Service data pushing method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of data processing, is applied to a service information introduction scene, and relates to a service data pushing method and device, equipment and a storage medium thereof. Performing semantic analysis, and extracting key data; and carrying out iterative transformation optimization on the service push data according to the key data to obtain the transformed and optimized service push data, and sending the current service push data to a target receiving end through evaluation until the current service push data meets a preset push requirement. The service data pushing method is applied to a scene that financial service promotion personnel carry out product promotion or service introduction to target clients, service pushing data can be modified and optimized for many times before actual pushing, service quality control can be carried out on the financial service promotion personnel, and the service quality of the financial service promotion personnel can be improved. And the service push data obtained by the client is more diversified.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and is applied to a service information introduction scenario, and in particular to a service data push method, device, equipment, and storage medium thereof. Background Art

[0002] At present, the business service data of customer service personnel is pushed in a commonly used way by providing professional speech texts, and then directly replacing the conversation texts between customer service personnel and customers with professional speech texts to achieve the business service data push of customer service personnel.

[0003] However, this service data push method cannot evaluate the customer service level of customer service personnel based on the conversation text between them and customers, which makes it impossible for the management to better control the service quality of different customer service personnel. Moreover, the direct replacement of professional speech text results in a relatively simple and mechanical output, which makes it impossible to push diversified service data to customers. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a service data push method, device, equipment and storage medium thereof to solve the problem in the prior art in the service data push scenario that the management party is unable to better control the business quality of different customer service personnel and is unable to push diversified service data to customers.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a method for pushing service data, which adopts the following technical solution:

[0006] A service data push method comprises the following steps:

[0007] Step 201, obtaining service push data of the target server;

[0008] Step 202, performing semantic analysis on the service push data to extract key data;

[0009] Step 203, determining whether the key data contains illegal key data;

[0010] Step 204: if the key data does not contain any illegal key data, the service push data is input into a preset service evaluation model;

[0011] Step 205: if the key data includes illegal key data, the service push data is transformed and optimized to obtain the transformed and optimized service push data, and the service push data is input into the service evaluation model;

[0012] Step 206, evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model;

[0013] Step 207: if the current service push data does not meet the push requirement, then iteratively execute steps 205 to 206 to perform transformation optimization and push evaluation on the latest service push data until the current service push data meets the push requirement, and then stop iterative execution;

[0014] Step 208: If the current service push data meets the push requirement, the current service push data is sent to the target receiving end.

[0015] Furthermore, before executing the step of performing semantic analysis on the service push data to extract key data, the method further includes:

[0016] Constructing a key data dictionary based on the prophet's experience, wherein the key data dictionary includes non-compliant key data, colloquial key data, and standardized key data;

[0017] Deploy the key data dictionary to the pre-trained semantic analysis model;

[0018] The step of performing semantic analysis on the service push data to extract key data specifically includes:

[0019] Inputting the service push data into the semantic analysis model, wherein the semantic analysis model is a semantic analysis model based on natural language processing technology;

[0020] Performing semantic analysis on the service push data through the semantic analysis model, and screening out all key data contained in the service push data according to the semantic analysis result;

[0021] After executing the step of performing semantic analysis on the service push data to extract key data, the method further includes:

[0022] Based on the key data dictionary, all key data in the service push data are classified and processed to obtain key data classification results.

[0023] Furthermore, before executing the step of transforming and optimizing the service push data to obtain the transformed and optimized service push data if the key data includes the illegal key data, the method further includes:

[0024] Obtain a preset speech text quality inspection data set, wherein each quality inspection data in the speech text quality inspection data set is composed of a key value and a value value in a pair, the key value represents the detection hit word, and the value value represents the transformation optimization word;

[0025] Generate a gradient optimization strategy based on the key value and value of each quality inspection data;

[0026] The gradient optimization strategy is deployed as optimization knowledge into a preset automatic optimization model, wherein the automatic optimization model includes a text automatic optimization model based on LLM.

[0027] Furthermore, the step of generating a gradient optimization strategy according to the key value and value of each quality inspection data specifically includes:

[0028] Sequentially obtain different quality inspection data from the speech text quality inspection data set as current quality inspection data;

[0029] Semantically encode the key value and the value in the current quality inspection data to obtain the semantic information encoding results corresponding to the key value and the value of all quality inspection data;

[0030] According to the semantic information encoding results corresponding to the key values ​​and value values ​​of all quality inspection data, the semantic encoding distance between the value value of the current quality inspection data and the key values ​​of other quality inspection data is calculated;

[0031] According to the relationship from small to large semantic coding distance, all quality inspection data are gradient arranged to obtain the gradient arrangement result;

[0032] The gradient optimization strategy is generated according to the gradient arrangement result, wherein the gradient optimization strategy includes: if the transformation optimization word obtained after the current optimization still does not meet the push requirements, then the next quality inspection data of the quality inspection data corresponding to the transformation optimization word is screened out from the gradient arrangement result; and the transformation optimization word of the next quality inspection data is obtained as the transformation optimization word again.

[0033] Furthermore, if the key data includes illegal key data, the service push data is transformed and optimized to obtain the transformed and optimized service push data, specifically including:

[0034] Inputting the service push data into the automatic optimization model;

[0035] Identifying illegal key data in the service push data through the key data classification result;

[0036] According to the gradient optimization strategy, all the key data of violations are iteratively transformed and optimized respectively;

[0037] This round of iterative transformation and optimization will be stopped until all illegal key data are converted into at least colloquial key data;

[0038] Replacing the transformed key data corresponding to all the illegal key data with the corresponding positions in the service push data one by one, and generating transformed and optimized service push data;

[0039] The step of transforming and optimizing the service push data to obtain the transformed and optimized service push data also includes:

[0040] inputting the service push data that does not meet the push requirement into the automatic optimization model;

[0041] identifying the colloquial key data in the service push data through the key data classification result;

[0042] According to the gradient optimization strategy, all the key oral data are iteratively transformed and optimized respectively;

[0043] This round of iterative transformation and optimization will be stopped until all colloquial key data are converted to at least standardized key data;

[0044] The transformed key data corresponding to all the colloquial key data are replaced one by one into the corresponding positions in the service push data to generate the transformed and optimized service push data.

[0045] Furthermore, before executing the step of evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model, the method further includes:

[0046] All key values ​​and all value values ​​in the speech text quality inspection data set are set as service score fields and deployed into the service evaluation model;

[0047] According to the gradient arrangement result, a service score is set for each service scoring field;

[0048] The step of evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model specifically includes:

[0049] Identify all service rating fields contained in the current service push data;

[0050] The service scores corresponding to all the service scoring fields are summed and averaged to obtain the service score mean corresponding to the current service push data;

[0051] Determining whether the service score average exceeds a preset score threshold;

[0052] If the service score average does not exceed the score threshold, the current service push data does not meet the push requirement;

[0053] If the service score average exceeds the score threshold, the current service push data meets the push requirement.

[0054] Further, after executing the step of sending the current service push data to the target receiving end, the method further includes:

[0055] According to the preset transformation and optimization log, count the total number of times the current service push data has been transformed and optimized;

[0056] Determine whether the total number of times the current service push data is modified and optimized exceeds a preset number threshold;

[0057] If the total number of times the current service push data is transformed and optimized exceeds the threshold, a feedback indicating that the number of transformation and optimization times is too many is sent to the target management end;

[0058] If the total number of times the current service push data is modified and optimized does not exceed the number threshold, an incentive feedback is sent to the target server.

[0059] In order to solve the above technical problems, the embodiment of the present application also provides a service data push device, which adopts the following technical solution:

[0060] A service data pushing device, comprising:

[0061] The service push data acquisition module is used to obtain the service push data of the target server;

[0062] A key data extraction module, used to perform semantic analysis on the service push data and extract key data;

[0063] A violation judgment module, used to judge whether the key data contains violation key data;

[0064] The first branch module of the evaluation process is used for inputting the service push data into a preset service evaluation model if the key data does not contain the key data of violation;

[0065] The second branch module of evaluation processing is used for transforming and optimizing the service push data if the key data contains the key data of violation, obtaining the transformed and optimized service push data, and inputting the service push data into the service evaluation model;

[0066] A push satisfaction judgment module is used to evaluate whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model;

[0067] An iterative transformation and optimization module, for iteratively performing transformation and optimization and push evaluation on the latest service push data if the current service push data does not meet the push requirements, until the current service push data meets the push requirements, and then stopping the iterative execution;

[0068] The service push data sending module is used to send the current service push data to the target receiving end if the current service push data meets the push requirement.

[0069] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0070] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned service data pushing method when executing the computer-readable instructions.

[0071] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0072] A computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service data pushing method as described above are implemented.

[0073] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0074] The service data push method described in the embodiment of the present application obtains service push data; performs semantic analysis to extract key data; iteratively transforms and optimizes the service push data according to the key data to obtain the optimized service push data, and through evaluation, sends the current service push data to the target receiving end until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0076] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0077] Figure 2 is a flow chart of an embodiment of a service data push method according to the present application;

[0078] Figure 3 It is a flowchart of a specific embodiment of the method for generating and deploying a gradient optimization strategy in the service data push method described in this application;

[0079] Figure 4 yes Figure 3 A flowchart of a specific embodiment of step 302 is shown;

[0080] Figure 5 yes Figure 2 A flowchart of a specific embodiment of step 206 is shown;

[0081] Figure 6 is a structural diagram of an embodiment of a service data push device according to the present application;

[0082] Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0083] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0084] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0085] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0086] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0087] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0088] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0089] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0090] It should be noted that the service data pushing method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the service data pushing device is generally arranged in the terminal device.

[0091] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0092] Continue to refer Figure 2 , shows a flow chart of an embodiment of a service data push method according to the present application. The service data push method comprises the following steps:

[0093] Step 201, obtaining service push data of the target server.

[0094] In this embodiment, the target service end includes a real-time conversation input end of a financial services salesperson; the service push data includes conversation data when the financial services salesperson communicates with the push target, and the push target refers to a customer who is having a conversation with the financial services salesperson.

[0095] By obtaining the service push data of the target service end, that is, obtaining the product promotion data or service introduction data input by the financial business salesperson at the real-time dialogue input end, the service data push method of the present application can be used to transform and optimize the service push data before the actual push, which can not only control the business quality of the financial business salesperson, but also make the service push data obtained by the customer more diversified.

[0096] Step 202: perform semantic analysis on the service push data to extract key data.

[0097] In this embodiment, the key data includes preset business violation words, false propaganda words, improper sales words, impolite words, business keywords, business high-frequency words, business summary information, business quotation information, business name information and business behavior verbs, etc.; the business behavior verbs and business name information in the service push data can also jointly constitute the push intention as the key data. Specifically, the push intention identification method includes: screening out business behavior verbs and business name information from the key data; identifying the push intention by splicing the business behavior verbs and the business name information, wherein the business behavior verbs are, for example, purchase, renewal, and claim settlement, and the business name information is, for example, life insurance type name, health insurance type name, auto insurance type name, etc. The push intention is also included in the key data, so that the service push data can be transformed and optimized through the key data, and the service push data can also be transformed and optimized based on the push intention, so that the transformation and optimization combines multi-dimensional key data, and the transformation and optimization results are closer to standardization.

[0098] Specifically, the key data include violation key data, colloquial key data and standardized key data in types, wherein the violation key data generally refers to the above-mentioned business violation words, false propaganda words, inappropriate sales words, impolite words, etc., the colloquial key data generally refers to non-professional words in the service push data that are semantically consistent with the professional terms in the preset speech text but inconsistent with the expression text, and the standardized key data generally refers to words in the service push data that are consistent with the professional terms in the preset speech text.

[0099] In this embodiment, before executing the step of performing semantic analysis on the service push data and extracting key data, the method also includes: constructing a key data dictionary based on prophetic experience, wherein the key data dictionary includes violation key data, colloquial key data and standardized key data; and deploying the key data dictionary to a pre-trained semantic analysis model.

[0100] Specifically, the key data dictionary constructed according to the prophet's experience can mark out the illegal key data, colloquial key data and standardized key data according to the historical service recommendation data of multiple financial business salesmen, and then construct the key data dictionary according to the marked information.

[0101] In this embodiment, the step of performing semantic analysis on the service push data to extract key data specifically includes: inputting the service push data into the semantic analysis model, wherein the semantic analysis model is a semantic analysis model based on natural language processing technology; performing semantic analysis on the service push data through the semantic analysis model, and filtering out all key data contained in the service push data according to the semantic analysis result, specifically, filtering out all key data contained in the service push data according to the key data dictionary in the semantic analysis model.

[0102] In this embodiment, after executing the step of performing semantic analysis on the service push data and extracting key data, the method further includes: classifying all key data in the service push data based on the key data dictionary to obtain key data classification results.

[0103] Specifically, the classification process is mainly aimed at classifying the illegal key data, colloquial key data and standardized key data in the service push data.

[0104] By performing semantic analysis on the service push data, key data is extracted to facilitate subsequent transformation and optimization processing of different types of key data, making the transformation and optimization processing more scientific, reasonable and intelligent.

[0105] Step 203, determining whether the key data contains illegal key data.

[0106] Step 204: If the key data does not include any violation key data, the service push data is input into a preset service evaluation model.

[0107] Step 205: If the key data includes illegal key data, the service push data is transformed and optimized to obtain the transformed and optimized service push data, and the service push data is input into the service evaluation model.

[0108] In this embodiment, before executing the step of transforming and optimizing the service push data if the key data contains illegal key data to obtain the transformed and optimized service push data, the method also includes a gradient optimization strategy generation and deployment method.

[0109] Continue to refer Figure 3 , Figure 3 It is a flowchart of a specific embodiment of the method for generating and deploying a gradient optimization strategy in the service data push method described in this application, including:

[0110] Step 301, obtaining a preset speech text quality inspection data set, wherein each quality inspection data in the speech text quality inspection data set is composed of a key value and a value value in a pair, the key value represents the detection hit word, and the value value represents the transformation optimization word;

[0111] Specifically, in an actual quality inspection scenario, the key data is the data to be quality inspected. The key data is input into the automatic optimization model, and the detection hit words corresponding to the key data are screened out through query matching. Then, the transformation optimization words corresponding to the detection hit words are output to complete a transformation optimization.

[0112] Step 302, generating a gradient optimization strategy according to the key value and value of each quality inspection data;

[0113] Continue to refer Figure 4 , Figure 4 yes Figure 3 The flowchart of a specific embodiment of step 302 shown includes:

[0114] Step 401, sequentially obtaining different quality inspection data from the speech text quality inspection data set as current quality inspection data;

[0115] Step 402, performing semantic information encoding on the key value and the value value in the current quality inspection data, respectively, to obtain semantic information encoding results corresponding to the key value and the value value of all quality inspection data;

[0116] Specifically, the key value and value value in the current quality inspection data are respectively encoded with semantic information. Code values ​​can be set in advance for descriptive texts commonly used by the financial business salesperson when recommending service data. Thereafter, the codes and values ​​corresponding to the key value and value value in the current quality inspection data are obtained by cumulative calculation in combination with the code values ​​as semantic information codes.

[0117] Step 403, calculating the semantic coding distance between the value of the current quality inspection data and the key values ​​of other quality inspection data according to the semantic information coding results corresponding to the key values ​​and value values ​​of all quality inspection data;

[0118] Specifically, the difference between the code and value corresponding to the value of the current quality inspection data and the code and value corresponding to the key value of other quality inspection data is calculated, and the difference is used as the semantic coding distance. By sequentially obtaining different quality inspection data in step 401 as the current quality inspection data, the semantic coding distance between the key value and the value value of all quality inspection data can be obtained, so as to facilitate the subsequent combination of the semantic coding distance between the key value and the value value of all quality inspection data, and perform gradient arrangement on all quality inspection data to obtain a gradient arrangement result.

[0119] Step 404, performing gradient arrangement on all quality inspection data according to the relationship of semantic coding distance from small to large, and obtaining a gradient arrangement result;

[0120] Step 405: Generate the gradient optimization strategy according to the gradient arrangement result.

[0121] Among them, the gradient optimization strategy includes: if the transformed optimization words obtained after the current optimization still do not meet the push requirements, then filter out the next quality inspection data corresponding to the transformed optimization words from the gradient arrangement results; obtain the transformed optimization words of the next quality inspection data as the second transformed optimization words.

[0122] By generating the gradient optimization strategy, it is possible to implement multiple gradient transformation optimizations with one key data input, so that the automatic optimization model can achieve automated transformation optimization, saving manpower consumption for multiple inputs and being more automated and intelligent.

[0123] Step 303: deploy the gradient optimization strategy as optimization knowledge into a preset automatic optimization model, wherein the automatic optimization model includes a text automatic optimization model based on LLM.

[0124] By deploying the gradient optimization strategy as optimization knowledge into the preset automatic optimization model, it is possible to implement multiple gradient transformation optimizations with one key data input, so that the automatic optimization model can realize automated transformation optimization, saving the manpower consumption of multiple inputs, and being more automated and intelligent. The text automatic optimization model based on LLM, LLM (Large Language Model) refers to a large language model, which is a basic machine learning model that uses deep learning algorithms to process and understand natural language. These models are trained on a large amount of text data to learn patterns and entity relationships in the language. Therefore, the process from step 301 to step 303 can be implemented in the large language model, that is, the speech text quality inspection data set is used as text training data to train the large language model, and the trained large language model is obtained as the automatic optimization model. The purpose of its training is to generate the gradient optimization strategy and deploy the gradient optimization strategy as optimization knowledge into the automatic optimization model, so as to facilitate the subsequent direct use of the automatic optimization model to automatically transform and optimize the key data according to the gradient optimization strategy.

[0125] In this embodiment, if the key data includes non-compliant key data, the service push data is transformed and optimized to obtain the transformed and optimized service push data, which specifically includes: inputting the service push data into the automatic optimization model; identifying the non-compliant key data in the service push data through the key data classification result; iteratively transforming and optimizing all non-compliant key data according to the gradient optimization strategy; stopping the current round of iterative transformation and optimization until all non-compliant key data are converted into at least colloquial key data; replacing the transformed key data corresponding to all non-compliant key data with the corresponding positions in the service push data one by one to generate the transformed and optimized service push data.

[0126] Specifically, the above transformation and optimization content is the step of transforming and optimizing the service push data when it is detected that the key data contains illegal key data. It is preset that the current round of iterative transformation and optimization is stopped until all illegal key data are converted into at least colloquial key data. The number of times of this round of iterative transformation and optimization is determined by the gradient change of the gradient optimization strategy. Of course, different iteration termination conditions can also be set, for example: the proportion of illegal key data is less than a certain proportion value, the proportion of colloquial key data is less than a certain proportion value, which will not be described one by one here.

[0127] In this embodiment, the step of transforming and optimizing the service push data to obtain the transformed and optimized service push data also includes: inputting the service push data that does not meet the push requirements into the automatic optimization model; identifying the colloquial key data in the service push data through the key data classification results; iteratively transforming and optimizing all the colloquial key data according to the gradient optimization strategy; stopping this round of iterative transformation and optimization until all the colloquial key data are converted into at least standardized key data; replacing the transformed key data corresponding to all the colloquial key data one by one into the corresponding positions in the service push data to generate the transformed and optimized service push data.

[0128] Specifically, the above-mentioned transformation and optimization content is a step of transforming and optimizing the service push data that does not meet the push requirements after the push evaluation in step 206. At this time, since the service push data no longer has illegal key data, the termination condition of this round of iterative transformation and optimization is improved, that is, until all colloquial key data are at least converted into standardized key data, the current round of iterative transformation and optimization is stopped to ensure that the subsequently outputted transformed and optimized service recommendation data only contains standardized key data, that is, only contains professional terms in the speech text, thereby achieving business quality control for financial business sales personnel and making the service push data obtained by customers more diversified.

[0129] Step 206: According to the data scoring strategy preset in the service evaluation model, it is evaluated whether the current service push data meets the preset push requirements.

[0130] In this embodiment, before executing the step of evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model, the method also includes: setting all key values ​​and all value values ​​in the speech text quality inspection data set as service scoring fields and deploying them into the service evaluation model; setting service scores for each service scoring field according to the gradient arrangement results.

[0131] Specifically, since the gradient arrangement result is based on the relationship of semantic coding distance from small to large, all quality inspection data are gradient arranged, combined with the above-mentioned gradient optimization strategy, it includes: if the transformed optimization words obtained after the current optimization still do not meet the push requirements, then the next quality inspection data of the quality inspection data corresponding to the transformed optimization words is screened out from the gradient arrangement results; the transformed optimization words of the next quality inspection data are obtained as the second transformed optimization words, which can be understood as the changes in words transformed and optimized according to the gradient arrangement results, following the rule of "first transforming and optimizing from illegal key data to colloquial key data, and then transforming and optimizing from colloquial key data to standardized key data". Therefore, the service score corresponding to each service rating field increases sequentially according to the gradient arrangement result. For example, the four quality inspection data in the speech text quality inspection data set are (key1, value1), (key2, value2), (key3, value3), and (key4, value4), and the sequence relationship between the key values ​​and value values ​​in the four quality inspection data in the gradient arrangement result is exactly key1, value1, key2, value2, key3, value3, key4, value4. At this time, the service scores of key1, value1, key2, value2, key3, value3, key4, value4 are set to 2, 3, 4, 5, 6, 7, 8, and 9, respectively, in an increasing relationship.

[0132] By setting service scores for all key values ​​and all value values ​​in the speech text quality inspection data set in advance, it is convenient to evaluate whether the current service push data meets the preset push requirements in a scoring manner later.

[0133] Continue to refer Figure 5 , Figure 5 yes Figure 2 The flowchart of a specific embodiment of step 206 shown includes:

[0134] Step 501, identifying all service rating fields contained in the current service push data;

[0135] Step 502, performing summing and averaging processing on the service scores corresponding to all the service rating fields to obtain the service score mean corresponding to the current service push data;

[0136] Step 503, determining whether the service score average exceeds a preset score threshold;

[0137] Step 504: If the service score average does not exceed the score threshold, the current service push data does not meet the push requirement;

[0138] Step 505: If the service score average exceeds the score threshold, the current service push data meets the push requirement.

[0139] The scoring method is used to evaluate whether the current service push data meets the preset push requirements, making the push judgment method simpler and saving model computing resources.

[0140] Step 207: If the current service push data does not meet the push requirements, steps 205 to 206 are executed iteratively to transform and optimize the latest service push data and perform push evaluation until the current service push data meets the push requirements, and the iterative execution is stopped.

[0141] Step 208: If the current service push data meets the push requirement, the current service push data is sent to the target receiving end.

[0142] In this embodiment, after executing the step of sending the current service push data to the target receiving end, the method also includes: according to a preset transformation and optimization log, counting the total number of times the current service push data is transformed and optimized, wherein the transformation and optimization log is used to record the number of times all key data are transformed and optimized respectively; judging whether the total number of times the current service push data is transformed and optimized exceeds a preset number threshold; if the total number of times the current service push data is transformed and optimized exceeds the number threshold, sending feedback of excessive transformation and optimization times to the target management end; if the total number of times the current service push data is transformed and optimized does not exceed the number threshold, sending incentive feedback to the target service end.

[0143] Specifically, by counting the total number of times the current service push data has been modified and optimized, a comprehensive quality assessment can be made on the service push data input by the financial business salesperson, helping the target management end, for example: the business quality management system of a financial institution, to manage the quality of service push data for financial business recommendation personnel, so as to facilitate timely training for financial business recommendation personnel with a large number of modification and optimization times, and timely rewards for financial business recommendation personnel with a small number of modification and optimization times, so that financial institutions can conduct more humane management of financial business salespersons.

[0144] The service data push method described in the present application is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service data push method of the present application can be used to transform and optimize the service push data before the actual push, which can not only control the business quality of the financial business sales personnel, but also make the service push data obtained by the customer more diversified. At the same time, an automatic optimization model and a data evaluation model are introduced to automatically transform and optimize the service promotion data, and the final number of transformation and optimization can be identified in combination with the data evaluation model, which is convenient for the financial institution management system to provide business training and rewards to financial business recommendation personnel in a timely manner, making management more humane.

[0145] This application obtains service push data; performs semantic analysis to extract key data; performs iterative transformation and optimization on the service push data according to the key data to obtain the optimized service push data, and sends the current service push data to the target receiving end through evaluation until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified.

[0146] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0147] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0148] In the embodiment of the present application, service push data is obtained; semantic analysis is performed to extract key data; service push data is iteratively transformed and optimized according to key data to obtain the optimized service push data, and the current service push data is sent to the target receiving end through evaluation until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers, and the service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified.

[0149] Further references Figure 6 , as a response to the above Figure 2 The present application provides an embodiment of a service data push device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0150] like Figure 6 As shown, the service data push device 600 described in this embodiment includes: a service push data acquisition module 601, a key data extraction module 602, a violation judgment module 603, an evaluation and processing first branch module 604, an evaluation and processing second branch module 605, a push satisfaction judgment module 606, an iterative transformation optimization module 607 and a service push data sending module 608. Among them:

[0151] The service push data acquisition module 601 is used to acquire the service push data of the target server;

[0152] The key data extraction module 602 is used to perform semantic analysis on the service push data and extract key data;

[0153] The violation judgment module 603 is used to judge whether the key data contains violation key data;

[0154] The first branch module 604 of the evaluation process is used to input the service push data into a preset service evaluation model if the key data does not contain the key data of violation;

[0155] The second branch module 605 of the evaluation process is used to transform and optimize the service push data if the key data contains the key data of violation, obtain the transformed and optimized service push data, and input the service push data into the service evaluation model;

[0156] The push satisfaction judgment module 606 is used to evaluate whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model;

[0157] Iterative transformation and optimization module 607, used for iteratively transforming and optimizing the latest service push data and performing push evaluation if the current service push data does not meet the push requirement, until the current service push data meets the push requirement, and then stopping the iterative execution;

[0158] The service push data sending module 608 is used to send the current service push data to the target receiving end if the current service push data meets the push requirement.

[0159] This application obtains service push data; performs semantic analysis to extract key data; performs iterative transformation and optimization on the service push data according to the key data to obtain the optimized service push data, and sends the current service push data to the target receiving end through evaluation until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified.

[0160] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0161] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0162] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7This is a basic structural block diagram of the computer device in this embodiment.

[0163] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 7 with components 7a-7c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0164] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0165] The memory 7a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 7a can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 7a can also be an external storage device of the computer device 7, such as a plug-in hard disk equipped on the computer device 7, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 7a can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 7a is generally used to store the operating system and various application software installed on the computer device 7, such as a computer-readable instruction of a service data push method, etc. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or are to be output.

[0166] The processor 7b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 7b is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to run the computer-readable instructions stored in the memory 7a or process data, such as running the computer-readable instructions of the service data push method.

[0167] The network interface 7c may include a wireless network interface or a wired network interface. The network interface 7c is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0168] The computer device proposed in this embodiment belongs to the field of data processing technology and is applied to the service information introduction scenario. The present application obtains service push data; performs semantic analysis to extract key data; iteratively transforms and optimizes the service push data according to the key data to obtain the transformed and optimized service push data, and through evaluation, sends the current service push data to the target receiving end until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified.

[0169] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the service data push method as described above.

[0170] The computer-readable storage medium proposed in this embodiment belongs to the field of data processing technology and is applied to the service information introduction scenario. This application obtains service push data; performs semantic analysis to extract key data; iteratively transforms and optimizes the service push data according to the key data to obtain the transformed and optimized service push data, and through evaluation, sends the current service push data to the target receiving end until the current service push data meets the preset push requirements. The service data push method is applied to the scenario where financial business sales personnel promote products or introduce services to target customers. The service push data can be transformed and optimized multiple times before the actual push, which can not only control the service quality of financial business sales personnel, but also make the service push data obtained by customers more diversified.

[0171] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0172] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A service data push method, characterized in that: The steps include: Step 201, obtaining service push data of the target server; Step 202, performing semantic analysis on the service push data to extract key data; Step 203, determining whether the key data contains illegal key data; Step 204: if the key data does not contain any illegal key data, the service push data is input into a preset service evaluation model; Step 205: if the key data includes illegal key data, the service push data is transformed and optimized to obtain the transformed and optimized service push data, and the service push data is input into the service evaluation model; Step 206, evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model; Step 207: if the current service push data does not meet the push requirement, then iteratively execute steps 205 to 206 to perform transformation optimization and push evaluation on the latest service push data until the current service push data meets the push requirement, and then stop iterative execution; Step 208: If the current service push data meets the push requirement, the current service push data is sent to the target receiving end.

2. The service data push method according to claim 1, characterized in that: Before executing the step of performing semantic analysis on the service push data to extract key data, the method further includes: Constructing a key data dictionary based on the prophet's experience, wherein the key data dictionary includes non-compliant key data, colloquial key data, and standardized key data; Deploy the key data dictionary to the pre-trained semantic analysis model; The step of performing semantic analysis on the service push data to extract key data specifically includes: Inputting the service push data into the semantic analysis model, wherein the semantic analysis model is a semantic analysis model based on natural language processing technology; Performing semantic analysis on the service push data through the semantic analysis model, and screening out all key data contained in the service push data according to the semantic analysis result; After executing the step of performing semantic analysis on the service push data to extract key data, the method further includes: Based on the key data dictionary, all key data in the service push data are classified and processed to obtain key data classification results.

3. The service data push method according to claim 2, characterized in that: Before executing the step of transforming and optimizing the service push data to obtain the transformed and optimized service push data if the key data includes the illegal key data, the method further includes: Obtain a preset speech text quality inspection data set, wherein each quality inspection data in the speech text quality inspection data set is composed of a key value and a value value in a pair, the key value represents the detection hit word, and the value value represents the transformation optimization word; Generate a gradient optimization strategy based on the key value and value of each quality inspection data; The gradient optimization strategy is deployed as optimization knowledge into a preset automatic optimization model, wherein the automatic optimization model includes a text automatic optimization model based on LLM.

4. The service data push method according to claim 3, characterized in that: The step of generating a gradient optimization strategy according to the key value and value of each quality inspection data specifically includes: Sequentially obtain different quality inspection data from the speech text quality inspection data set as current quality inspection data; Semantically encode the key value and the value in the current quality inspection data to obtain the semantic information encoding results corresponding to the key value and the value of all quality inspection data; According to the semantic information encoding results corresponding to the key values ​​and value values ​​of all quality inspection data, the semantic encoding distance between the value value of the current quality inspection data and the key values ​​of other quality inspection data is calculated; According to the relationship from small to large semantic coding distance, all quality inspection data are gradient arranged to obtain the gradient arrangement result; The gradient optimization strategy is generated according to the gradient arrangement result, wherein the gradient optimization strategy includes: if the transformation optimization word obtained after the current optimization still does not meet the push requirements, then the next quality inspection data of the quality inspection data corresponding to the transformation optimization word is screened out from the gradient arrangement result; and the transformation optimization word of the next quality inspection data is obtained as the transformation optimization word again.

5. The service data push method according to claim 3 or 4, characterized in that: If the key data includes the illegal key data, the step of transforming and optimizing the service push data to obtain the transformed and optimized service push data specifically includes: Inputting the service push data into the automatic optimization model; Identifying illegal key data in the service push data through the key data classification result; According to the gradient optimization strategy, all the key data of violations are iteratively transformed and optimized respectively; This round of iterative transformation and optimization will be stopped until all illegal key data are converted into at least colloquial key data; Replacing the transformed key data corresponding to all the illegal key data with the corresponding positions in the service push data one by one, and generating transformed and optimized service push data; The step of transforming and optimizing the service push data to obtain the transformed and optimized service push data also includes: inputting the service push data that does not meet the push requirement into the automatic optimization model; identifying the colloquial key data in the service push data through the key data classification result; According to the gradient optimization strategy, all the key oral data are iteratively transformed and optimized respectively; This round of iterative transformation and optimization will be stopped until all colloquial key data are converted to at least standardized key data; The transformed key data corresponding to all the colloquial key data are replaced one by one into the corresponding positions in the service push data to generate the transformed and optimized service push data.

6. The service data push method according to claim 3, characterized in that: Before executing the step of evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model, the method further includes: All key values ​​and all value values ​​in the speech text quality inspection data set are set as service score fields and deployed into the service evaluation model; According to the gradient arrangement result, a service score is set for each service scoring field; The step of evaluating whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model specifically includes: Identify all service rating fields contained in the current service push data; The service scores corresponding to all the service scoring fields are summed and averaged to obtain the service score mean corresponding to the current service push data; Determining whether the service score average exceeds a preset score threshold; If the service score average does not exceed the score threshold, the current service push data does not meet the push requirement; If the service score average exceeds the score threshold, the current service push data meets the push requirement.

7. The service data push method according to claim 1, characterized in that: After executing the step of sending the current service push data to the target receiving end, the method further includes: According to the preset transformation and optimization log, count the total number of times the current service push data has been transformed and optimized; Determine whether the total number of times the current service push data is modified and optimized exceeds a preset number threshold; If the total number of times the current service push data is transformed and optimized exceeds the threshold, a feedback indicating that the number of transformation and optimization times is too many is sent to the target management end; If the total number of times the current service push data is modified and optimized does not exceed the number threshold, an incentive feedback is sent to the target server.

8. A service data push device, characterized in that: include: The service push data acquisition module is used to obtain the service push data of the target server; A key data extraction module, used to perform semantic analysis on the service push data and extract key data; A violation judgment module, used to judge whether the key data contains violation key data; The first branch module of the evaluation process is used for inputting the service push data into a preset service evaluation model if the key data does not contain the key data of violation; The second branch module of the evaluation process is used for, if the key data contains the key data of violation, transforming and optimizing the service push data, obtaining the transformed and optimized service push data, and inputting the service push data into the service evaluation model; A push satisfaction judgment module is used to evaluate whether the current service push data meets the preset push requirements according to the data scoring strategy preset in the service evaluation model; An iterative transformation and optimization module, for iteratively performing transformation and optimization and push evaluation on the latest service push data if the current service push data does not meet the push requirements, until the current service push data meets the push requirements, and then stopping the iterative execution; The service push data sending module is used to send the current service push data to the target receiving end if the current service push data meets the push requirement.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the service data pushing method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service data pushing method according to any one of claims 1 to 7 are implemented.

Images