary database: S207 obtains the current time, and calculates the time difference between the current time and the construction time, and updates the vocabulary database when the time difference is greater than the preset time difference. This method calculates the similarity and sets a threshold. This method records the construction time and judges the time difference to regularly update the above-mentioned vocabulary database, ensuring that the database can promptly reflect the latest business scenarios and language changes. This ensures that the database can promptly reflect the latest business scenarios and language changes, including adding new professional vocabulary, emotional vocabulary or revising the strength information of vocabulary to reflect the latest semantic changes and adapt to new business scenarios. This dynamic update process maintains the timeliness and accuracy of the sentiment analysis method.

[0066] Specifically, after constructing a vocabulary database, the construction time is recorded as a time reference. After a period of time, the time difference between the current time and the construction time is calculated. If the time difference is greater than a preset time difference (e.g., three months), the vocabulary database is updated. This ensures that the vocabulary database can promptly reflect the latest business needs and language trends, improving the accuracy and reliability of analysis.

[0067] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the business system optimization method of the present application will be described in detail below with reference to specific embodiments.

[0068] This embodiment relates to a specific method for constructing a vocabulary database. Figure 3 As shown, the following steps are included:

[0069] Step S1: Acquire proprietary knowledge base and existing dictionary resources (professional knowledge base);

[0070] Step S2: manual labeling and automatic extraction;

[0071] Step S3: Obtain a professional word segmentation dictionary (professional vocabulary), sentiment words (sentimental vocabulary) and intensity information, and modifying components (modifying vocabulary) and intensity information.

[0072] This embodiment relates to another specific processing method after obtaining the user input text, such as Figure 4 As shown, the following steps are included:

[0073] Step S4: combining with the constructed word segmentation dictionary;

[0074] Step S5: The user input text is pre-processed by word segmentation, stop word removal, punctuation removal, etc. (punctuation, prepositions, auxiliary words, function words, etc. are deleted);

[0075] Step S6: Obtain usable data.

[0076] This embodiment relates to another specific method for determining the similarity between a word and a word in a user input text, such as Figure 5 As shown, the following steps are included:

[0077] Step S7: combining business knowledge (professional vocabulary) and sentiment dictionary (sentiment vocabulary);

[0078] Step S8: by semantic similarity calculation, string matching, etc.;

[0079] Step S9: involves emotional vocabulary matching logic (determination of familiarity threshold);

[0080] Step S10: Find the sentiment words, modifying components and intensity information (the sentiment words are determined to be the target sentiment words).

[0081] This embodiment relates to another specific method for calculating emotion scores, such as Figure 6 As shown, the following steps are included:

[0082] Step S11: combining sentiment words, modifying components (modification intensity) and intensity information (sentiment intensity);

[0083] Step S12: involves emotion scoring rules (product of emotion intensity and modification intensity);

[0084] Step S13: Calculate the emotion score (emotion score);

[0085] This embodiment relates to another specific method for sentiment word matching and sentiment score calculation, such as Figure 7 As shown, the following steps are included:

[0086] Step S14: Input example: The function of this system is not very perfect and there are some lags;

[0087] Step S15: loading a real-time dictionary (vocabulary database);

[0088] Step S16: Matching process: This system function is not (modifying component) very perfect (emotional word), there are some lags (emotional word)! (modifying component).

[0089] Step S17: Scoring process: emotional word strength (emotional strength) * modifying component strength (modification strength) + coefficient +: emotional word strength (emotional strength) * modifying component strength (modification strength) + ... = emotional value (emotional score).

[0090] This embodiment relates to another specific method for determining user emotions based on emotion scores, such as Figure 8 As shown, the following steps are included:

[0091] Step S18: according to the emotion score (emotion score);

[0092] Step S19: involving emotion threshold (preset score);

[0093] Step S20: Determine the user's emotional attitude.

[0094] The embodiments of the present application also provide an optimization device for a business system. It should be noted that the optimization device for the business system of the embodiments of the present application can be used to execute the optimization method for the business system provided in the embodiments of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the details that have been described will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0095] The following introduces the optimization device of the business system provided in the embodiment of the present application.

[0096] Figure 9 Schematic diagram of an optimization device for a business system according to an embodiment of the present application. The device includes:

[0097] A construction unit 10 is configured to construct a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary, and modifying vocabulary, wherein the professional vocabulary represents proper nouns in the financial profession, the emotional vocabulary is vocabulary that expresses the user's emotions, and the modifying vocabulary is vocabulary that serves as a modifier;

[0098] Specifically, professional vocabulary refers to proper nouns in the financial field, such as "deposit", "asset liability", "intelligent approval" and "risk indicator"; emotional vocabulary refers to vocabulary that can express the user's emotional tendency (positive or negative), such as "perfect", "stuck" and "satisfied"; modifying vocabulary includes degree adverbs, negative words, transition words, fixed sentence patterns and comprehensive modifying component information, such as "very", "slightly", "not", "but" and "although, but". The determination unit 20 is used to obtain user input text, match the vocabulary database with the user input text, extract target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determine the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business;

[0099] The determining unit 20 is configured to obtain a user input text, match the vocabulary database with the user input text, extract target professional vocabulary, target emotional vocabulary, and target modifying vocabulary from the user input text, and determine a business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business;

[0100] Specifically, the text input by the user is obtained. This text can be the user's suggestions, feedback or comments on the business or system in the financial field. Then, the constructed vocabulary database is matched with the obtained user input text, with the goal of extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the text. The target professional vocabulary refers to the above-mentioned proper nouns in the text related to the financial field, the target emotional vocabulary can express the user's emotional tendency (positive or negative), and the target modifying vocabulary refers to the above-mentioned modifying vocabulary of degree adverbs, negative words, transition words, fixed sentence patterns and comprehensive modifying component information. The business system is a system used to handle various financial businesses such as assets and liabilities, risk indicators, and intelligent approval.

[0101] The optimization unit 30 is configured to obtain the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determine the user emotion according to the emotional intensity and the modification intensity, and optimize the business system according to the user emotion.

[0102] Specifically, the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary are obtained. The emotional intensity can be a preset score. For example, "satisfied" may be preset to a score of 5 points, while "stuck" may be preset to a score of 1 point. The modification intensity depends on the modifying effect of the vocabulary and can also be a preset score. For example, "very" may be preset to a score of 5 points, and "not" may be preset to a score of 2 points. By combining the calculation formula preset by the technicians and bringing the preset scores corresponding to the emotional intensity and modification intensity into the formula for calculation, the user's emotional attitude towards a specific business can be accurately calculated, which provides a direct basis for subsequent business system optimization.

[0103] By building a vocabulary database, matching the vocabulary database with the user input text, respectively identifying the professional vocabulary, emotional vocabulary and modifying vocabulary in the user input text, so as to distinguish the professional vocabulary, and finally using the corresponding emotional intensity and modifying vocabulary to determine the user's emotions, and optimizing the business system to meet the needs of the user. Compared with the prior art, which may identify the user's professional vocabulary as a vocabulary representing the user's emotions, resulting in inaccurate judgment of the user's emotions, the present application can identify and filter the user input text through a pre-built vocabulary database including professional vocabulary, etc., so as to accurately filter out the target emotional vocabulary and target modifying vocabulary, so as to accurately determine the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user. Therefore, it can solve the problem that the language analysis technology in the prior art cannot identify the relevant vocabulary in the professional field, resulting in the problem that the final emotional analysis results of the user are not accurate enough, and achieve the effect of accurately determining the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user. In the specific implementation process, the above-mentioned construction unit includes a first annotation module, a second annotation module and a generation module: the first annotation module is used to obtain a professional knowledge base, annotate the professional knowledge base, and obtain the professional vocabulary, wherein the professional knowledge base is a database of knowledge including financial expertise; the second annotation module is used to obtain a general knowledge base, annotate the general knowledge base, and obtain the emotional vocabulary and the modifying vocabulary, wherein the general knowledge base is a knowledge database common to multiple professions; the generation module is used to generate the vocabulary database from the professional vocabulary, the emotional vocabulary and the modifying vocabulary. The device constructs a professional and comprehensive vocabulary database by annotating the professional knowledge base and the general knowledge base. This database not only contains professional terms in the financial field, ensuring applicability in the specialized field, but also covers vocabulary that expresses emotions and intensity, making sentiment analysis more accurate and explanatory.

[0104] Specifically, we can build a vocabulary of specialized segmentation terms encompassing both general and finance-specific terms based on automatic extraction and manual annotation from proprietary knowledge bases, combined with existing dictionary resources and textbooks. From the general knowledge base (which encompasses general knowledge across multiple fields), we can similarly extract sentiment terms and modifiers through annotation. This ensures that the vocabulary database contains both specialized terms in the financial field and terms and modifiers that can express user sentiment.

[0105] To simplify the text structure and enable the algorithm to focus more on the recognition and analysis of sentiment words during processing. It reduces unnecessary calculations, improves processing efficiency, ensures the accuracy of analysis, and avoids analysis deviations caused by non-semantic elements. The above-mentioned device of this application further includes a first deletion unit and a second deletion unit: The first deletion unit is used to obtain preset punctuation marks, search for the preset punctuation marks in the user input text to obtain target punctuation marks, and delete the target punctuation marks. Among them, the preset punctuation marks at least include one of commas, periods, and semicolons; The second deletion unit is used to obtain preset words, search for the preset words in the user input text to obtain target words, and delete the target words to obtain the preprocessed user input text. Among them, the preset words at least include one of prepositions, auxiliary words, and function words. The device preprocesses the obtained user input text, such as word segmentation, stop word removal, and punctuation mark removal, according to the constructed above-mentioned vocabulary database, so as to obtain usable data.

[0106] Specifically, after obtaining the user input text, the preset punctuation marks in the text are removed to reduce the interference of punctuation marks on subsequent analysis. These punctuation marks are usually used to separate sentences or express pauses in the text, but they do not contain actual valid information for analysis. The preset punctuation marks include but are not limited to commas, periods, and semicolons, etc. By searching for and deleting the above punctuation marks, the interference of non-semantic information is avoided. Preset words are obtained. The preset words include but are not limited to prepositions, auxiliary words, and function words, such as "de", "shi", "zai", etc. The above preset words do not have a clear emotional color and do not provide additional useful information during the analysis process. By searching for and deleting the preset words, the text can be further streamlined, and the efficiency and accuracy of analysis can be improved.

[0107] In a specific implementation, the determination unit includes a first determination module, a second determination module, and a third determination module: the first determination module is configured to calculate the similarity between the professional vocabulary in the vocabulary database and the user input text, obtaining a first similarity. If the first similarity is greater than a similarity threshold, the professional vocabulary is determined as the target professional vocabulary; the second determination module is configured to calculate the similarity between the emotional vocabulary in the vocabulary database and the user input text, obtaining a second similarity. If the second similarity is greater than the similarity threshold, the emotional vocabulary is determined as the target emotional vocabulary; and the third determination module is configured to calculate the similarity between the modifier vocabulary in the vocabulary database and the user input text, obtaining a third similarity. If the third similarity is greater than the similarity threshold, the modifier vocabulary is determined as the target modifier vocabulary. By calculating similarities and setting thresholds, the device can effectively extract target professional vocabulary, emotional vocabulary, and modifier vocabulary that are highly relevant to the analysis target from the user input text. This improves the accuracy of vocabulary matching while reducing noise in the analysis process, ensuring the pertinence of the analysis and the accuracy of the results. The reasonably set similarity threshold is determined based on a large amount of experimental data and the characteristics of financial texts. While maintaining a high matching rate, it effectively avoids false positives and provides a more reliable and objective basis for subsequent business system optimization.

[0108] Specifically, for each category of target professional vocabulary, target sentiment vocabulary, and target modifier vocabulary in the user input text, the similarity between the vocabulary in the above-mentioned vocabulary database and the user input text is calculated. This similarity calculation can be achieved through technical means such as semantic similarity or string matching, which can accurately identify vocabulary in the text that matches the vocabulary database. For example, for professional vocabulary, the above-mentioned means calculates a first similarity; for sentiment vocabulary, the above-mentioned means calculates a second similarity; and for modifier vocabulary, the above-mentioned means calculates a third similarity. After calculating the similarities of these different vocabulary, a similarity threshold preset by the technician is used as the judgment criterion. If the first similarity exceeds the preset similarity threshold, the professional vocabulary is determined as the target professional vocabulary; if the second similarity exceeds the similarity threshold, the sentiment vocabulary is determined as the target sentiment vocabulary; and if the third similarity exceeds the similarity threshold, the modifier vocabulary is determined as the target modifier vocabulary. The threshold setting is based on financial business scenarios to improve the targetedness and effectiveness of the analysis, ensuring that the extracted vocabulary is highly relevant and representative.

[0109] In order to clearly define positive and negative emotions, quantify the emotion score, and thus improve the accuracy of decision-making and ensure the correct direction of business system optimization, the above-mentioned optimization unit includes a calculation module, a fourth determination module, and a fifth determination module. The calculation module is used to calculate the product of the emotion intensity and the modification intensity to obtain the emotion score; the fourth determination module is used to determine that the user emotion is positive when the emotion score is greater than a preset score; and the fifth determination module is used to determine that the user emotion is negative when the emotion score is less than or equal to the preset score.

[0110] Specifically, the sentiment score is obtained by multiplying the sentiment intensity and the modifier intensity. For example, if the preset sentiment intensity score of the sentiment word "satisfied" is 0.8, and the preset modifier intensity score of the modifier "very" is 1.5, then the sentiment score is 0.8*1.5=1.2. Technicians can design weight calculation rules based on the characteristics of the financial field, semantic relationships such as sentiment words and modifier words, and then calculate the sentiment score of the entire text. This ensures the accuracy and rationality of the sentiment score. Technicians use preset scores, such as 0.5, as a standard for distinguishing between positive and negative emotions. When the sentiment score is greater than the preset score, the user's emotion is judged to be positive; when the sentiment score is less than or equal to the preset score, the user's emotion is judged to be negative. This provides a more objective and quantitative reference for business system optimization and enhances the practicality and controllability of the optimization device.

[0111] In order to accurately match negative emotions with specific user suggestions, it is possible to accurately identify the problems or deficiencies mentioned in user feedback, thereby providing a clear direction for the formulation of optimization measures. The above-mentioned optimization unit also includes an acquisition module and an optimization module. The acquisition module is used to generate user suggestions based on the user input text when the user emotion is negative, and obtain a one-to-one mapping relationship between preset user suggestions and optimization measures; the optimization module is used to determine the optimization measures corresponding to the user suggestions with negative emotions based on the one-to-one mapping relationship between the preset user suggestions and optimization measures, and use the optimization measures to optimize the business system.

[0112] Specifically, when the user emotion is determined to be negative, specific user suggestions are generated based on the text content entered by the user. These suggestions are usually direct feedback from users on the functions, performance or experience of the business system, pointing out problems or deficiencies in the system. Obtain a one-to-one mapping relationship between preset user suggestions and optimization measures. Optimization measures for different user suggestions can be preset in a mapping table or database, and each user suggestion corresponds to one or more specific optimization solutions. By comparing the negative emotion user suggestions with the preset mapping relationship, the system can determine the corresponding optimization measures and use the above optimization measures to optimize the business system. This can quickly and effectively solve the problems raised by users and improve the user experience.

[0113] During the specific implementation process, the above-mentioned device of the present application also includes a recording unit and an updating unit. The recording unit is used to record the construction time of the vocabulary database; the updating unit is used to obtain the current time and calculate the time difference between the current time and the construction time. When the time difference is greater than the preset time difference, the vocabulary database is updated. The device calculates the similarity and sets the threshold. The device records the construction time and judges the time difference to regularly update the above-mentioned vocabulary database, ensuring that the database can promptly reflect the latest business scenarios and language changes. This ensures that the database can promptly reflect the latest business scenarios and language changes, including adding new professional vocabulary, emotional vocabulary or revising the strength information of vocabulary to reflect the latest semantic changes and adapt to new business scenarios. This dynamic update process maintains the timeliness and accuracy of the sentiment analysis device.

[0114] Specifically, after constructing a vocabulary database, the construction time is recorded as a time reference. After a period of time, the time difference between the current time and the construction time is calculated. If the time difference is greater than a preset time difference (e.g., three months), the vocabulary database is updated. This ensures that the vocabulary database can promptly reflect the latest business needs and language trends, improving the accuracy and reliability of analysis.

[0115] The business system optimization device includes a processor and memory. The aforementioned units are stored as program units in the memory, and the processor executes the program units stored in the memory to implement the corresponding functions. The aforementioned modules are all located in the same processor; alternatively, the aforementioned modules can be located in different processors in any combination.

[0116] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and kernel parameters can be adjusted to accurately determine user emotions. This allows the business system to be optimized based on user emotions, making it more responsive to user needs.

[0117] The memory may include non-permanent memory in a computer-readable medium, 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.

[0118] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program runs, the device where the computer-readable storage medium is located is controlled to execute the optimization device of the business system.

[0119] Specifically, the optimization device of the business system includes:

[0120] Step S201, constructing a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary and modifying vocabulary, professional vocabulary represents proper nouns in the financial profession, emotional vocabulary is vocabulary that expresses the user's emotions, and modifying vocabulary is vocabulary that plays a modifying role.

[0121] Specifically, a vocabulary database is constructed, which contains at least professional vocabulary, sentiment vocabulary, and modifier vocabulary. Professional vocabulary refers to proper nouns in the financial field, such as "deposit," "asset liability," "intelligent approval," and "risk indicator." Sentiment vocabulary refers to words that can express user emotional tendencies (positive or negative), such as "perfect," "stuck," and "satisfied." Modifier vocabulary includes adverbs of degree, negative words, transition words, fixed sentence patterns, and comprehensive information on modifier components, such as "very," "slightly," "not," "but," and "although, but."

[0122] Step S202, obtain the user input text, match the vocabulary database with the user input text, extract the target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determine the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business.

[0123] Specifically, the text input by the user is obtained. This text can be the user's suggestions, feedback or comments on the business or system in the financial field. Then, the constructed vocabulary database is matched with the obtained user input text, with the goal of extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the text. The target professional vocabulary refers to the above-mentioned proper nouns in the text related to the financial field, the target emotional vocabulary can express the user's emotional tendency (positive or negative), and the target modifying vocabulary refers to the above-mentioned modifying vocabulary of degree adverbs, negative words, transition words, fixed sentence patterns and comprehensive modifying component information. The business system is a system used to handle various financial businesses such as assets and liabilities, risk indicators, and intelligent approval.

[0124] Step S203, obtaining the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determining the user emotion according to the emotional intensity and the modification intensity, and optimizing the business system according to the user emotion so that the optimized business system meets the user's needs.

[0125] Specifically, the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary are obtained. The emotional intensity can be a preset score. For example, "satisfied" may be preset to a score of 5 points, while "stuck" may be preset to a score of 1 point. The modification intensity depends on the modifying effect of the vocabulary and can also be a preset score. For example, "very" may be preset to a score of 5 points, and "not" may be preset to a score of 2 points. By combining the calculation formula preset by the technicians and bringing the preset scores corresponding to the emotional intensity and modification intensity into the formula for calculation, the user's emotional attitude towards a specific business can be accurately calculated, which provides a direct basis for subsequent business system optimization.

[0126] An embodiment of the present invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are performed:

[0127] Step S201, constructing a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary and modifying vocabulary, professional vocabulary represents proper nouns in the financial profession, emotional vocabulary is vocabulary that expresses the user's emotions, and modifying vocabulary is vocabulary that plays a modifying role.

[0128] Specifically, a vocabulary database is constructed, which contains at least professional vocabulary, sentiment vocabulary, and modifier vocabulary. Professional vocabulary refers to proper nouns in the financial field, such as "deposit," "asset liability," "intelligent approval," and "risk indicator." Sentiment vocabulary refers to words that can express user emotional tendencies (positive or negative), such as "perfect," "stuck," and "satisfied." Modifier vocabulary includes adverbs of degree, negative words, transition words, fixed sentence patterns, and comprehensive information on modifier components, such as "very," "slightly," "not," "but," and "although, but."

[0129] Step S202, obtain the user input text, match the vocabulary database with the user input text, extract the target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the user input text, and determine the business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business.

[0130] Specifically, the text input by the user is obtained. This text can be the user's suggestions, feedback or comments on the business or system in the financial field. Then, the constructed vocabulary database is matched with the obtained user input text, with the goal of extracting target professional vocabulary, target emotional vocabulary and target modifying vocabulary in the text. The target professional vocabulary refers to the above-mentioned proper nouns in the text related to the financial field, the target emotional vocabulary can express the user's emotional tendency (positive or negative), and the target modifying vocabulary refers to the above-mentioned modifying vocabulary of degree adverbs, negative words, transition words, fixed sentence patterns and comprehensive modifying component information. The business system is a system used to handle various financial businesses such as assets and liabilities, risk indicators, and intelligent approval.

[0131] Step S203, obtaining the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determining the user emotion according to the emotional intensity and the modification intensity, and optimizing the business system according to the user emotion so that the optimized business system meets the user's needs.

[0132] Specifically, the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary are obtained. The emotional intensity can be a preset score. For example, "satisfied" may be preset to a score of 5 points, while "stuck" may be preset to a score of 1 point. The modification intensity depends on the modifying effect of the vocabulary and can also be a preset score. For example, "very" may be preset to a score of 5 points, and "not" may be preset to a score of 2 points. By combining the calculation formula preset by the technicians and bringing the preset scores corresponding to the emotional intensity and modification intensity into the formula for calculation, the user's emotional attitude towards a specific business can be accurately calculated, which provides a direct basis for subsequent business system optimization.

[0133] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0134] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0135] Those skilled in the art will appreciate that the embodiments of the present application can be provided as devices, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0136] The present application is described with reference to the flowcharts and / or block diagrams of the apparatus, device (system), and computer program product according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0139] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0140] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0141] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be used to store information by any device or technology. The information can be computer-readable instructions, data structures, program modules, 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, commodity, or device that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, apparatus, commodity, or device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, apparatus, commodity, or device that includes the element.

[0143] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0144] 1) The optimization method of the business system of the present application, by constructing a vocabulary database, matching the vocabulary database with the user input text, respectively identifying the professional vocabulary, emotional vocabulary and modifying vocabulary in the user input text, so as to distinguish the professional vocabulary, and finally using the corresponding emotional intensity and modifying vocabulary to determine the user's emotions, and optimizing the business system to meet the needs of the user. Compared with the prior art, which may identify the user's professional vocabulary as a vocabulary representing the user's emotions, resulting in inaccurate judgment of the user's emotions, the present application can identify and filter the user input text through a pre-constructed vocabulary database including professional vocabulary, etc., so as to accurately filter out the target emotional vocabulary and target modifying vocabulary, so as to accurately determine the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user. Therefore, it can solve the problem that the language analysis technology in the prior art cannot identify the relevant vocabulary in the professional field, resulting in the final inaccurate analysis results of the user's emotions, and achieve the effect of accurately determining the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user.

[0145] 2) The optimization device of the business system of the present application, by building a vocabulary database, matches the vocabulary database with the user input text, and respectively identifies the professional vocabulary, emotional vocabulary and modifying vocabulary in the user input text to distinguish the professional vocabulary, and finally uses the corresponding emotional intensity and modifying vocabulary to determine the user's emotions, and optimizes the business system to meet the needs of the user. Compared with the prior art, which may identify the user's professional vocabulary as a vocabulary representing the user's emotions, resulting in inaccurate judgment of the user's emotions, the present application can identify and filter the user input text through a pre-built vocabulary database including professional vocabulary, etc., so as to accurately filter out the target emotional vocabulary and target modifying vocabulary to accurately determine the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user. Therefore, it can solve the problem that the language analysis technology in the prior art cannot identify the relevant vocabulary in the professional field, resulting in the final inaccurate analysis results of the user's emotions, and achieve the effect of accurately determining the user's emotions, thereby optimizing the business system according to the user's emotions, so that the business system can better meet the needs of the user.

[0146] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for optimizing a business system, characterized in that: include: Constructing a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary, and modifying vocabulary, wherein the professional vocabulary represents proper nouns in the financial profession, the emotional vocabulary is vocabulary that expresses the user's emotions, and the modifying vocabulary is vocabulary that has a modifying effect; Obtaining user input text, matching the vocabulary database with the user input text, extracting target professional vocabulary, target emotional vocabulary, and target modifying vocabulary from the user input text, and determining a business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business; The emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary are obtained, the user emotion is determined according to the emotional intensity and the modification intensity, and the business system is optimized according to the user emotion so that the optimized business system meets the needs of the user.

2. The business system optimization method according to claim 1, characterized in that: Build a vocabulary database, including: Acquiring a professional knowledge base, annotating the professional knowledge base, and obtaining the professional vocabulary, wherein the professional knowledge base is a database including financial professional knowledge; Acquire a general knowledge base, annotate the general knowledge base, and obtain the sentiment vocabulary and the modifying vocabulary, wherein the general knowledge base is a knowledge database common to multiple professions; The professional vocabulary, the emotional vocabulary and the modifying vocabulary are used to generate the vocabulary database.

3. The business system optimization method according to claim 1, characterized in that: After obtaining the user input text, the method further includes: Obtaining a preset punctuation mark, searching the preset punctuation mark in the user input text to obtain a target punctuation mark, and deleting the target punctuation mark, wherein the preset punctuation mark includes at least one of a comma, a period, and a semicolon; Acquire a preset word, search the preset word in the user input text to obtain a target word, and delete the target word to obtain the preprocessed user input text, wherein the preset word includes at least one of a preposition, an auxiliary word, and a function word.

4. The business system optimization method according to claim 1, characterized in that: Extracting target professional vocabulary, target emotional vocabulary, and target modifying vocabulary from the user input text includes: Calculating the similarity between the professional vocabulary in the vocabulary database and the user input text to obtain a first similarity, and determining the professional vocabulary as the target professional vocabulary when the first similarity is greater than a similarity threshold; Calculating the similarity between the emotion vocabulary in the vocabulary database and the user input text to obtain a second similarity, and determining the emotion vocabulary as the target emotion vocabulary when the second similarity is greater than the similarity threshold; The similarity between the modifying word in the vocabulary database and the user input text is calculated to obtain a third similarity. If the third similarity is greater than the similarity threshold, the modifying word is determined as the target modifying word.

5. The business system optimization method according to claim 1, characterized in that: Determining the user's emotion according to the emotion intensity and the modification intensity includes: Calculating the product of the emotion intensity and the modification intensity to obtain an emotion score; When the emotion score is greater than a preset score, determining that the user emotion is a positive emotion; When the emotion score is less than or equal to the preset score, it is determined that the user emotion is a negative emotion.

6. The business system optimization method according to claim 5, characterized in that: Optimizing the business system according to the user emotion includes: In a case where the user emotion is the negative emotion, generating user suggestions according to the user input text, and obtaining a one-to-one mapping relationship between preset user suggestions and optimization measures; The optimization measure corresponding to the user suggestion with negative emotions is determined according to the one-to-one mapping relationship between the preset user suggestions and the optimization measures, and the business system is optimized using the optimization measure.

7. The business system optimization method according to claim 1, characterized in that: After building the vocabulary database, the method further includes: Recording the construction time of the vocabulary database; The current time is obtained, and a time difference between the current time and the construction time is calculated. If the time difference is greater than a preset time difference, the vocabulary database is updated.

8. An optimization device for a business system, characterized in that: include: A construction unit, configured to construct a vocabulary database, wherein the vocabulary database includes at least professional vocabulary, emotional vocabulary, and modifying vocabulary, wherein the professional vocabulary represents proper nouns in the financial profession, the emotional vocabulary is vocabulary that expresses the user's emotions, and the modifying vocabulary is vocabulary that has a modifying effect; a determination unit, configured to obtain a user input text, match the vocabulary database with the user input text, extract target professional vocabulary, target emotional vocabulary, and target modifying vocabulary from the user input text, and determine a business system corresponding to the target professional vocabulary, wherein the business system is used to handle financial business; The optimization unit is used to obtain the emotional intensity of the target emotional vocabulary and the modification intensity of the target modifying vocabulary, determine the user emotion according to the emotional intensity and the modification intensity, and optimize the business system according to the user emotion so that the optimized business system meets the needs of the user.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the business system optimization method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include an optimization method for executing the business system described in any one of claims 1 to 7.

Images