Service data auxiliary management method and system

Abstract

The invention belongs to the technical field of data management, and provides a service data auxiliary management method and system. The method comprises the steps that a data request sent by a salesman terminal is received, the data request comprises customer information to be negotiated, and negotiation record data is called from a corresponding customer folder according to the customer information; a negotiation stage is obtained through evaluation according to the negotiation record data, a plurality of negotiation cases are determined according to the negotiation stage, and the negotiation cases comprise business quotation data; and sending the negotiation record data and each negotiation case to a salesman terminal. The business management platform receives a salesman terminal request, calls customer negotiation record data, analyzes negotiation stages, matches cases and sends the cases to the terminal, the problems that traditional negotiation depends on personal experience, and an existing system cannot achieve accurate assistance are effectively solved, data-driven intelligent management is achieved, targeted guidance can be provided for salesmen, and the service quality of the salesmen is improved. The negotiation efficiency and the transaction rate are improved, and the customer satisfaction is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a business data auxiliary management method and system. Background Art

[0002] In modern business activities, the efficiency and quality of negotiations between sales representatives and customers directly affect the business closing rate and customer satisfaction. In traditional business negotiation processes, sales representatives mainly rely on personal experience and memory to carry out their work. When faced with a large amount of customer information, it is difficult to quickly and accurately sort out customer needs and past communication situations. Key information is easily missed, resulting in a lack of targeted negotiations, which not only wastes the time of both parties but may also miss cooperation opportunities. Although there are some customer relationship management systems in the existing technology that can store and simply retrieve customer information, these systems are often unable to deeply analyze the historical negotiation records between sales representatives and customers. It is difficult to provide adaptive reference cases and strategic recommendations based on the different negotiation stages of customers. They cannot meet the sales representatives' needs for intelligent and personalized assistance in actual business scenarios.

[0003] Therefore, there is an urgent need for a management method that can effectively utilize historical business data and provide precise assistance to sales staff. Summary of the Invention

[0004] In response to the above technical problems, the present invention provides a business data auxiliary management method, system, electronic device, computer storage medium and computer program product to solve the problems of low measurement accuracy, complex equipment and high cost in the prior art.

[0005] The present invention discloses a business data auxiliary management method, which is applied to a business management platform. The method comprises the following steps:

[0006] Receiving a data request sent by a salesperson terminal, the data request including customer information to be negotiated, and retrieving negotiation record data from a corresponding customer folder based on the customer information;

[0007] Determining a negotiation stage based on the negotiation record data, and determining a number of negotiation cases based on the negotiation stage, wherein the negotiation cases include business quotation data;

[0008] The negotiation record data and each negotiation case are sent to the salesperson terminal.

[0009] The present invention also discloses a business data auxiliary management system, which is applied to a business management platform. The system includes at least one processor and a memory, in which computer code is stored. The processor calls and executes the computer code stored in the memory to implement the method described in any of the preceding items.

[0010] Optionally, the system further includes a negotiation case library in which a plurality of negotiation cases are stored.

[0011] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the methods described above.

[0012] The present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in any of the above items.

[0013] The present invention further discloses a computer program product, which includes computer code. When the computer code is executed by a processor of an electronic device, the method described in any of the above items is implemented.

[0014] The solution of the present invention receives salesperson terminal requests through the business management platform, retrieves customer negotiation record data, analyzes the negotiation stage, matches cases and sends them to the terminal, effectively solving the problem that traditional negotiations rely on personal experience and the existing system cannot provide accurate assistance, realizes data-driven intelligent management, can provide targeted guidance for salespeople, improve negotiation efficiency and transaction rate, and enhance customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 This is a flow chart of a business data auxiliary management method disclosed in an embodiment of the present invention;

[0017] Figure 2 It is a structural diagram of a business data auxiliary management system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following specific embodiments illustrate the implementation of this application. Those familiar with the art can easily understand the other advantages and functions of this application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0020] like Figure 1 As shown, in order to solve the above technical problems, an embodiment of the present invention discloses a business data auxiliary management method, which is applied to a business management platform. The method includes the following steps:

[0021] S1, receiving a data request sent by a salesperson terminal, wherein the data request includes customer information to be negotiated, and retrieving negotiation record data from a corresponding customer folder according to the customer information.

[0022] The business management platform maintains a communication connection with the salesperson's terminal. When the salesperson prepares to negotiate with a customer, a data request is initiated on the salesperson's terminal. This request contains relevant information about the customer to be negotiated, such as the customer name and number. After receiving the request, the business management platform uses the customer information as an index to quickly locate the corresponding pre-set customer folder. This customer folder stores all past negotiation records related to the customer, including the time of each negotiation, the content of the communication, customer feedback, and other information. This folder may have been created by the salesperson on the business management platform during the initial negotiation with the customer, and all data and information related to the entire negotiation process are stored in this folder.

[0023] S2, evaluating the negotiation record data to obtain a negotiation stage, and determining a number of negotiation cases based on the negotiation stage, wherein the negotiation cases include business quotation data.

[0024] After the business management platform obtains the negotiation record data, it analyzes the key information, communication frequency, changes in customer focus, and other content in the negotiation record to determine the current negotiation stage of the customer, such as the initial contact stage, demand clarification stage, quotation negotiation stage, etc.

[0025] After determining the negotiation stage, the business management platform selects several negotiation cases from a pre-set case library that are suitable for that negotiation stage. These negotiation cases not only include successful negotiation strategies and sales pitches, but also include business quotation data, which is based on a variety of factors such as past similar business scenarios, customer types, and market conditions.

[0026] This step, through analysis of historical data and case matching, provides sales representatives with targeted guidance that fits the actual negotiation stage, reducing the probability of sales representatives falling into a passive position during negotiations due to lack of experience or insufficient information.

[0027] S3, sending the negotiation record data and each negotiation case to the salesperson terminal.

[0028] The business management platform packages and integrates the retrieved negotiation record data and selected negotiation cases, and then sends them to the salesperson's terminal. The salesperson can view this data and cases on the terminal, and during the negotiation process, they can refer to past negotiation records at any time to understand the customer's historical needs and feedback. They can also draw on successful cases and quotation strategies from similar negotiation stages to flexibly adjust their negotiation plans, thereby improving the success rate and efficiency of negotiations. The solution of this invention is particularly suitable for situations where the salesperson for a specific enterprise has changed.

[0029] The above-mentioned solution of the present invention receives salesperson terminal requests through the business management platform, retrieves customer negotiation record data, analyzes the negotiation stage and matches cases and sends them to the terminal, effectively solving the problem that traditional negotiations rely on personal experience and the existing system cannot provide accurate assistance, and realizes data-driven intelligent management. It can provide targeted guidance for salespeople, improve negotiation efficiency and transaction rate, and enhance customer satisfaction.

[0030] Optionally, evaluating and determining the negotiation stage based on the negotiation record data includes:

[0031] The negotiation record data is evaluated using a generative adversarial network to obtain the negotiation stage; the generative adversarial network includes a generator and a discriminator, and is pre-trained in the following manner:

[0032] The generator is used to receive a random noise vector and generate a number of simulated negotiation record data based on the random noise vector and real negotiation record data. The characteristic dimensions of the simulated negotiation record data are consistent with the real negotiation record data. The simulated negotiation record data includes negotiation time interval, communication frequency, customer feedback attitude, and degree of demand clarity; the discriminator is used to determine whether the input data is real negotiation record data or simulated negotiation record data generated by the generator.

[0033] Traditional assessment methods struggle to process the nonlinear relationships and underlying patterns found in complex negotiation records. Generative adversarial networks, however, possess powerful learning capabilities and can automatically extract features and patterns from data, enabling more accurate assessment of negotiation stages. Therefore, this paper employs a generative adversarial network to assess the current negotiation stage.

[0034] During training, the generator and discriminator undergo adversarial training. The generator continuously adjusts its parameters to generate simulated negotiation data that is closer to real negotiation data, while the discriminator continuously improves its ability to distinguish between real and simulated negotiation data. The generative adversarial network (GAN) comprises a generator and a discriminator. Through pre-training, the two networks learn from and reinforce each other, adapting the entire generator and discriminator network to the characteristics and patterns of negotiation data, thereby improving the accuracy of the assessment. A pre-trained GAN can better understand the distribution and characteristic patterns of negotiation data. The specific training process is as follows:

[0035] Because real negotiation records often suffer from limited quantity and uneven distribution, the present invention employs a generator that generates simulated data by introducing random noise vectors and combining them with real data. This increases the data volume and diversity, allowing the generative adversarial network to learn from a wider range of data, enabling it to accurately assess the negotiation stage across a wide range of negotiation record types. It is understood that the simulated negotiation record data generated by the generator should have consistent feature dimensions with real negotiation record data, specifically including negotiation time interval, communication frequency, customer feedback attitude, and demand clarity.

[0036] The negotiation interval refers to the time span between two consecutive negotiations between a salesperson and a customer. A shorter interval indicates a higher level of customer interest or a more urgent desire to cooperate; a longer interval indicates a temporary decrease in customer interest or a wait-and-see attitude. To quantify the negotiation interval, the interval can be calculated in calendar days, for example, a one-day interval is recorded as 1, a seven-day interval as 7, and any interval exceeding 30 days is recorded as 30.

[0037] Communication frequency refers to the number of times a salesperson communicates with a customer during a specific time period. A high frequency reflects active customer participation or focused follow-up by the salesperson; a low frequency indicates insufficient interaction between the two parties. Numerical processing of communication frequency can be performed directly using the actual number of communications, for example, three communications in a week would be recorded as 3. If the number of communications is excessive (e.g., more than 10 times), normalization can be performed, with all communications of 10 or more recorded as 10, to ensure that the data remains within a reasonable range.

[0038] Customer feedback attitude is used to represent the customer's attitude toward the business during the negotiation process and is categorized as positive, neutral, or negative. A positive attitude indicates that the customer is interested in the business and approves of the product or service; a neutral attitude means that the customer has not yet made a firm commitment and is in the observation and evaluation phase; and a negative attitude indicates that the customer has doubts or refuses to cooperate. A positive attitude can be assigned a value of 3, a neutral attitude a value of 2, and a negative attitude a value of 1, thereby achieving numerical processing.

[0039] Demand clarity measures the degree of clarity of a customer's needs. Clear needs indicate that the customer clearly understands what they need, which helps accurately match business needs. Ambiguous needs may require further guidance and exploration by sales representatives. Numerical processing can categorize demand clarity into three levels: completely clear needs are recorded as 3, partially clear needs are recorded as 2, and ambiguous needs are recorded as 1. Demand clarity can be assessed using the following specific numerical parameters:

[0040] Number of Requirement Clauses: Count the number of specific requirement clauses explicitly raised by the customer during the negotiation. For example, during equipment procurement negotiations, the customer may raise specific requirements regarding the equipment's technical specifications, after-sales service, delivery time, and other aspects. Each explicit requirement can be considered a clause. If the customer raises 10 explicit requirement clauses, it indicates a high level of clarity; if only 2-3 are raised, the clarity is relatively low.

[0041] Richness of Requirement Details: Scoring can be done based on the level of detail provided by the customer for each requirement point. For example, for a product feature requirement, if the customer can provide a detailed description of the feature's specific operational procedures, expected results, and how it interacts with other features, a higher score (e.g., 8-10) may be given. If the customer simply mentions the feature name without specific details, a lower score (e.g., 1-3) may be given. The scores for all requirement points are summed and averaged to obtain a numerical value for the richness of requirement details. A higher value indicates a more defined requirement.

[0042] Number of Requirements Changes: During the negotiation process, record the number of times the client changes their previously proposed requirements. If the client frequently changes previously proposed requirements late in the negotiation, it indicates that their initial requirements were not clear enough and may be undergoing continuous adjustment and reflection. For example, during a project collaboration negotiation, the client made three significant changes to the project's objectives, scope, and deliverables within a week, indicating a lack of clarity in their requirements. This parameter is expressed as the number of changes; fewer changes indicate a higher level of clarity.

[0043] During training, the generator and discriminator engage in adversarial training. The generator continuously optimizes its generation to make it difficult for the discriminator to distinguish, while the discriminator continuously improves its discrimination capabilities to accurately distinguish. This competitive mechanism drives the continuous evolution of the entire network. After sufficient adversarial training, the generative adversarial network can accurately capture the inherent characteristics and patterns of negotiation record data, thereby more accurately assessing the negotiation stage and providing more effective support for business negotiations.

[0044] Optionally, the generator and the discriminator are subjected to adversarial training during the training process, including:

[0045] During each training iteration, we analyze the data distribution differences and standard deviations of the input data (i.e., real negotiation records and simulated negotiation records) in terms of negotiation time interval, communication frequency, customer feedback attitude, and demand clarity.

[0046] The learning rate of the generator is adjusted according to the data distribution difference, and the parameters of the batch normalization layer in the generator network are adjusted according to the standard deviation.

[0047] During the adversarial training of a generative adversarial network (GAN), the learning rates of the generator and discriminator, as well as the parameters of the batch normalization layer in the generator network, directly affect the stability and convergence of the generative adversarial network during training. To this end, the present invention provides for dynamic adjustment of the learning rate and the parameters (scaling factor and offset factor) of the batch normalization layer in the generator network. The details are as follows:

[0048] (1) The learning rate controls the step size of the model parameter update. When the distribution difference between the real negotiation record data and the simulated negotiation record data is large, the generator needs more learning to approach the distribution of the real data. For example, in the characteristic dimension of communication frequency, the real data shows that the proportion of communication 3-5 times a week is high, while the simulated data is concentrated in 1-2 times a week, and the distribution difference between the two is obvious. If the learning rate of the generator is 0.001 at this time, it can be appropriately increased to 0.002, so that the generator can adjust the parameters faster to approach the real data distribution. A comparison table of the generator's learning rate and the data distribution difference (taking KL divergence as an example) is pre-established, as shown in Table 1 below:

[0049]

[0050]

[0051] Therefore, dynamically adjusting the learning rate of the generator according to the difference in data distribution can enable the generator to learn the distribution of real data more quickly while ensuring training accuracy, thereby improving the speed of adversarial training.

[0052] (2) The standard deviation reflects the degree of dispersion of the data. In real negotiation record data, the standard deviation of each feature dimension follows a certain pattern. For example, the standard deviation of the customer feedback attitude score in the real data is small, indicating that the customer feedback attitude is relatively concentrated; if the standard deviation of the simulated data on this feature dimension is too large, it indicates that the customer feedback attitude scores generated by the generator are too dispersed and lack stability. By analyzing the standard deviation, we can identify possible problems in the generator when generating data, and make targeted adjustments.

[0053] The batch normalization layer normalizes the input data to the network, aligning it to a mean of 0 and a standard deviation of 1. This accelerates network convergence and improves model stability. For example, the standard deviation of the real negotiation data is 0.8, while the standard deviation of the simulated negotiation data is 1.5, indicating that the distribution of the data generated by the generator on this feature dimension is unstable. In this case, the scaling and offset factors of the batch normalization layer are adjusted to make the simulated data more closely resemble the distribution of the real data on this feature dimension, as shown in Table 2 below:

[0054] Table 2

[0055] Standard Deviation Scaling Factor Offset Factor 0.1-0.3 0.9-1.1 -0.1-0.1 0.3-0.5 0.8-1.2 -0.2-0.2 0.5-0.7 0.7-1.3 -0.3-0.3 0.7-1.0 0.6-1.4 -0.4-0.4 1.0-1.5 0.5-1.5 -0.5-0.5

[0056] The standard deviation difference in Table 2 above refers to the difference between the standard deviation of all input real negotiation record data and the standard deviation of all input simulated negotiation record data.

[0057] It should be noted that the above data distribution differences and standard deviations are obtained by normalizing the data distribution differences and standard deviations of all dimensions and then weighting them.

[0058] Optionally, the plurality of negotiation cases determined according to the negotiation stage include:

[0059] Calculate the similarity between the current client's industry category, business scale, and number of historical collaborations and each case in the negotiation case library. Each negotiation case in the negotiation case library is labeled with the corresponding client's industry category, business scale, number of historical collaborations, and negotiation stage.

[0060] At a determined negotiation stage, a preset number of negotiation cases ranked top in similarity to the current customer are screened out. If the number of screened cases is less than the preset number, all cases at that negotiation stage are taken as the determined number of negotiation cases.

[0061] Clients in different industries have different business needs and cooperation models; the size of the business affects the scale, complexity, and decision-making process of the cooperation; the number of historical collaborations reflects the familiarity and trust between the two parties; and the negotiation stage ensures that the selected cases match the current stage of the client. Therefore, the present invention pre-constructs a negotiation case library, in which each stored negotiation case is labeled with the corresponding client's industry category, business scale, number of historical collaborations, and the negotiation stage.

[0062] Based on the current client's industry category, business scale, and number of historical collaborations, calculate their similarity with each case in the negotiation case database. The similarity calculation for each industry category, business scale, and number of historical collaborations can be performed using the Euclidean distance formula. Weights of 0.3, 0.4, and 0.3 are assigned to the industry category, business scale, and number of historical collaborations, respectively. The final similarity is then calculated using these weights.

[0063] Similar industry categories suggest commonalities in market environments and business needs; similar business scales suggest comparable resource inputs and risk tolerance; and similar historical collaborations reflect the closeness of the partnership and potential challenges. By comprehensively considering these factors, the calculated similarity can help identify more valuable case studies for current clients.

[0064] Cases at the same negotiation stage offer valuable insights into negotiation strategies, potential problems, and solutions. Selecting highly similar cases provides sales representatives with references that closely align with the current client's situation, helping them better formulate negotiation strategies. If the number of highly similar cases is insufficient, including all cases at that stage ensures sales representatives have as much reference information as possible, preventing decisions from being impacted by a lack of references.

[0065] Optionally, sending the negotiation record data and each negotiation case to the salesperson terminal includes:

[0066] Determining the number of keywords based on the similarity matching, and extracting keywords corresponding to the number of keywords from each of the negotiation cases using a semantic analysis component;

[0067] The keywords associated with the negotiation cases are displayed on a primary display interface, and the detailed content of the negotiation cases is displayed on a secondary display interface.

[0068] The present invention is designed to display each negotiation case in a hierarchical manner. The first-level display interface only displays the name or number of each negotiation case and several keywords, while the second-level display interface displays detailed information of the corresponding case. The second-level display interface can be called out based on the user's click operation. Specifically:

[0069] When faced with numerous negotiation cases, salespeople need to quickly grasp key information. By determining the number of keywords based on similarity matching and extracting corresponding keywords from negotiation cases, salespeople can present the most representative core information, helping them quickly understand the key points of the case, saving reading time and improving information acquisition efficiency.

[0070] First, the number of keywords to be extracted is determined based on the similarity calculation results between the current customer and each negotiation case. The higher the similarity, the stronger the relevance of the case to the current customer, and the greater the number of keywords that can be extracted. Then, the semantic analysis component is used to conduct an in-depth analysis of the negotiation case. The semantic analysis component identifies semantic units in the case text and selects keywords that accurately summarize the core content of the case by analyzing the semantic relationships between words and the context. For example, in a negotiation case regarding the sale of electronic products, the semantic analysis component may extract keywords such as "product model," "sales price," and "after-sales service."

[0071] The salesperson's terminal interface design presents keywords and case content in a layered display. The primary display interface presents keywords associated with each negotiation case. These keywords are arranged concisely and clearly, allowing salespeople to quickly scan and form a preliminary impression of multiple cases. When salespeople click on a keyword or the corresponding case icon, they are redirected to the secondary display interface, which displays the case details, including complete information such as the negotiation process, customer needs, solutions, and business quotes.

[0072] like Figure 2 As shown, an embodiment of the present invention also discloses a business data auxiliary management system, which is applied to a business management platform. The system includes at least one processor and a memory, and the memory stores computer code. The processor calls and executes the computer code stored in the memory to implement the method described in the above embodiment.

[0073] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the aforementioned embodiment.

[0074] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0075] An embodiment of the present invention further discloses a computer program product, which includes computer code. When the computer code is executed by a processor of an electronic device, the method described in the above embodiment is implemented.

[0076] The computer storage media mentioned above include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. Alternatively, the computer readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include electrical connections based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0077] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0078] The above specific embodiments do not constitute a limitation on the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A business data auxiliary management method, applied to a business management platform, characterized by: The method comprises the following steps: Receiving a data request sent by a salesperson terminal, the data request including customer information to be negotiated, and retrieving negotiation record data from a corresponding customer folder based on the customer information; Determining a negotiation stage based on the negotiation record data, and determining a number of negotiation cases based on the negotiation stage, wherein the negotiation cases include business quotation data; The negotiation record data and each negotiation case are sent to the salesperson terminal.

2. A business data auxiliary management method according to claim 1, characterized in that: The negotiation stage determined based on the negotiation record data evaluation includes: The negotiation record data is evaluated using a generative adversarial network to obtain the negotiation stage; the generative adversarial network includes a generator and a discriminator, and is pre-trained in the following manner: The generator is used to receive a random noise vector and generate a number of simulated negotiation record data based on the random noise vector and real negotiation record data. The characteristic dimensions of the simulated negotiation record data are consistent with the real negotiation record data. The simulated negotiation record data includes negotiation time interval, communication frequency, customer feedback attitude, and degree of demand clarity; the discriminator is used to determine whether the input data is real negotiation record data or simulated negotiation record data generated by the generator.

3. A business data auxiliary management method according to claim 2, characterized in that: During the training process, the generator and the discriminator perform adversarial training, including: During each training iteration, we analyze the data distribution differences and standard deviations of the input data (i.e., real negotiation records and simulated negotiation records) in terms of negotiation time interval, communication frequency, customer feedback attitude, and demand clarity. The learning rate of the generator is adjusted according to the data distribution difference, and the parameters of the batch normalization layer in the generator network are adjusted according to the standard deviation.

4. A business data auxiliary management method according to claim 3, characterized in that: Several negotiation cases are determined according to the negotiation stage, including: Calculate the similarity between the current client's industry category, business scale, and number of historical collaborations and each case in the negotiation case library. Each negotiation case in the negotiation case library is labeled with the corresponding client's industry category, business scale, number of historical collaborations, and negotiation stage. At a determined negotiation stage, a preset number of negotiation cases ranked top in similarity to the current customer are screened out. If the number of screened cases is less than the preset number, all cases at that negotiation stage are taken as the determined number of negotiation cases.

5. A business data auxiliary management method according to claim 4, characterized in that: The sending of the negotiation record data and each negotiation case to the salesperson terminal includes: Determining the number of keywords based on the similarity matching, and extracting keywords corresponding to the number of keywords from each of the negotiation cases using a semantic analysis component; The keywords associated with the negotiation cases are displayed on a primary display interface, and the detailed content of the negotiation cases is displayed on a secondary display interface.

6. A business data auxiliary management system, applied to a business management platform, characterized by: The system includes at least one processor and a memory, wherein the memory stores computer code, and the processor retrieves and executes the computer code stored in the memory to implement the method according to any one of claims 1 to 5.

7. The business data auxiliary management system according to claim 6, characterized in that: The system also includes a negotiation case library, in which a plurality of negotiation cases are stored.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 5.

9. A computer storage medium storing a computer program, wherein: The computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

10. A computer program product, characterized in that: The computer program product includes computer code, and when the computer code is executed by a processor of an electronic device, the method according to any one of claims 1 to 5 is implemented.

Images